CN112464081A - Project information matching method, device and storage medium - Google Patents

Abstract

The disclosure provides a project information matching method, a project information matching device and a storage medium, and relates to the technical field of computers, wherein the project information matching method comprises the following steps: acquiring a corresponding channel keyword in a channel corpus and a corresponding expert keyword in an expert corpus according to a demand keyword, and calculating a first association degree; selecting a candidate item matching combination and calculating a second association degree of the candidate item matching combination according to the requirement key words, the channel key words and the expert key words; calculating a third degree of association corresponding to the candidate item matching combination according to the first degree of association and the second degree of association to determine a target item matching combination; the method, the device and the storage medium disclosed by the invention have the advantages that the automatic matching of the supply and demand parties and the third-party transfer channel is realized, the manual searching and matching processes are reduced, the matching efficiency and precision are improved, the technology transfer conversion efficiency is improved, and the use experience of a user is improved.

Description

Project information matching method, device and storage medium

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for matching project information, and a storage medium.

Background

With the development of the internet, technology transfer gradually shifts to an online technology transfer platform for realization. The online technology transfer platform can break through the limit of time and space, make up the unbalance of regional development, accelerate the marketization of technological innovation, and reduce the transaction cost of technology transfer. Meanwhile, the online technology transfer platform can store a large amount of data including technical information, transaction content and the like of both technical supply and demand parties, so that on one hand, the timeliness of information is improved, and the opacity of the information is reduced; on the other hand, the information with large data volume puts higher requirements on the matching technology and the connection technology of the technology transfer platform, so that the communication and communication of the information are better promoted, the technology transfer channels of the supply and demand parties and the third party are matched, and the technology transfer is promoted. At present, although an online technology transfer platform has a lot of data, the matching process still carries out matching of corresponding items through manual retrieval of information by both parties of supply and demand or according to platform tag data, the matching efficiency is low and even the matching precision is not high, and automatic matching of technology supply and demand is not realized.

Disclosure of Invention

The present disclosure is proposed to solve the above technical problems. The embodiment of the disclosure provides a project information matching method, a project information matching device and a storage medium.

According to a first aspect of the embodiments of the present disclosure, there is provided a project information matching method, including: receiving project demand information, and acquiring demand keywords from a demand corpus based on the project demand information; acquiring a corresponding channel keyword in a channel corpus and a corresponding expert keyword in an expert corpus according to the requirement keyword; calculating a first association degree among the requirement keywords, the channel keywords and the expert keywords; selecting a candidate item matching combination and calculating a second association degree of the candidate item matching combination according to the requirement keyword, the channel keyword and the expert keyword; wherein the candidate item matching combination comprises: the project requirement information, current channel information corresponding to the project requirement information and current expert information; and calculating a third degree of association corresponding to the candidate item matching combination according to the first degree of association and the second degree of association, and determining a target item matching combination from the candidate item matching combination based on the third degree of association.

Optionally, history project information which is transferred or converted successfully is obtained, the requirement keywords, the channel keywords and the expert keywords are extracted from the history project information, and corresponding word vectors are calculated; and respectively storing the requirement keywords, the channel keywords, the expert keywords and the corresponding word vectors in the requirement corpus, the channel corpus and the expert corpus.

Optionally, the extracting the requirement keyword, the channel keyword, the expert keyword, and the corresponding word vector from the historical item information includes: performing word segmentation processing and preprocessing on the historical project information to obtain the requirement keywords, the channel keywords and the expert keywords; vectorizing the demand keywords, the channel keywords and the expert keywords respectively to obtain word vectors; respectively calculating word frequency TF and inverse document frequency IDF of the requirement key words, the channel key words and the expert key words to obtain TF-IDF values corresponding to the requirement key words, the channel key words and the expert key words; and respectively selecting a preset number of demand keywords, channel keywords and expert keywords based on a preset sequencing rule and according to the TF-IDF value.

Optionally, the requirement corpus comprises: a demand attribute word bank and a demand target word bank; the acquiring of the demand keyword from the demand corpus based on the project demand information includes: acquiring a requirement item attribute keyword and a requirement item target keyword from the requirement attribute word bank and the requirement target word bank respectively based on the item requirement information;

optionally, the channel corpus comprises: a channel attribute word thesaurus, a channel target word thesaurus and a channel success word thesaurus; the expert corpus comprises: an expert attribute word lexicon and an expert success word lexicon; the acquiring of the channel keywords corresponding to the channel corpus and the expert keywords corresponding to the expert corpus according to the requirement keywords comprises: setting a first library group and a second library group; wherein the first library set comprises: the requirement attribute word library, the channel attribute word library and the expert attribute word library; the second library set includes: a demand target word lexicon, a channel success word lexicon and an expert success word lexicon; acquiring corresponding channel attribute keywords and expert attribute keywords from the channel attribute word bank and the expert attribute word bank in the first bank group according to the requirement item attribute keywords; establishing at least one first keyword group based on the corresponding relation among the requirement item attribute keywords, the channel attribute keywords and the expert attribute keywords; acquiring corresponding channel target item keywords, channel success item keywords and expert success item keywords from the channel target word thesaurus, the channel success word thesaurus and the expert success word thesaurus in the second library group according to the requirement item target keywords; and establishing at least one second keyword group based on the corresponding relation among the requirement project target keyword, the channel target project keyword, the channel success project keyword and the expert success project keyword.

Optionally, the calculating a first degree of association among the requirement keyword, the channel keyword, and the expert keyword includes: acquiring a word vector of each keyword in the first keyword group, and calculating attribute association degree corresponding to the first keyword group based on the word vector; acquiring a word vector of each keyword in the second keyword group, and calculating a target association degree corresponding to the second keyword group based on the word vector; calculating the first degree of association based on the attribute degree of association and the target degree of association.

Optionally, the calculating the attribute association degree corresponding to the first keyword group includes: calculating a first distance between word vectors of every two keywords in the requirement item attribute keywords, the channel attribute keywords and the expert attribute keywords, and taking the product of the three first distances as the attribute association degree; the calculating the target association degree corresponding to the second keyword group comprises: calculating a second distance between word vectors of every two keywords in the requirement project target keywords, the channel target project keywords and the expert success project keywords, and taking the product of the three second distances as a first sub-project association degree; calculating a third distance between word vectors of every two keywords in the requirement project target keywords, the channel success project keywords and the expert success project keywords, and taking the product of the three third distances as a second sub-target association degree; calculating the average sum of the first sub-target relevance and the second sub-target relevance as the target relevance; the calculating the first degree of association based on the attribute degree of association and the target degree of association includes: and calculating the first relevance based on all the attribute relevance and all the target relevance.

Optionally, the selecting a candidate item matching combination according to the requirement keyword, the channel keyword and the expert keyword comprises: generating a demand keyword set according to the demand item attribute keywords and the demand item target keywords; generating a channel keyword set according to the channel attribute keywords, the channel target project keywords and the channel success project keywords; generating an expert keyword set according to the expert attribute keywords and the expert success project keywords; selecting the current channel information based on the channel keyword set; wherein the current channel information comprises at least one first keyword in the channel keyword set; selecting the current expert information based on the expert keyword set; wherein the current expert information comprises at least one second keyword in the expert keyword set; and generating the candidate project matching combination according to the project demand information, the current channel information and the current expert information.

