A demand text-based science and technology resource pushing method and device

Abstract

The embodiment of the application provides a kind of based on demand text's science and technology resource pushing method and device, the method includes: according to the user demand and science and technology professional dictionary generated in advance, generate science and technology resource demand dictionary, science and technology resource demand dictionary includes multiple demand keywords;Through science and technology resource demand dictionary and the service category dictionary generated in advance, the demand keyword and the service keyword in service category dictionary are matched, and demand service matching pair is obtained, and service matching pair includes demand keyword and corresponding service keyword;According to the science and technology resource corresponding to user demand and service keyword, generate target science and technology resource, can be integrated into science and technology professional dictionary, based on user demand, science and technology resource is pushed, to improve the accuracy and applicability of science and technology resource determination.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method and apparatus for pushing scientific and technological resources based on demand text. Background Technology

[0002] Science and technology resource sharing service platforms aggregate all information, material, financial, and human resources (both hardware and software) involved in scientific research activities. Guided by users' scientific research and innovation needs, they match services such as instrument reservations and software development. With the popularization of the science and technology service industry, science and technology resource sharing models have gradually been established and developed. However, the inefficiency and inaccuracy in matching supply and demand for science and technology services are serious problems, severely hindering the improvement of science and technology resource sharing service platforms. In related technologies, resource delivery is achieved through standardized business requirements and by first identifying suppliers and then providing resources, but this fails to incorporate industry characteristics and lacks accuracy in resource matching. Furthermore, it cannot accurately deliver science and technology resources to non-standardized requirement texts, resulting in poor applicability. Summary of the Invention

[0003] One object of this invention is to provide a method for recommending scientific and technological resources based on demand text, which can integrate a scientific and technological dictionary and recommend scientific and technological resources based on user needs, thereby improving the accuracy and applicability of the identification of scientific and technological resources. Another object of this invention is to provide a device for recommending scientific and technological resources based on demand text. A further object of this invention is to provide a computer-readable medium. A still other object of this invention is to provide a computer device.

[0004] To achieve the above objectives, this invention discloses a method for pushing scientific and technological resources based on demand text, including:

[0005] Based on pre-generated user needs and a science and technology professional dictionary, a science and technology resource demand dictionary is generated, which includes multiple demand keywords.

[0006] By matching the demand keywords with the pre-generated service category dictionary, the demand keywords and service keywords in the service category dictionary are matched to obtain demand-service matching pairs. Each service matching pair includes the demand keyword and the corresponding service keyword.

[0007] Generate target technology resources based on the technology resources corresponding to user needs and service keywords.

[0008] Preferably, user needs include explicit needs, implicit needs, and hidden needs;

[0009] Before generating a science and technology resource demand dictionary based on pre-generated user needs and a science and technology professional dictionary, which includes multiple demand keywords, the dictionary also includes:

[0010] The explicit requirement to receive user input;

[0011] Based on the user's basic information, match similar users;

[0012] Generate users' implicit needs based on the browsing history of similar users;

[0013] Keyword extraction is performed on the service text of the acquired historical services to generate hidden user requirements.

[0014] Preferably, before generating a science and technology resource demand dictionary based on pre-generated user needs and a science and technology professional dictionary, which includes multiple demand keywords, the process also includes:

[0015] We crawled and deduplicated data from third-party professional thesaurus to build a scientific and technological dictionary.

[0016] Preferably, a science and technology resource demand dictionary is generated based on pre-generated user needs and a science and technology professional dictionary. This dictionary includes multiple demand keywords, including:

[0017] Using word segmentation tools, we accurately segment user needs based on a scientific and technological dictionary, resulting in multiple keywords related to those needs.

[0018] Preferably, by matching the demand keywords with the pre-generated service category dictionary using a technology resource demand dictionary, service keywords in the service category dictionary are obtained to produce demand-service matching pairs. Each service matching pair includes the demand keyword and its corresponding service keyword, including:

[0019] Perform lexical consistency matching on demand keywords and service keywords;

[0020] The successfully matched demand keywords and corresponding service keywords are identified as demand-service matching pairs.

[0021] The demand keywords that fail to match are matched with the service keywords based on similarity to obtain demand-service matching pairs.

[0022] Preferably, the demand keywords that fail to match are matched with service keywords based on similarity to obtain demand-service matching pairs, including:

[0023] Using a string fuzzy matching library, the similarity between the demand keywords and service keywords that failed to match is calculated to obtain multiple fuzzy similarities.