Optionally, the calculating the second degree of association of the candidate item matching combination includes: acquiring all first keywords in the channel keyword set contained in the current channel information; determining a corresponding first association coefficient based on a word bank to which the first keyword belongs; calculating a first matching correlation degree of the current channel information based on all first correlation coefficients; acquiring all second keywords in the expert keyword set contained in the current expert information; determining a corresponding second association coefficient based on a word bank to which the second keyword belongs; calculating a second matching correlation degree of the current expert information based on all second correlation coefficients; and calculating the second relevance according to the first matching relevance and the second matching relevance.

Optionally, the calculating a third degree of association corresponding to the candidate item matching combination according to the first degree of association and the second degree of association, and the determining a target item matching combination from the candidate item matching combination based on the third degree of association includes: taking the sum of the first relevance degree and the second relevance degree or the product of the first relevance degree and the second relevance degree as the third relevance degree; and determining the candidate item matching combination corresponding to the maximum third association degree as the target item matching combination.

According to a second aspect of the embodiments of the present disclosure, there is provided an item information matching apparatus including: the first keyword acquisition module is used for receiving project demand information and acquiring a demand keyword from a demand corpus based on the project demand information; the second keyword acquisition module is used for acquiring corresponding channel keywords in the channel corpus and corresponding expert keywords in the expert corpus according to the requirement keywords; the first association degree calculation module is used for calculating a first association degree among the requirement keywords, the channel keywords and the expert keywords; the second association degree calculation module is used for selecting a candidate item matching combination and calculating the second association degree of the candidate item matching combination according to the requirement keyword, the channel keyword and the expert keyword; wherein the candidate item matching combination comprises: the project requirement information, current channel information corresponding to the project requirement information and current expert information; and the target item matching determination module is used for calculating a third degree of association corresponding to the candidate item matching combination according to the first degree of association and the second degree of association and determining a target item matching combination from the candidate item matching combination based on the third degree of association.

Optionally, the corpus construction module is configured to obtain history project information that is transferred or converted successfully, extract the requirement keyword, the channel keyword, and the expert keyword from the history project information, and calculate a corresponding word vector; and respectively storing the requirement keywords, the channel keywords, the expert keywords and the corresponding word vectors in the requirement corpus, the channel corpus and the expert corpus.

Optionally, the corpus construction module includes: the keyword processing unit is used for performing word segmentation processing on the historical project information and preprocessing the historical project information to obtain the requirement keywords, the channel keywords and the expert keywords; vectorizing the demand keywords, the channel keywords and the expert keywords respectively to obtain word vectors; a keyword selecting unit, configured to calculate a word frequency TF and an inverse document frequency IDF where the demand keyword, the channel keyword, and the expert keyword occur, respectively, and obtain TF-IDF values corresponding to the demand keyword, the channel keyword, and the expert keyword; and respectively selecting a preset number of demand keywords, channel keywords and expert keywords based on a preset sequencing rule and according to the TF-IDF value.

Optionally, the requirement corpus comprises: a demand attribute word bank and a demand target word bank; the first keyword obtaining module is used for obtaining a requirement project attribute keyword and a requirement project target keyword from the requirement attribute word bank and the requirement target word bank respectively based on the project requirement information.

Optionally, the channel corpus comprises: a channel attribute word thesaurus, a channel target word thesaurus and a channel success word thesaurus; the expert corpus comprises: an expert attribute word lexicon and an expert success word lexicon; the second keyword obtaining module includes: the keyword matching unit is used for setting a first library group and respectively acquiring corresponding channel attribute keywords and expert attribute keywords from the channel attribute word library and the expert attribute word library in the first library group according to the requirement item attribute keywords; the first library set includes: the requirement attribute word library, the channel attribute word library and the expert attribute word library; the phrase establishing unit is used for establishing at least one first keyword phrase based on the corresponding relation among the requirement item attribute key words, the channel attribute key words and the expert attribute key words; the keyword matching unit is used for setting a second library group and respectively acquiring corresponding channel target item keywords, channel success item keywords and expert success item keywords from the channel target word thesaurus, the channel success word thesaurus and the expert success word thesaurus in the second library group according to the requirement item target keywords; the second library set includes: a demand target word lexicon, a channel success word lexicon and an expert success word lexicon; the phrase establishing unit is used for establishing at least one second keyword phrase based on the corresponding relation among the requirement item target keyword, the channel target item keyword, the channel success item keyword and the expert success item keyword.

Optionally, the first relevance calculating module includes: the attribute association calculation unit is used for acquiring a word vector of each keyword in the first keyword group and calculating the attribute association degree corresponding to the first keyword group based on the word vector; the target association calculation unit is used for acquiring a word vector of each keyword in the second keyword group and calculating a target association degree corresponding to the second keyword group based on the word vector; and the comprehensive association calculating unit is used for calculating the first association degree based on the attribute association degree and the target association degree.

Optionally, the attribute association calculating unit is configured to calculate a first distance between word vectors of every two keywords of the requirement item attribute keyword, the channel attribute keyword, and the expert attribute keyword, and take a product of the three first distances as the attribute association degree; the target association calculation unit is used for calculating a second distance between word vectors of every two keywords in the requirement project target keywords, the channel target project keywords and the expert success project keywords, and taking the product of the three second distances as a first sub-target association degree; calculating a third distance between word vectors of every two keywords in the requirement project target keywords, the channel success project keywords and the expert success project keywords, and taking the product of the three third distances as a second sub-target association degree; calculating the average sum of the first sub-target relevance and the second sub-target relevance as the target relevance; and the comprehensive association calculating unit is used for calculating the first association degree based on all the attribute association degrees and all the target association degrees.

Optionally, the second relevance calculating module includes: the project matching combination obtaining unit is used for generating a demand keyword set according to the demand project attribute keywords and the demand project target keywords; generating a channel keyword set according to the channel attribute keywords, the channel target project keywords and the channel success project keywords; generating an expert keyword set according to the expert attribute keywords and the expert success project keywords; selecting the current channel information based on the channel keyword set; wherein the current channel information comprises at least one first keyword in the channel keyword set; selecting the current expert information based on the expert keyword set; wherein the current expert information comprises at least one second keyword in the expert keyword set; and generating the candidate project matching combination according to the project demand information, the current channel information and the current expert information.

Optionally, the second relevance calculating module includes: the matching correlation calculation unit is used for acquiring all first keywords in the channel keyword set contained in the current channel information; determining a corresponding first association coefficient based on a word bank to which the first keyword belongs; calculating a first matching correlation degree of the current channel information based on all first correlation coefficients; acquiring all second keywords in the expert keyword set contained in the current expert information, and determining a corresponding second correlation coefficient based on a word bank to which the second keywords belong; calculating a second matching correlation degree of the current expert information based on all second correlation coefficients; and calculating the second relevance according to the first matching relevance and the second matching relevance.

Optionally, the target item matching determining module is configured to use a sum of the first relevance degree and the second relevance degree or a product of the first relevance degree and the second relevance degree as the third relevance degree; and determining the candidate item matching combination corresponding to the maximum third association degree as the target item matching combination.

According to a third aspect of the embodiments of the present disclosure, there is provided an item information matching apparatus including: a processor; a memory for storing the processor-executable instructions; the processor is used for reading the executable instructions from the memory and executing the instructions to realize the method.

According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing the above-mentioned method.

Based on the project information matching method, device and storage medium provided by the embodiment of the disclosure, the corresponding channel keywords in the channel corpus and the corresponding expert keywords in the expert corpus are obtained according to the requirement keywords, and the first association degree is calculated; selecting a candidate item matching combination and calculating a second association degree of the candidate item matching combination according to the requirement key words, the channel key words and the expert key words; calculating a third degree of association corresponding to the candidate item matching combination according to the first degree of association and the second degree of association to determine a target item matching combination; the automatic matching between the supply and demand parties and the third-party transfer channel is realized, the manual searching and matching processes are reduced, the matching efficiency and precision are improved, the technology transfer conversion efficiency is improved, and the use experience of the user is improved.

The technical solution of the present disclosure is further described in detail by the accompanying drawings and examples.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent by describing in more detail embodiments of the present disclosure with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the disclosure, and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the principles of the disclosure and not to limit the disclosure. In the drawings, like reference numbers generally represent like parts or steps.

FIG. 1 is a schematic flow chart diagram illustrating one embodiment of a project information matching method of the present disclosure;

FIG. 2 is a schematic flow chart illustrating a corpus establishment process according to an embodiment of the project information matching method of the present disclosure;

FIG. 3 is a schematic diagram of a process of extracting keywords according to an embodiment of the project information matching method of the present disclosure;

FIG. 4A is a diagram illustrating obtaining a requirement keyword from a requirement corpus based on project requirement information;

fig. 4B is a flowchart illustrating a process of calculating a first degree of association in an embodiment of the project information matching method of the present disclosure;

fig. 5 is a flowchart illustrating a second relevance calculation process in an embodiment of the item information matching method of the present disclosure;

FIG. 6 is a schematic flow chart illustrating the determination of a target item matching combination according to an embodiment of the item information matching method of the present disclosure;

FIG. 7 is a block diagram illustrating an embodiment of an apparatus for matching project information according to the present disclosure;

FIG. 8 is a block diagram of another embodiment of an item information matching apparatus of the present disclosure;

FIG. 9 is a schematic block diagram of a corpus building module in an embodiment of an apparatus for matching project information according to the present disclosure;

FIG. 10 is a block diagram of a second keyword obtaining module in an embodiment of an apparatus for matching item information according to the present disclosure;

FIG. 11 is a block diagram of a first relevance calculating module in an embodiment of the project information matching apparatus of the present disclosure;

fig. 12 is a block diagram of a second relevance calculating module in an embodiment of the item information matching apparatus of the present disclosure;

fig. 13 is a schematic structural diagram of another embodiment of the item information matching apparatus according to the present disclosure.

Detailed Description

Example embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of the embodiments of the present disclosure and not all embodiments of the present disclosure, with the understanding that the present disclosure is not limited to the example embodiments described herein.

It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.

It will be understood by those of skill in the art that the terms "first," "second," and the like in the embodiments of the present disclosure are used merely to distinguish one element from another, and are not intended to imply any particular technical meaning, nor is the necessary logical order between them.

It is also understood that in embodiments of the present disclosure, "a plurality" may refer to two or more than two and "at least one" may refer to one, two or more than two.

It is also to be understood that any reference to any component, data, or structure in the embodiments of the disclosure, may be generally understood as one or more, unless explicitly defined otherwise or stated otherwise.

In addition, the term "and/or" in the present disclosure is only one kind of association relationship describing the associated object, and means that there may be three kinds of relationships, such as a and/or B, and may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the former and latter associated objects are in an "or" relationship.

It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and the same or similar parts may be referred to each other, so that the descriptions thereof are omitted for brevity.

Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.

Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

Embodiments of the present disclosure may be implemented in electronic devices such as terminal devices, computer systems, servers, etc., which are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with an electronic device, such as a terminal device, computer system, or server, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set top boxes, programmable consumer electronics, network pcs, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above, and the like.

Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be implemented in a distributed cloud computing environment. In a distributed cloud computing environment, tasks may be performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.

Exemplary method

Fig. 1 is a flowchart of an embodiment of an item information matching method of the present disclosure, where the method shown in fig. 1 includes the steps of: S101-S105. The following describes each step.

S101, receiving project requirement information, and acquiring requirement keywords from a requirement corpus based on the project requirement information.

In one embodiment, the relevant project requirement information is filled in after the user logs in the technical platform. The project requirement information can be project information needing technical transfer, transaction and the like, and comprises information such as requirement enterprises, requirement states, technical requirement names, requirement fields, technical keywords, technical requirement categories, requirement specific contents and the like. A demand corpus is established in advance, and demand keywords are stored in the demand corpus.

S102, acquiring the corresponding channel keywords in the channel corpus and the corresponding expert keywords in the expert corpus according to the requirement keywords.

In one embodiment, a channel corpus and an expert corpus are pre-established, and channel keywords and expert keywords are stored in the channel corpus and the expert corpus, respectively. The existing various matching methods can be adopted to match channel keywords and expert keywords similar to the required keywords in the channel corpus and the expert corpus respectively according to the required keywords; the matching method can be an existing semantic analysis matching method and the like.

S103, calculating a first association degree among the requirement keywords, the channel keywords and the expert keywords.

And S104, selecting a candidate item matching combination and calculating a second association degree of the candidate item matching combination according to the requirement keyword, the channel keyword and the expert keyword.

In one embodiment, the candidate matching combination includes: the system comprises project requirement information, current channel information corresponding to the project requirement information and current expert information. The current channel information is the channel information currently in an effective state, and the channel information can be technical broker information and the like; the current expert information may be expert information currently in an active state, and the expert information may be technical expert information or the like.

For example, the channel information is technical broker information for transferring the conversion channel, and includes personal resume, professional expertise, and personal performance. The expert information includes basic information, technical fields, technical keywords, main work and study experiences, main research directions, project experiences and the like.

And S105, calculating a third degree of association corresponding to the candidate item matching combination according to the first degree of association and the second degree of association, and determining a target item matching combination from the candidate item matching combination based on the third degree of association.

In one embodiment, after the target project matching combination is determined, current channel information and current expert information in the target project matching combination are obtained, the current channel information and the current expert information are pushed to a user publishing project demand information, automatic matching between a technology transfer supply and demand side and a transfer channel is achieved, and a technology broker and an expert corresponding to a matching result are recommended to the user.

Fig. 2 is a schematic flowchart of establishing a corpus in an embodiment of the project information matching method of the present disclosure, and the method shown in fig. 2 includes the steps of: S201-S202. The following describes each step.

S201, obtaining history project information which is transferred or converted successfully, extracting requirement keywords, channel keywords and expert keywords from the history project information, and calculating corresponding word vectors.

In one embodiment, the history item information of successful transfer or conversion includes history item requirement information of successful transfer or conversion, and channel information and expert information corresponding to the history item requirement information. After the information transfer or conversion of one project requirement is successful, the related information is stored.

S202, storing the requirement keywords, the channel keywords, the expert keywords and the corresponding word vectors in a requirement corpus, a channel corpus and an expert corpus respectively.

Fig. 3 is a schematic flowchart of a keyword extraction process in an embodiment of the item information matching method of the present disclosure, where the method shown in fig. 3 includes the steps of: S301-S304. The following describes each step.

S301, performing word segmentation processing and preprocessing on the historical project information to obtain a requirement keyword, a channel keyword and an expert keyword.

S302, vectorization processing is carried out on the requirement keywords, the channel keywords and the expert keywords respectively to obtain word vectors.

S303, respectively calculating the word frequency TF and the inverse document frequency IDF of the requirement key words, the channel key words and the expert key words to obtain TF-IDF values corresponding to the requirement key words, the channel key words and the expert key words.

S304, respectively selecting a preset number of demand keywords, channel keywords and expert keywords based on a preset sequencing rule and according to the TF-IDF value. The predetermined number may be set to 300, for example, and 300 demand keywords, channel keywords, and expert keywords with the highest TF-IDF value are stored in the demand corpus, the channel corpus, and the expert corpus, respectively.