[0024] The demand keywords and service keywords corresponding to the highest fuzzy similarity selected are determined as the initial matching pairs;

[0025] The initial matching pairs are updated using a semantic similarity algorithm based on a technology service category tree to generate demand service matching pairs.

[0026] Preferably, based on user needs and the technological resources corresponding to service keywords, target technological resources are generated, including:

[0027] Semantic similarity calculation is performed on the technological resources corresponding to user needs and service keywords to generate an overall similarity score, which is the similarity between user needs and technological resources.

[0028] The overall similarity scores are sorted to obtain an ordered overall similarity score.

[0029] Based on the ordered overall similarity, the corresponding target technology resources are matched.

[0030] Preferably, user needs include explicit needs, implicit needs, and hidden needs;

[0031] Semantic similarity is calculated for the technological resources corresponding to user needs and service keywords to generate an overall similarity score. The overall similarity score represents the similarity between user needs and technological resources, including:

[0032] Based on the pre-constructed technology service category tree, semantic similarity is calculated between explicit needs and technology resources to obtain the explicit needs similarity.

[0033] Based on other user information obtained in advance, semantic similarity is calculated between implicit needs and technological resources to obtain the implicit need similarity.

[0034] Based on the pre-acquired service text keywords, semantic similarity is calculated between hidden requirements and technological resources to obtain the hidden requirement similarity.

[0035] The overall similarity is generated based on the similarity of explicit requirements, implicit requirements, and hidden requirements.

[0036] This invention also discloses a technology resource push device based on demand text, comprising:

[0037] The demand dictionary generation unit is used to generate a science and technology resource demand dictionary based on pre-generated user needs and a science and technology professional dictionary. The science and technology resource demand dictionary includes multiple demand keywords.

[0038] The first matching unit is used to match the demand keywords and the service keywords in the service category dictionary with the technology resource demand dictionary and the pre-generated service category dictionary to obtain demand service matching pairs. The service matching pairs include demand keywords and corresponding service keywords.

[0039] The resource generation unit is used to generate target technology resources based on user needs and the technology resources corresponding to service keywords.

[0040] Preferably, user needs include explicit needs, implicit needs, and hidden needs; the device also includes:

[0041] The receiving unit is used to receive explicit user input requests;

[0042] The second matching unit is used to match similar users based on the user's basic information;

[0043] The implicit demand generation unit is used to generate users' implicit demands based on the browsing history information of similar users.

[0044] The hidden requirement generation unit is used to extract keywords from the service text of historical services and generate hidden requirements for users.

[0045] Preferably, the device further includes:

[0046] The data preprocessing unit is used to crawl and deduplicate data from third-party professional thesaurus to build a scientific and technical dictionary.

[0047] Preferably, the demand dictionary generation unit is specifically used to accurately segment user demands using a word segmentation tool based on a scientific and technical dictionary to obtain multiple demand keywords.

[0048] Preferably, the first matching unit is specifically used to perform lexical consistency matching on demand keywords and service keywords; determine the successfully matched demand keywords and corresponding service keywords as demand-service matching pairs; and perform similarity matching on demand keywords and service keywords that fail to match to obtain demand-service matching pairs.

[0049] Preferably, the first matching unit is specifically used to calculate the similarity between the demand keywords and service keywords that failed to match using a string fuzzy matching library, and obtain multiple fuzzy similarities; determine the demand keyword and service keyword corresponding to the largest fuzzy similarity as the initial matching pair; and update the initial matching pair using a semantic similarity algorithm based on a technology service category tree to generate a demand-service matching pair.

[0050] Preferably, the resource generation unit is specifically used to perform semantic similarity calculation on the technological resources corresponding to user needs and service keywords, generate an overall similarity, which is the similarity between user needs and technological resources; sort the overall similarities to obtain an ordered overall similarity; and match the corresponding target technological resources based on the ordered overall similarity.

[0051] Preferably, user needs include explicit needs, implicit needs, and hidden needs;

[0052] The resource generation unit is specifically used to calculate the semantic similarity between explicit needs and technological resources based on a pre-constructed technology service category tree, to obtain the explicit need similarity; to calculate the semantic similarity between implicit needs and technological resources based on other pre-acquired user information, to obtain the implicit need similarity; to calculate the semantic similarity between hidden needs and technological resources based on pre-acquired service text keywords, to obtain the hidden need similarity; and to generate an overall similarity based on the explicit need similarity, implicit need similarity, and hidden need similarity.