The historical item information can be subjected to word segmentation processing and preprocessing by using various existing methods, and a word vector and a TF-IDF value are obtained. For example, history item information that is successfully transferred or converted is acquired, the history item information is text data, and word segmentation processing and preprocessing are performed on the history item information to acquire a plurality of words. And (3) carrying out vectorization processing on a plurality of words by using the existing Skip-gram model of Word2vec to obtain each Word vector. And calculating the word frequency TF of each word and the inverse document frequency IDF to obtain the TF-IDF value. The TF-IDF values of all words are sorted in descending order, the word of topK is selected as the keyword, and K is the number of the selected keywords, for example, 300. The TF-IDF of the entry w is specifically calculated as follows:

TF-IDF_w＝TF_w*IDF_w (1-1)；

in one embodiment, the requirements corpus includes: a demand attribute word bank and a demand target word bank; the requirement keywords include: a requirement item attribute keyword and a requirement item target keyword; the requirement item attribute keywords and the requirement item target keywords are respectively stored in a requirement attribute word bank and a requirement target word bank.

The channel corpus includes: a channel attribute word thesaurus, a channel target word thesaurus and a channel success word thesaurus; the channel keywords include: channel attribute keywords, channel target project keywords and channel success project keywords; the channel attribute keywords, the channel target item keywords and the channel success item keywords are respectively stored in a channel attribute word thesaurus, a channel target word thesaurus and a channel success word thesaurus.

The expert corpus includes: an expert attribute word lexicon and an expert success word lexicon; the expert keywords comprise expert attribute keywords and expert success project keywords; the expert attribute keywords and the expert success item keywords are respectively stored in an expert attribute word thesaurus and an expert success word thesaurus.

The requirement item attribute key words, the channel attribute key words and the expert attribute key words are used for respectively representing fixed attribute characteristics of requirement items, channels (technical brokers), technical fields, regions, units or types of units to which the experts belong, technical key words and the like. The requirement project target keywords and the channel target word lexicon are keywords representing the content of projects which a requirement project and a channel (technical broker) want to complete or interface. Channel success project keywords and expert success project keywords are keywords that characterize a project that a channel (technology broker), expert, historically, successfully completed or docked successfully.

In one embodiment, the requirement item attribute keywords and the requirement item target keywords are acquired from a requirement attribute word bank and a requirement target word bank respectively based on item requirement information. For example, the existing method may be used to perform word segmentation processing on the project requirement information, and the existing matching method is used to match the obtained words with the keywords in the requirement attribute word bank and the requirement target word bank, so as to obtain the requirement project attribute keywords and the requirement project target keywords.

Setting a first library group and a second library group; the first library set includes: the system comprises a demand attribute word bank, a channel attribute word bank and an expert attribute word bank; the second library set includes: a demand target word thesaurus, a channel success word thesaurus and an expert success word thesaurus.

The first library group and the second library group are divided, keywords under the first library group are easier to extract and have higher precision, keywords under the second library group are often lower in extraction precision than the first library group and are more complicated in content, and if the first library group and the second library group are subjected to mixed calculation, the matching result is often inaccurate.

And respectively acquiring corresponding channel attribute keywords and expert attribute keywords from a channel attribute word library and an expert attribute word library in the first library group according to the requirement item attribute keywords, and establishing at least one first keyword group based on the corresponding relation of the requirement item attribute keywords, the channel attribute keywords and the expert attribute keywords.

And respectively acquiring corresponding channel target item keywords, channel success item keywords and expert success item keywords from a channel target word thesaurus, a channel success word thesaurus and an expert success word thesaurus in the second library group according to the requirement item target keywords, and establishing at least one second keyword group based on the corresponding relation of the requirement item target keywords, the channel target item keywords, the channel success item keywords and the expert success item keywords.

In one embodiment, as shown in fig. 4, when a user issues a new demand, the name of the demand is a demand item a, and based on item demand information such as a technical field, a region, a unit, and a technical keyword of the demand item a, a demand item attribute keyword is matched from a demand attribute word bank; and matching the required item target keywords from the required target word lexicon based on the item required information of the specific content text of the required item A.

For example, three requirement item attribute keywords are matched from the requirement attribute word bank, which are: "automatic fusion", "automatic flaw detection", "fusion equipment"; four requirement item target keywords are matched from the requirement target word library, and the four requirement item target keywords are respectively as follows: automatic welding, automatic flaw detection, cable fusion and welding equipment. The requirement item attribute keyword and the requirement item target keyword may be the same or different.

The method comprises the steps of respectively obtaining one or more corresponding channel attribute keywords and one or more corresponding expert attribute keywords from a channel attribute word bank and an expert attribute word bank in a first bank group according to three requirement item attribute keywords of automatic welding, automatic flaw detection and welding equipment, and establishing at least one first keyword group based on the corresponding relation of the requirement item attribute keywords, the channel attribute keywords and the expert attribute keywords. The channel attribute keywords and the expert attribute keywords can be respectively obtained from the channel attribute word bank and the expert attribute word bank in the first bank group by adopting the existing multiple keyword matching method.

For example, for the requirement item attribute keyword "automatic fusion", a channel attribute keyword "sonic wave inspection" and an expert attribute keyword "sonic wave fusion" are respectively obtained from a channel attribute word library and an expert attribute word library in the first library group, and a first keyword group { "automatic fusion", "sonic wave inspection" } is established.

If the requirement item attribute keyword is in automatic welding, a plurality of corresponding channel attribute keywords and a plurality of corresponding expert attribute keywords are respectively obtained from the channel attribute word stock and the expert attribute word stock in the first stock group, a plurality of first keyword groups in the format are established based on the corresponding relation between the automatic welding and the channel attribute keywords and the expert attribute keywords, and the first keyword of each first keyword group is in automatic welding.

Based on the same method, one or more first keyword groups are respectively established for the other two requirement item attribute keywords of automatic welding, automatic flaw detection and welding equipment.

The channel attribute keywords and the expert attribute keywords corresponding to different requirement item attribute keywords can be the same or different. For example, if the channel attribute keywords and the expert attribute keywords corresponding to the three requirement item attribute keywords "automatic welding", "automatic flaw detection", "welding equipment" are all one and the same, a total of three first keyword groups are generated: the method comprises the following steps of { "automatic welding", "sonic inspection" }, { "automatic inspection", "sonic inspection" }, and { "welding equipment", "sonic inspection" }.

And respectively acquiring one or more corresponding channel target project keywords, one or more channel success project keywords and one or more expert success project keywords from the channel target word lexicon, the channel success word lexicon and the expert success word lexicon in the second library group according to the four requirement project target keywords, namely automatic welding, automatic flaw detection, cable fusion and welding equipment.

For example, based on the requirement project target keyword "automatic fusion", a corresponding one of the channel target project keyword "radiographic inspection", a channel success project keyword "sonic inspection" and an expert success project keyword "optical fiber fusion" are respectively obtained from the channel target word lexicon, the channel success word lexicon and the expert success word lexicon in the second library group; establishing a second key phrase { "automatic fusion", "radiographic inspection", "sonic inspection", "optical fiber fusion" }.

If the requirement project target keyword is 'automatically welded', a plurality of corresponding channel target project keywords, a plurality of channel success project keywords and a plurality of expert success project keywords are respectively obtained from a channel target word stock, a channel success word stock and an expert success word stock in the second stock group, a plurality of second keyword groups in the format are established based on the corresponding relation between 'automatically welded' and the plurality of channel target project keywords, the plurality of channel success project keywords and the plurality of expert success project keywords, and the first keyword of each second keyword group is 'automatically welded'.

Based on the same method, one or more second keyword groups are respectively established for other three requirement project target keywords of automatic flaw detection, cable fusion and welding equipment. The channel target project keywords, channel success project keywords and expert success project keywords corresponding to different requirement project target keywords may be the same or different. For example, if the channel target item keywords, the channel success item keywords, and the expert success item keywords corresponding to the four requirement item target keywords "automatic fusion," "automatic flaw detection," "cable fusion," "fusion equipment," are all one and the same, a total of four second keyword groups are generated: { "automatic fusion splice", "radiographic inspection", "sonic inspection", "optical fiber fusion splice" },

The method comprises the following steps of { "automatic flaw detection", "radiographic inspection", "sonic flaw detection", "optical fiber fusion" }, { "cable fusion", "radiographic inspection", "sonic flaw detection", "optical fiber fusion" }, { "fusion equipment", "radiographic inspection", "sonic flaw detection", "optical fiber fusion" }.

Fig. 4B is a schematic flowchart of calculating a first relevance degree in an embodiment of the item information matching method of the present disclosure, where the method shown in fig. 4 includes the steps of: S401-S403. The following describes each step.

S401, obtaining a word vector of each keyword in the first keyword group, and calculating attribute association degree corresponding to the first keyword group based on the word vector.

S402, obtaining a word vector of each keyword in the second keyword group, and calculating the target association degree corresponding to the second keyword group based on the word vector.

S403, calculating a first relevance degree based on the attribute relevance degree and the target relevance degree.

The attribute association degree corresponding to the first keyword group may be calculated by various methods. For example, a first distance between word vectors of every two keywords among the requirement item attribute keyword, the channel attribute keyword, and the expert attribute keyword is calculated, and a product of the three first distances is taken as the attribute association degree.

The target association degree corresponding to the second keyword group may be calculated by various methods. For example, a second distance between word vectors of every two keywords in the demand item target keyword, the channel target item keyword and the expert success item keyword is calculated, and the product of the three second distances is used as the first sub-target association degree.

And calculating a third distance between word vectors of every two keywords in the requirement project target keywords, the channel success project keywords and the expert success project keywords, taking the product of the three third distances as a second sub-target association degree, and calculating the average sum of the first sub-target association degree and the second sub-target association degree as a target association degree.

Various methods may be used to calculate the first degree of association based on the attribute degree of association and the target degree of association. For example, based on all the attribute relevance degrees and all the target relevance degrees, a comprehensive average sum is calculated to obtain a first relevance degree.

In one embodiment, Word vectors, which are vector forms of the requirement keyword, the channel keyword and the expert keyword, are calculated in advance by using a Word2vec tool and are stored in the requirement corpus, the channel corpus and the expert corpus respectively by using a Skip-gram model. For example, cosine similarity calculation is performed on each keyword in the keyword set a of the demand corpus, the keyword set B of the channel corpus, and the keyword set C of the expert corpus to obtain a similarity matrix, where the similarity is the association between the keywords:

the cosine similarity is calculated in the following manner:

v_i、v_j、v_kare respectively key words A_i、B_j、C_kM, n, l are the number of keywords of the keyword set A, B, C, respectively.

Calculating a first distance between word vectors of every two keywords in the requirement item attribute keywords, the channel attribute keywords and the expert attribute keywords, wherein the first distance can be cosine similarity (cosine distance) between the word vectors; and calculating a second distance between word vectors of every two keywords in the demand project target keywords, the channel target project keywords and the expert success project keywords, wherein the second distance can also be cosine similarity (cosine distance) of the word vectors.

For example, the set of requirement item attribute keywords t₁The method comprises three keywords of automatic welding, automatic flaw detection and welding equipment. For each requirement item attribute keyword, respectively obtaining a corresponding channel attribute keyword set t from a channel attribute word lexicon and an expert attribute word lexicon in a first library group₂And expert Attribute keywords t₃。

Based on each requirement item attribute keyword and channel attribute keyword set t₂And expert Attribute keywords t₃The corresponding relation between the first keyword group and the second keyword group is established.

The quantity of the first keyword groups established based on the requirement item attribute keywords is as follows: t is t₂Number of channel attribute keywords t₃The number of expert attribute keywords in (1); adding the number of first keyword groups established based on all the attribute keywords of the demand items to obtain the total number n of the first keyword groups_Properties。

For example, for t₁Generating a plurality of first key phrases, wherein the plurality of first key phrases comprise three first key phrases: the method comprises the following steps of { "automatic welding", "sonic inspection" }, { "automatic inspection", "sonic inspection" }, and { "welding equipment", "sonic inspection" }.

t₁The first distance between the three keywords and the channel attribute keyword 'sonic inspection' is [0.94, 0.92, 0.95 ]]；t₁The first distance between the three keywords and the expert attribute keyword "sonic welding" is [0.89,0.95,0.90 ]]. Channel attribute keyword 'sonic wave flaw detection' and expertThe matching result between the sex keywords "sonic welding" was [0.94]。

The following description will be given by taking a group of keyword relevance degrees { "automatic fusion", "sonic flaw detection" } in the first keyword group as an example to calculate the attribute relevance degree corresponding to the first keyword group.

Calculating attribute association degrees corresponding to the phrases { "automatic welding", "sonic flaw detection" }, namely association degree r₁₁Comprises the following steps: r is₁₁[ (automatic welding)_{Requirement item attribute keywords}(Acoustic wave test)_{Channel attribute keywords}(Sound wave welding)_{Expert Attribute keywords}]R [ (automatic welding)_{Requirement item attribute keywords}(Acoustic wave test)_{Channel attribute keywords}]R [ (sonic wave flaw detection)_{Channel attribute keywords}(Sound wave welding)_{Expert Attribute keywords}]R [ (sonic welding)_{Expert Attribute keywords}(automatic welding)_{Requirement item attribute keywords}]；

Wherein,

r [ (automatic welding)_{Requirement item attribute keywords}(Acoustic wave test)_{Channel attribute keywords}]

＝S_{Requirement item attribute keywords and channel attribute keywords}("automatic weld", "sonic flaw detection")

Wherein S is_{Requirement item attribute keywords and channel attribute keywords}The first distance between the corresponding keywords is the cosine similarity between the keywords.

Based on the same method, the attribute association degrees corresponding to the rest first keyword groups can be calculated, and the obtained number of the attribute association degrees is the total number of the first keyword groups.

Requirement project target keyword set t₄The method comprises four keywords { "automatic fusion welding", "radiographic inspection", "sonic inspection", "optical fiber fusion welding". For each requirement project target keyword, respectively acquiring corresponding channel target project keywords from a channel target word lexicon, a channel success word lexicon and an expert success word lexicon in the second library groupSet t₅Channel success project keyword set t₆And expert success project keyword set t₇。

Target keyword set t based on each demand project and channel target project₅Channel success project keyword set t₆And expert success project keyword set t₇The corresponding relation between the first key phrase and the second key phrase is established.