[0053] The present invention also discloses a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the method described above.

[0054] The present invention also discloses a computer device, including a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, wherein the processor executes the program to implement the method described above.

[0055] The present invention also discloses a computer program product, including a computer program / instruction, which, when executed by a processor, implements the method described above.

[0056] This invention generates a science and technology resource demand dictionary based on pre-generated user needs and a science and technology professional dictionary. The science and technology resource demand dictionary includes multiple demand keywords. By matching the demand keywords with the pre-generated service category dictionary, service keywords in the service category dictionary are obtained to obtain demand-service matching pairs. Each service matching pair includes the demand keyword and its corresponding service keyword. Based on the science and technology resources corresponding to the user needs and service keywords, target science and technology resources are generated. These resources can be integrated into the science and technology professional dictionary and pushed to users based on their needs, thereby improving the accuracy and applicability of science and technology resource identification. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 A flowchart illustrating a method for pushing scientific and technological resources based on demand text, provided as an embodiment of the present invention;

[0059] Figure 2A flowchart illustrating yet another method for pushing scientific and technological resources based on demand text, provided as an embodiment of the present invention;

[0060] Figure 3 This is a schematic diagram illustrating the decomposition of platform user requirements as provided in an embodiment of the present invention;

[0061] Figure 4 A schematic diagram of a technology resource push device based on demand text provided in an embodiment of the present invention;

[0062] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0063] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0064] To facilitate understanding of the technical solution provided in this application, the relevant content of the technical solution will be explained below. The essence of technology service matching is the synchronous connection process between technology resources and platform users, pairing the technology resources that best meet user needs with users to support them in completing a series of scientific research activities. Therefore, user needs identification is a crucial step in laying the foundation for matching. Accurate user needs identification is of great significance on a technology resource sharing service platform. Specifically, by comprehensively considering user characteristics and industry features, and utilizing information such as the demand text generated during user-platform interaction, user needs are categorized, and user demands for technology services are extracted, ultimately improving the accuracy of technology service matching. This invention utilizes efficient intelligent recognition technology to improve the technology service matching model, thereby addressing the large and diverse user system and complex and varied user demand texts within the technology resource sharing service platform, thus meeting the ever-growing demand for technology resources and achieving efficient and rapid user response.

[0065] The following example uses a technology resource push device based on demand text as the execution subject to illustrate the implementation process of the technology resource push method based on demand text provided in this embodiment of the invention. It is understood that the execution subject of the technology resource push method based on demand text provided in this embodiment of the invention includes, but is not limited to, a technology resource push device based on demand text.

[0066] Figure 1 A flowchart illustrating a method for pushing scientific and technological resources based on demand text, as provided in this embodiment of the invention, is shown below. Figure 1 As shown, the method includes:

[0067] Step 101: Generate a science and technology resource demand dictionary based on the pre-generated user needs and science and technology professional dictionary. The science and technology resource demand dictionary includes multiple demand keywords.

[0068] Step 102: Match the demand keywords with the pre-generated service category dictionary using the technology resource demand dictionary to obtain demand-service matching pairs. Each service matching pair includes the demand keyword and the corresponding service keyword.

[0069] In this embodiment of the invention, the service category dictionary is a collection of all service categories on the platform, including multiple service keywords.

[0070] Step 103: Generate target technology resources based on user needs and the technology resources corresponding to service keywords.

[0071] It is worth noting that the acquisition, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations. The user information in the embodiments of this application was obtained through legal and compliant means, and the acquisition, storage, use, and processing of user information have been authorized and agreed upon by the client.

[0072] In the technical solution provided by this invention, a science and technology resource demand dictionary is generated based on pre-generated user needs and a science and technology professional dictionary. The science and technology resource demand dictionary includes multiple demand keywords. By matching the demand keywords with the pre-generated service category dictionary, service keywords in the service category dictionary are obtained to obtain demand-service matching pairs. Each service matching pair includes the demand keyword and the corresponding service keyword. Target science and technology resources are generated based on the science and technology resources corresponding to the user needs and service keywords. These resources can be integrated into the science and technology professional dictionary and pushed based on user needs, thereby improving the accuracy and applicability of science and technology resource identification.