The number of the second keyword groups established based on the target keyword of one demand item is as follows: t is t₅Number of keywords of channel target item(s) t₆Number of channel success project keywords t₇The number of expert success project keywords in (1); adding the number of second keyword groups established based on all the target keywords of the demand items to obtain the total number n of the second keyword groups_Target。

Calculating the target association degree r of a group of keywords { "automatic fusion", "radiographic inspection", "sonic inspection", "optical fiber fusion" } in the second keyword group₁₂Comprises the following steps:

wherein,

r [ (automatic welding)_{Demand item target keywords}(radiographic inspection)_{Channel target project key word}(optical fiber fusion splice)_{Expert success project keywords}]For the first sub-goal association degree,

r [ (automatic welding)_{Demand item target keywords}(Acoustic wave test)_{Keyword for successful item of channel}(optical fiber fusion splice)_{Expert success project keywords}]For the second sub-target relevance degree, the specific calculation method of the first sub-target relevance degree and the second sub-target relevance degree is the same as the calculation method of the attribute relevance degree.

And respectively calculating the target association degrees of the rest second key phrases based on the same method, wherein the obtained number of the target association degrees is the total number of the second key phrases.

Calculating a first degree of association r based on all attribute degrees of association and all target degrees of association₁. For example, all the attribute relevance degrees and all the target relevance degrees can be comprehensively added to obtain a first relevance degree r₁：

Wherein, t_a,bIs a key phrase, t, in a requirement library corresponding to the project requirement information_a,bBy a key-phrase t corresponding to the requirement attribute_aAnd a keyword t corresponding to the demand target_bComposition is carried out; r is_i1(t_a) Is the attribute association degree corresponding to the ith first key phrase, r_i2(t_b) The target association degree corresponding to the ith second key phrase is obtained; a is a first library group, b is a second library group; n is_PropertiesIs the number of all first key phrases, n_TargetIs the number of all second key phrases.

In one embodiment, a demand keyword set is generated based on the demand item attribute keywords and the demand item target keywords. And generating a channel keyword set according to the channel attribute keywords, the channel target project keywords and the channel success project keywords. And generating an expert keyword set according to the expert attribute keywords and the expert success project keywords.

Selecting current channel information based on the channel keyword set; the current channel information comprises at least one first keyword in a channel keyword set. Selecting current expert information based on the expert keyword set; wherein the current expert information includes at least one second keyword in the set of expert keywords. And generating a candidate project matching combination according to the project demand information, the current channel information and the current expert information.

For example, according to the requirement item attribute keywords and the requirement item target keywords, a requirement keyword set { "automatic fusion", "automatic flaw detection", "fusion equipment", "cable fusion" } is generated. And generating a channel keyword set { "sonic inspection", "radiographic inspection" } according to the channel attribute keywords, the channel target project keywords and the channel success project keywords. And generating an expert keyword set { 'sonic wave fusion splice', 'optical fiber fusion splice' } according to the expert attribute keywords and the expert success item keywords.

Selecting current channel information B2 and B2 based on the channel keyword set; the current channel information B2 and B2 comprise at least one first keyword of { "sonic flaw detection", "radiographic flaw detection" }. And selecting current expert information C1 and C2 based on the expert keyword set, wherein the current expert information C1 and C2 comprise at least one second keyword of { "sonic wave fusion", "optical fiber fusion" }.

And generating candidate project matching combinations according to the project requirement information A, the current channel information B2 and B2 and the current expert information C1 and C2. Because the project requirement information A is the same, four candidate project matching combinations are respectively: { project requirement information a, current channel information B1, current expert information C1}, { project requirement information a, current channel information B1, current expert information C2}, { project requirement information a, current channel information B2, current expert information C1}, { project requirement information a, current channel information B2, current expert information C2 }.

Fig. 5 is a schematic flowchart of calculating a second relevance degree in an embodiment of the item information matching method of the present disclosure, where the method shown in fig. 5 includes the steps of: S501-S507. The following describes each step.

S501, all first keywords in a channel keyword set contained in current channel information are obtained.

S502, determining a corresponding first association coefficient based on the word bank to which the first keyword belongs.

S503, calculating a first matching correlation degree of the current channel information based on all the first correlation coefficients.

S504, all second keywords in the expert keyword set contained in the current expert information are obtained.

And S505, determining a corresponding second association coefficient based on the word bank to which the second keyword belongs.

S506, calculating a second matching correlation degree of the current expert information based on all the second correlation coefficients.

And S507, calculating a second correlation degree according to the first matching correlation degree and the second matching correlation degree.

In one embodiment, all first keywords in { "sonic inspection", "radiographic inspection" } included in the acquired current channel information B1 are "sonic inspection", that is, only one first keyword is included. All first keywords in { "sonic inspection", "radiographic inspection" } included in the current channel information B2 are acquired as "sonic inspection", "radiographic inspection", and include two first keywords.

The word stock to which the acoustic flaw detection belongs is a channel target word stock, and the word stock to which the ray flaw detection belongs is a channel success word stock. The first association coefficient of the keywords in the channel target word lexicon is preset to be 0.5, and the first association coefficient of the keywords in the channel success word lexicon is 0.7. If the word banks are different, the first association coefficients of the keywords in the word banks are different and can be set according to the importance.

The first matching degree of association of the current channel information B1 is calculated to be 0.5, and the first matching degree of association of the current channel information B2 is calculated to be 0.5+ 0.7-1.2.

All the second keywords in { "sound wave fusion splice", "optical fiber fusion splice" } included in the current expert information C1 are acquired as "sound wave fusion splice", and all the second keywords in { "sound wave fusion splice", "optical fiber fusion splice" } included in the current expert information C2 are acquired as "sound wave fusion splice" and "optical fiber fusion splice".

The word stock to which the sound wave fusion splicing belongs is an expert attribute word stock, and the word stock to which the optical fiber fusion splicing belongs is an expert success word stock. The second correlation coefficient of the keywords in the expert attribute word lexicon is preset to be 0.4, and the second correlation coefficient of the keywords in the expert success word lexicon is 0.6.

The second matching degree of association of the current expert information C1 is calculated to be 0.4, and the second matching degree of association of the current expert information C2 is calculated to be 0.4+ 0.6-1.0.

The second degree of association may be calculated by adding the first degree of association and the second degree of association. For example, the second degree of association of the candidate item matching combination { item requirement information a, current channel information B2, current expert information C2} is 1.2+1.0 ═ 2.2. Since each item matching combination includes the item requirement information a, the item requirement information a may not be considered when calculating the second degree of association.

The second degree of association is mainly determined by whether fuzzy matching is performed when the keyword is matched with the current channel information and the current expert information, and whether fuzzy matching is performed on each keyword contained in the keyword.

Fig. 6 is a schematic flowchart of determining a target item matching combination in an embodiment of the item information matching method of the present disclosure, where the method shown in fig. 6 includes the steps of: S601-S602. The following describes each step.

S601, using the sum of the first relevance degree and the second relevance degree, or the product of the first relevance degree and the second relevance degree as a third relevance degree.

And S601, determining the candidate item matching combination corresponding to the maximum third relevance as the target item matching combination.

For example, a weighted sum of the first degree of association and the second degree of association is calculated, or a weighted product of the first degree of association and the second degree of association is calculated, and the weighted sum or the weighted product is taken as the third degree of association. And selecting a third degree of association for sorting, selecting i candidate item matching combinations with highest scores as target item matching combinations, using the target item matching combinations as recommendation results, and recommending current channel information (technical broker information) and current expert information in the target item matching combinations to the user, wherein i can be 1,2,3 and the like.

Exemplary devices

In one embodiment, as shown in fig. 7, the present disclosure provides an item information matching apparatus, including: a first keyword obtaining module 701, a second keyword obtaining module 702, a first relevancy calculating module 703, a second relevancy calculating module 704 and a target item matching determining module 705.

The first keyword obtaining module 701 receives the project requirement information, and obtains a requirement keyword from a requirement corpus based on the project requirement information. The second keyword obtaining module 702 obtains the channel keyword corresponding to the channel corpus and the expert keyword corresponding to the expert corpus according to the requirement keyword. The first association degree calculation module 703 calculates a first association degree between the requirement keyword, the channel keyword, and the expert keyword.

The second relevance calculating module 704 selects a candidate item matching combination and calculates a second relevance of the candidate item matching combination according to the requirement keyword, the channel keyword and the expert keyword; wherein the candidate item matching combination comprises: the system comprises project requirement information, current channel information corresponding to the project requirement information and current expert information.

The target item matching determination module 705 calculates a third degree of association corresponding to the candidate item matching combination according to the first degree of association and the second degree of association, and determines a target item matching combination from the candidate item matching combination based on the third degree of association. For example, the target item matching determination module 705 takes the sum of the first degree of association and the second degree of association, or the product of the first degree of association and the second degree of association as the third degree of association; and determining the candidate item matching combination corresponding to the maximum third association degree as the target item matching combination.

In one embodiment, as shown in fig. 8, the corpus construction module 706 obtains history item information that is successfully transferred or converted, extracts a requirement keyword, a channel keyword, and an expert keyword from the history item information, and calculates a corresponding word vector. The corpus construction module 706 stores the requirement keywords, the channel keywords, the expert keywords, and the corresponding word vectors in a requirement corpus, a channel corpus, and an expert corpus, respectively.

As shown in fig. 9, corpus construction module 706 includes: a keyword processing unit 7061 and a keyword selecting unit 7062. The keyword processing unit 7061 performs word segmentation processing on the historical item information and performs preprocessing to obtain a demand keyword, a channel keyword, and an expert keyword, and performs vectorization processing on the demand keyword, the channel keyword, and the expert keyword, respectively, to obtain a word vector. The keyword selecting unit 7062 calculates a word frequency TF and an inverse document frequency IDF where the demand keyword, the channel keyword, and the expert keyword occur, respectively, obtains TF-IDF values corresponding to the demand keyword, the channel keyword, and the expert keyword, and selects a preset number of the demand keyword, the channel keyword, and the expert keyword, respectively, based on a preset sorting rule and according to the TF-IDF values.

In one embodiment, the requirements corpus includes: a demand attribute word bank and a demand target word bank. The first keyword obtaining module 701 obtains a requirement item attribute keyword and a requirement item target keyword from a requirement attribute word bank and a requirement target word bank respectively based on item requirement information. The channel corpus includes: a channel attribute word thesaurus, a channel target word thesaurus and a channel success word thesaurus; the expert corpus includes: an expert attribute word thesaurus and an expert success word thesaurus.

As shown in fig. 10, the second keyword obtaining module 702 includes: a library group dividing unit 7021, a keyword matching unit 7022, and a phrase establishing unit 7023. The bank group dividing unit 7021 sets a first bank group and a second bank group; wherein the first library set comprises: the system comprises a demand attribute word bank, a channel attribute word bank and an expert attribute word bank; the second library set includes: a demand target word thesaurus, a channel success word thesaurus and an expert success word thesaurus. The first library group and the second library group may also be set by the keyword matching unit 7022. The keyword matching unit 7022 obtains the corresponding channel attribute keyword and the expert attribute keyword from the channel attribute word bank and the expert attribute word bank in the first bank group, respectively, according to the requirement item attribute keyword. The phrase establishing unit 7023 establishes at least one first keyword phrase based on the correspondence relationship between the requirement item attribute keyword, the channel attribute keyword, and the expert attribute keyword.

The keyword matching unit 7022 obtains the corresponding channel target item keyword, channel success item keyword, and expert success item keyword from the channel target word lexicon, the channel success word lexicon, and the expert success word lexicon in the second library set, respectively, according to the demand item target keyword. The phrase establishing unit 7023 establishes at least one second keyword phrase based on the correspondence relationship of the demand item target keyword, the channel target item keyword, the channel success item keyword, and the expert success item keyword.

As shown in fig. 11, the first relevance calculating module 703 includes: an attribute association calculating unit 7031, a target association calculating unit 7032, and a comprehensive association calculating unit 7033. Attribute association calculating section 7031 obtains a word vector of each keyword in the first keyword group, and calculates an attribute association degree corresponding to the first keyword group based on the word vector.

The target association calculating unit 7032 obtains a word vector of each keyword in the second keyword group, and calculates a target association degree corresponding to the second keyword group based on the word vector. The integrated association calculating unit 7033 calculates a first degree of association based on the attribute degree of association and the target degree of association.

The attribute association calculating unit 7031 calculates a first distance between word vectors of every two keywords among the requirement item attribute keyword, the channel attribute keyword, and the expert attribute keyword, and takes the product of the three first distances as the attribute association degree.

In one embodiment, the target association calculation unit 7032 calculates a second distance between word vectors of every two keywords among the requirement project target keyword, the channel target project keyword, and the expert success project keyword, and takes the product of the three second distances as the first sub-target association degree.

The target association calculation unit 7032 calculates a third distance between word vectors of every two keywords among the requirement project target keyword, the channel success project keyword, and the expert success project keyword, takes the product of the three third distances as a second sub-target association degree, and calculates an average sum of the first sub-target association degree and the second sub-target association degree as a target association degree. The integrated association calculating unit 7033 calculates a first degree of association based on all the attribute degrees of association and all the target degrees of association.

As shown in fig. 12, the second association degree calculation module 704 includes: an item matching combination acquisition unit 7041 and a matching association calculation unit 7042. The item matching combination obtaining unit 7041 generates a demand keyword set according to the demand item attribute keyword and the demand item target keyword; the item matching combination obtaining unit 7041 generates a channel keyword set according to the channel attribute keyword, the channel target item keyword, and the channel success item keyword.

The item matching combination obtaining unit 7041 generates an expert keyword set according to the expert attribute keywords and the expert success item keywords, and selects current channel information based on the channel keyword set; the current channel information comprises at least one first keyword in a channel keyword set. The item matching combination obtaining unit 7041 selects current expert information based on the expert keyword set; wherein the current expert information includes at least one second keyword in the set of expert keywords. The item matching combination obtaining unit 7041 generates a candidate item matching combination according to the item demand information, the current channel information, and the current expert information.

Matching association calculating unit 7042 obtains all first keywords in the channel keyword set included in the current channel information, determines corresponding first association coefficients based on the word bank to which the first keywords belong, and calculating unit 7042 calculates a first matching association degree of the current channel information based on all the first association coefficients. The matching association calculating unit 7042 obtains all the second keywords in the expert keyword set included in the current expert information, determines a corresponding second association coefficient based on the lexicon to which the second keyword belongs, and calculates a second matching association degree of the current expert information based on all the second association coefficients. Matching correlation calculation section 7042 calculates a second correlation degree from the first matching correlation degree and the second matching correlation degree.

Fig. 13 is a schematic structural diagram of yet another embodiment of the item information matching apparatus of the present disclosure, and as shown in fig. 13, the item information matching apparatus 131 includes one or more processors 1311 and a memory 1312.

The processor 1311 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the item information matching apparatus 131 to perform desired functions.

Memory 1312 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. Volatile memory, for example, may include: random Access Memory (RAM) and/or cache memory (cache), etc. The nonvolatile memory, for example, may include: read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on a computer-readable storage medium and executed by the processor 1311 to implement the project information matching methods of the various embodiments of the disclosure above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, etc. may also be stored in the computer-readable storage medium.