[0073] Figure 2 A flowchart illustrating another method for pushing scientific and technological resources based on demand text provided in this embodiment of the invention is shown below. Figure 2 As shown, the method includes:

[0074] Step 201: Receive explicit user input.

[0075] In this embodiment of the invention, each step is performed by a technology resource push device based on demand text.

[0076] In this embodiment of the invention, explicit requirements are the text actively expressed by the user on the platform, such as the information entered by the user in the search box and the user's input requirements in the intelligent customer service dialogue.

[0077] Step 202: Match similar users based on the user's basic information.

[0078] In this embodiment of the invention, the user's basic information includes, but is not limited to, user identification code (ID), location, scope of business needs, browsing history, historical orders, and historical order ratings.

[0079] In this embodiment of the invention, the technology resource platform records user information for all visiting users. As an optional approach, a text similarity matching algorithm is used to match the user information of the user to be analyzed with the user information recorded by the technology resource platform to identify similar users.

[0080] In this embodiment of the invention, the classification of similar users also adopts the text similarity matching method, thus requiring the collection of as much information as possible.

[0081] Step 203: Generate the user's implicit needs based on the browsing history information of similar users.

[0082] In this embodiment of the invention, implicit needs are subconscious needs that users do not directly express but are still determined by the user's own characteristics.

[0083] In this embodiment of the invention, the demand scope refers to the service category information that the user may need. For example, if similar users have viewed the service category of logo design, then the logo design can be included in the demand scope of the user to be analyzed.

[0084] Step 204: Extract keywords from the service text of the acquired historical services to generate hidden user needs.

[0085] In this embodiment of the invention, hidden needs refer to deeper user needs that may be triggered by platform content. Historical services include services or products in the Case Center; service text is a paragraph of text describing past events in the Case Center or product description, depicting user needs and service processes, and expressing hidden needs that the user did not enter in the search box. The service text of historical services can be obtained from the historical service records and Case Center of the technology resource platform.

[0086] Specifically, keyword extraction algorithms are used to extract keywords from the service text of historical services, and the extracted keywords represent the user's hidden needs.

[0087] Figure 3 This is a schematic diagram illustrating the decomposition of platform user requirements provided in an embodiment of the present invention, such as... Figure 3As shown, platform user requirements include user input text (i.e., explicit requirements), basic user information (i.e., implicit requirements), and service descriptions (i.e., hidden requirements). The user input text includes a brief requirement in the search box and a detailed description of the requirement. User information includes preferences and scope, and the service description includes a details page and a case study center.

[0088] It is worth noting that platform user needs can also include other decomposition methods to decompose user needs in other directions, and this embodiment of the invention does not limit this.

[0089] Step 205: Crawl and deduplicate data from third-party professional thesaurus to construct a scientific and technological professional dictionary.

[0090] In this embodiment of the invention, a data crawling tool is used to crawl and deduplicate data from a third-party professional thesaurus on a website to construct a technical terminology database. This third-party professional thesaurus includes, but is not limited to, an instrument database and a technology database.

[0091] Step 206: Generate a science and technology resource demand dictionary based on the pre-generated user needs and science and technology professional dictionary. The science and technology resource demand dictionary includes multiple demand keywords.

[0092] In this embodiment of the invention, user requirements include explicit requirements, implicit requirements, and hidden requirements.

[0093] Specifically, word segmentation tools are used to accurately segment user needs based on a scientific and technological dictionary, resulting in multiple keywords related to those needs. As an optional solution, the Jieba word segmentation tool is used in a precise segmentation mode. This precise segmentation mode uses a scientific and technological dictionary to accurately segment user needs, yielding multiple keywords. For example, in basic Jieba segmentation, "infrared detection instrument" would be split into "infrared, detection, instrument". However, if a scientific and technological dictionary is added for precise segmentation, "infrared detection instrument" would be considered a single word and would not be segmented.

[0094] Furthermore, the dictionary of science and technology resource requirements is cleaned to obtain a cleaned dictionary of science and technology resource requirements.

[0095] Step 207: Perform lexical consistency matching on the demand keywords and service keywords. If the match is successful, proceed to step 208; if the match fails, proceed to step 209.

[0096] In this embodiment of the invention, a lexical consistency match is performed on each demand keyword and service keyword. If the match is successful, it means that the demand keyword and the successfully matched service keyword are completely consistent, and step 208 is continued; if the match fails, it means that the demand keyword and the service keyword are not completely consistent, and step 209 is continued.

[0097] Step 208: Determine the successfully matched demand keywords and corresponding service keywords as demand-service matching pairs, and continue to step 210.

[0098] In this embodiment of the invention, based on the service keyword j, the successfully matched demand keywords s are... i Labeled as s ij That is: the demand-service matching pair includes the demand keywords and the corresponding service keywords, then proceed to step 210.

[0099] Step 209: Perform similarity matching between the failed demand keywords and service keywords to obtain demand-service matching pairs.

[0100] In this embodiment of the invention, step 209 specifically includes:

[0101] Step 2091: Using a string fuzzy matching library, calculate the similarity between the demand keywords and service keywords that failed to match, and obtain multiple fuzzy similarities.

[0102] In this embodiment of the invention, the demand keywords that fail to match are those that are not completely consistent with the service keywords. Specifically, the similarity between each demand keyword and the service keyword is calculated using a string fuzzy matching library (FuzzyWuzzy), resulting in multiple fuzzy similarities.

[0103] Step 2092: Determine the demand keywords and service keywords corresponding to the highest fuzzy similarity found in the filter as the initial matching pair.

[0104] In this embodiment of the invention, multiple fuzzy similarities are compared, and the maximum value is selected, i.e., the largest fuzzy similarity; the demand keyword and service keyword corresponding to the largest fuzzy similarity are determined as the initial matching pair.

[0105] In this embodiment of the invention, for demand keywords that are not entirely consistent with service keywords, a string fuzzy matching library (FuzzyWuzzy) is first used to calculate the similarity between the demand keywords and service keywords. The category words with the highest similarity are then selected and labeled. That is, the demand keywords s i Labeled as s ij .

[0106] Step 2093: Update the initial matching pairs using a semantic similarity algorithm based on the technology service category tree to generate demand service matching pairs.

[0107] Specifically, using a semantic similarity algorithm based on a technology service category tree, the similarity between each demand keyword and a service keyword is calculated to obtain multiple matching similarities. The multiple matching similarities corresponding to each demand keyword are compared with the corresponding fuzzy similarities calculated in step 2092. Service keywords with matching similarities greater than fuzzy similarities are selected, and the service keyword and the demand keyword are determined as a demand-service matching pair, that is, the initial matching pair is updated.

[0108] Furthermore, the demand keywords s in the initial matching pairs ij Updated label to s ij’ .

[0109] Step 210: Generate target technology resources based on user needs and the technology resources corresponding to service keywords.

[0110] In this embodiment of the invention, user requirements include explicit requirements, implicit requirements, and hidden requirements.

[0111] In this embodiment of the invention, a platform description model is pre-constructed. Based on the platform description model, target technological resources are generated according to the technological resources corresponding to user needs and service keywords. The platform description model includes each user's needs (NE), platform information (P), and the platform's single service content (Gi). Each user's needs are described as NE = {{sNE}, {fNE}, {U}}, where sNE represents the brief needs entered in the search box, fNE represents the detailed description of the user's needs, and U represents user information; the platform's P information is described as P = {{sP}, {G}, {fP}, {UP}}, where sP represents the technology service category tree, G represents the platform's service content set, fP represents the service text keywords generated by the platform during the service process, mainly including the case center and user reviews, and UP represents other user information on the platform; the platform's single service content Gi is described as Gi = {{GsPi}, {GfP}, {GUP}}, where GfP represents the description of the service content under the technology service category, GfP represents the service text keywords generated by the platform's service content in past service processes, and GUP represents other user information that has used the service content.

[0112] Step 210 specifically includes:

[0113] Step 2101: Calculate the semantic similarity of the technological resources corresponding to user needs and service keywords to generate an overall similarity score. The overall similarity score is the similarity between user needs and technological resources. The overall similarity score includes explicit need similarity, implicit need similarity, and hidden need similarity.

[0114] In this embodiment of the invention, semantic similarity is calculated between explicit demand sNE and technological resources based on a pre-constructed technology service category tree, resulting in explicit demand similarity sim1(sNE, GsPi). The technology resource category tree is a hierarchical service classification system.

[0115] In this embodiment of the invention, keywords for user needs and keywords for technology services are matched using semantic similarity of words. The needs and services of mutually matched keywords are considered to be in the same category, thereby achieving the purpose of category extraction.