In one example, the item information matching apparatus 131 may further include: an input device 1313, and an output device 1314, among others, interconnected by a bus system and/or other form of connection mechanism (not shown). The input device 1313 may also include, for example, a keyboard, a mouse, and the like. The output unit 1314 may output various information to the outside. The output devices 1314 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.

Of course, for the sake of simplicity, only some of the components related to the present disclosure in the item information matching device 131 are shown in fig. 13, and components such as a bus, an input/output interface, and the like are omitted. Besides, the item information matching device 131 may also include any other suitable components according to specific application.

In addition to the above-described methods and apparatus, embodiments of the present disclosure may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the project information matching method according to various embodiments of the present disclosure described in the above-mentioned "exemplary methods" section of this specification.

The computer program product may write program code for carrying out operations for embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.

Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform steps in a project information matching method according to various embodiments of the present disclosure described in the "exemplary methods" section above in this specification.

The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium may include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.

The project information matching method, the project information matching device and the storage medium in the embodiments described above acquire a channel keyword corresponding to a channel corpus and an expert keyword corresponding to an expert corpus according to a demand keyword, and calculate a first degree of association; selecting a candidate item matching combination and calculating a second association degree of the candidate item matching combination according to the requirement key words, the channel key words and the expert key words; calculating a third degree of association corresponding to the candidate item matching combination according to the first degree of association and the second degree of association to determine a target item matching combination; the automatic matching between the supply and demand parties and the third-party transfer channel is realized, the manual searching and matching processes are reduced, the matching efficiency and precision are improved, the technology transfer conversion efficiency is improved, and the use experience of the user is improved.

In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, and systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," comprising, "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".

The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

It is also noted that in the devices, apparatuses, and methods of the present disclosure, each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.

The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects, and the like, will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.

Claims (10)

1. A project information matching method comprises the following steps:

receiving project demand information, and acquiring demand keywords from a demand corpus based on the project demand information;

acquiring a corresponding channel keyword in a channel corpus and a corresponding expert keyword in an expert corpus according to the requirement keyword;

calculating a first association degree among the requirement keywords, the channel keywords and the expert keywords;

selecting a candidate item matching combination and calculating a second association degree of the candidate item matching combination according to the requirement keyword, the channel keyword and the expert keyword; wherein the candidate item matching combination comprises: the project requirement information, current channel information corresponding to the project requirement information and current expert information;

and calculating a third degree of association corresponding to the candidate item matching combination according to the first degree of association and the second degree of association, and determining a target item matching combination from the candidate item matching combination based on the third degree of association.

2. The method of claim 1, further comprising:

acquiring history project information which is transferred or converted successfully, extracting the requirement keywords, the channel keywords and the expert keywords from the history project information, and calculating corresponding word vectors;

and respectively storing the requirement keywords, the channel keywords, the expert keywords and the corresponding word vectors in the requirement corpus, the channel corpus and the expert corpus.

3. The method of claim 2, said extracting said demand keywords, said channel keywords and said expert keywords and corresponding word vectors from said historical project information comprising:

performing word segmentation processing and preprocessing on the historical project information to obtain the requirement keywords, the channel keywords and the expert keywords;

vectorizing the demand keywords, the channel keywords and the expert keywords respectively to obtain word vectors;

respectively calculating word frequency TF and inverse document frequency IDF of the requirement key words, the channel key words and the expert key words to obtain TF-IDF values corresponding to the requirement key words, the channel key words and the expert key words;

and respectively selecting a preset number of demand keywords, channel keywords and expert keywords based on a preset sequencing rule and according to the TF-IDF value.

4. The method of claim 2 or 3, wherein the demand corpus comprises: a demand attribute word bank and a demand target word bank; the acquiring of the demand keyword from the demand corpus based on the project demand information includes:

and acquiring a requirement item attribute keyword and a requirement item target keyword from the requirement attribute word bank and the requirement target word bank respectively based on the item requirement information.

5. The method of claim 4, wherein the channel corpus comprises: a channel attribute word thesaurus, a channel target word thesaurus and a channel success word thesaurus; the expert corpus comprises: an expert attribute word lexicon and an expert success word lexicon; the acquiring of the channel keywords corresponding to the channel corpus and the expert keywords corresponding to the expert corpus according to the requirement keywords comprises:

setting a first library group, and respectively acquiring corresponding channel attribute keywords and expert attribute keywords from the channel attribute word library and the expert attribute word library in the first library group according to the requirement item attribute keywords; the first library set includes: the requirement attribute word library, the channel attribute word library and the expert attribute word library;

establishing at least one first keyword group based on the corresponding relation among the requirement item attribute keywords, the channel attribute keywords and the expert attribute keywords;

setting a second library group, and respectively acquiring corresponding channel target item keywords, channel success item keywords and expert success item keywords from the channel target word library, the channel success word library and the expert success word library in the second library group according to the demand item target keywords; the second library set includes: a demand target word lexicon, a channel success word lexicon and an expert success word lexicon;

and establishing at least one second keyword group based on the corresponding relation among the requirement project target keyword, the channel target project keyword, the channel success project keyword and the expert success project keyword.

6. The method of claim 5, the calculating a first degree of association between the demand keyword, the channel keyword, and the expert keyword comprising:

acquiring a word vector of each keyword in the first keyword group, and calculating attribute association degree corresponding to the first keyword group based on the word vector;

acquiring a word vector of each keyword in the second keyword group, and calculating a target association degree corresponding to the second keyword group based on the word vector;

calculating the first degree of association based on the attribute degree of association and the target degree of association.

7. The method of claim 6, said calculating a degree of attribute relevance corresponding to said first keyword set comprising:

calculating a first distance between word vectors of every two keywords in the requirement item attribute keywords, the channel attribute keywords and the expert attribute keywords, and taking the product of the three first distances as the attribute association degree;

the calculating the target association degree corresponding to the second keyword group comprises:

calculating a second distance between word vectors of every two keywords in the requirement project target keywords, the channel target project keywords and the expert success project keywords, and taking the product of the three second distances as a first sub-project association degree;

calculating a third distance between word vectors of every two keywords in the requirement project target keywords, the channel success project keywords and the expert success project keywords, and taking the product of the three third distances as a second sub-target association degree;

calculating the average sum of the first sub-target relevance and the second sub-target relevance as the target relevance;

the calculating the first degree of association based on the attribute degree of association and the target degree of association includes:

and calculating the first relevance based on all the attribute relevance and all the target relevance.

8. An item information matching apparatus comprising:

the first keyword acquisition module is used for receiving project demand information and acquiring a demand keyword from a demand corpus based on the project demand information;

the second keyword acquisition module is used for acquiring corresponding channel keywords in the channel corpus and corresponding expert keywords in the expert corpus according to the requirement keywords;

the first association degree calculation module is used for calculating a first association degree among the requirement keywords, the channel keywords and the expert keywords;

the second association degree calculation module is used for selecting a candidate item matching combination and calculating the second association degree of the candidate item matching combination according to the requirement keyword, the channel keyword and the expert keyword; wherein the candidate item matching combination comprises: the project requirement information, current channel information corresponding to the project requirement information and current expert information;

and the target item matching determination module is used for calculating a third degree of association corresponding to the candidate item matching combination according to the first degree of association and the second degree of association and determining a target item matching combination from the candidate item matching combination based on the third degree of association.

9. An item information matching apparatus comprising:

a processor; a memory for storing the processor-executable instructions;

the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method of any one of claims 1-7.

10. A computer-readable storage medium, the storage medium storing a computer program for performing the method of any of the preceding claims 1-7.

Images