[0116] In this embodiment of the invention, semantic similarity is calculated between implicit needs and technological resources based on pre-acquired user information (GUP) to obtain implicit need similarity sim2(U,GUP). The similarity between users is calculated based on other user information (GUP) that has used the service content, and is denoted as sim2(U,GUP).

[0117] In this embodiment of the invention, based on the pre-acquired service text keyword fNE, the semantic similarity between the hidden demand and the technological resources is calculated to obtain the hidden demand similarity sim3(fNE,GfP).

[0118] In this embodiment of the invention, an overall similarity score is generated based on the similarity scores of explicit, implicit, and hidden requirements. Specifically, the overall similarity score is... Where β is the weight and sim is the similarity calculated above.

[0119] Specifically, the similarity calculation above adopts a semantic similarity matching method based on Chinese Wikipedia and scientific dictionaries. The formula for calculating semantic similarity is as follows:

[0120] sim ij =αsimz ij +(1-α)simb ij

[0121] Where α is the weighting coefficient of the similarity method based on a scientific and technical dictionary relative to the similarity method based on a search engine, and simz ij For word semantic similarity calculation results based on CNKI, most existing methods define it by the maximum value of the similarity of each combination of senses:

[0122]

[0123] simb ij The semantic similarity calculation results based on the Wikipedia search engine are calculated using the most widely used PMIB formula, as follows:

[0124]

[0125] Where, N b This indicates the total number of indexes for the search engine: 10. 9 N(s) i ,d j ) for query s i and d j The average of the results, N(s) i ) for query s i The average of the results, N(d) j ) for query d j The average of the results.

[0126] By combining the technology service category tree, a new semantic similarity calculation method is designed, and its mathematical formula is as follows:

[0127] sim ij =simt ij [αsimz ij +(1-α)simb ij ]

[0128] Among them, simt ij To measure the similarity between demand keywords and service keywords within the technology service category tree, the semantic similarity calculation for the technology service category tree is defined as follows:

[0129]

[0130] Where α' is the distance between technology service categories with a similarity of 0.5, dis(s i ,d j ) is the category tree for science and technology services. i and d j The path distance between them. α' is the parameter defined in the formula, dis(s i ,d j The calculation method can adopt the existing formula for calculating the path length of a tree, and the embodiments of the present invention do not limit this.

[0131] Step 2102: Sort the overall similarity to obtain an ordered overall similarity.

[0132] In this embodiment of the invention, the overall similarity can be sorted in descending order or in ascending order.

[0133] Step 2103: Match the corresponding target technology resources based on the ordered overall similarity.

[0134] In this embodiment of the invention, the overall similarity is the similarity between user needs and technological resources. Based on the ordered overall similarity, ordered technological resources are identified. If no further filtering is needed, the corresponding ordered technological resources are determined as target technological resources. If further filtering is needed, target technological resources are selected according to actual needs. As an optional solution, the top N technological resources in descending order can be determined as target technological resources.

[0135] Step 211: Push the target technology resources to the user terminal so that the user can view the target technology resources.

[0136] In this embodiment of the invention, the target technology resource is a technology resource determined according to user needs. The target technology resource will be pushed to the user terminal, and the user can view the target technology resource through the user terminal for further research.

[0137] The process of determining target scientific and technological resources is illustrated below with a specific example:

[0138] We acquire technology resource service requests from resource requesters. For example, if a user's request is "LOGO solicitation - a LOGO selection activity for regional public brands of agricultural products," we use a similarity matching method to match with a service category dictionary, filtering out the top three service keywords as [('cartoon LOGO'), ('animated LOGO'), ('product appearance')]. We then continue matching services under these three lists to obtain a list of target technology resources ranked from high to low as [('Maidian brand design'), ('Ruichen creative design'), ...]. By providing this list to the user, we can achieve an immediate response to their request.

[0139] It is worth noting that the acquisition, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations. The user information in the embodiments of this application was obtained through legal and compliant means, and the acquisition, storage, use, and processing of user information have been authorized and agreed upon by the client.

[0140] In this embodiment of the invention, a science and technology resource thesaurus is established by combining data from existing science and technology resource sharing service platforms, and a method for targeted calculation of the similarity of science and technology service terms is completed, improving the accuracy of science and technology service matching. Simultaneously, it solves the problem of accurate service matching on science and technology resource sharing service platforms and improves upon the platform's inability to perform large-scale accurate matching. From the perspective of terminology similarity matching, it improves the user demand identification method of science and technology resource sharing service platforms, revealing the user demand identification mechanism in the supply and demand matching process of science and technology services through full-process text similarity calculation. Applying the user demand identification mechanism to the actual platform service process can help automate the matching of user demands, solving the problems of a large number of pending matching demands and excessive reliance on manual customer service matching on existing science and technology resource sharing service platforms, thus completing a revolution in platform automation for user demand matching.

[0141] In the technical solution of the technology resource push method based on demand text provided in this embodiment of the invention, a technology resource demand dictionary is generated according to pre-generated user needs and a technology professional dictionary. The technology resource demand dictionary includes multiple demand keywords. By matching the demand keywords with the pre-generated service category dictionary, service keywords in the service category dictionary are obtained to obtain demand-service matching pairs. The service matching pairs include demand keywords and corresponding service keywords. Target technology resources are generated according to the technology resources corresponding to user needs and service keywords. This method can be integrated into the technology professional dictionary and push technology resources based on user needs, thereby improving the accuracy and applicability of technology resource identification.

[0142] Figure 4 This is a schematic diagram of a technology resource push device based on demand text, provided in an embodiment of the present invention. This device is used to execute the aforementioned technology resource push method based on demand text. Figure 4 As shown, the device includes: a demand dictionary generation unit 11, a first matching unit 12, and a resource generation unit 13.

[0143] The demand dictionary generation unit 11 is used to generate a science and technology resource demand dictionary based on pre-generated user needs and a science and technology professional dictionary. The science and technology resource demand dictionary includes multiple demand keywords.

[0144] The first matching unit 12 is used to match the demand keywords and the service keywords in the service category dictionary with the technology resource demand dictionary and the pre-generated service category dictionary to obtain demand service matching pairs. The service matching pairs include demand keywords and corresponding service keywords.

[0145] The resource generation unit 13 is used to generate target technology resources based on user needs and technology resources corresponding to service keywords.

[0146] In this embodiment of the invention, user requirements include explicit requirements, implicit requirements, and hidden requirements; the device further includes: a receiving unit 14, a second matching unit 15, an implicit requirement generation unit 16, and a hidden requirement generation unit 17.

[0147] The receiving unit 14 is used to receive explicit user input requests.

[0148] The second matching unit 15 is used to match similar users based on the user's basic information.

[0149] The implicit demand generation unit 16 is used to generate implicit demands of users based on the historical browsing information of similar users.

[0150] The hidden requirement generation unit 17 is used to extract keywords from the service text of the acquired historical services and generate the user's hidden requirements.

[0151] In this embodiment of the invention, the apparatus further includes a data preprocessing unit 18.

[0152] The data preprocessing unit 18 is used to crawl and deduplicate data from third-party professional thesaurus to build a scientific and technological professional dictionary.

[0153] In this embodiment of the invention, the demand dictionary generation unit 11 is specifically used to accurately segment user demands using a word segmentation tool based on a scientific and technical dictionary to obtain multiple demand keywords.

[0154] In this embodiment of the invention, the first matching unit 12 is specifically used to perform lexical consistency matching on demand keywords and service keywords; determine the successfully matched demand keywords and corresponding service keywords as demand-service matching pairs; and perform similarity matching on demand keywords and service keywords that fail to match to obtain demand-service matching pairs.

[0155] In this embodiment of the invention, the first matching unit 12 is specifically used to calculate the similarity between the failed matching demand keywords and service keywords through a string fuzzy matching library to obtain multiple fuzzy similarities; determine the demand keyword and service keyword corresponding to the largest fuzzy similarity as the initial matching pair; and update the initial matching pair through a semantic similarity algorithm based on a technology service category tree to generate a demand-service matching pair.

[0156] In this embodiment of the invention, the resource generation unit 13 is specifically used to perform semantic similarity calculation on the scientific and technological resources corresponding to user needs and service keywords, generate an overall similarity, which is the similarity between user needs and scientific and technological resources; sort the overall similarity to obtain an ordered overall similarity; and match the corresponding target scientific and technological resources based on the ordered overall similarity.

[0157] In this embodiment of the invention, user needs include explicit needs, implicit needs, and hidden needs. The resource generation unit 13 is specifically used to calculate the semantic similarity between explicit needs and technological resources based on a pre-constructed technology service category tree to obtain the explicit needs similarity; to calculate the semantic similarity between implicit needs and technological resources based on other pre-acquired user information to obtain the implicit needs similarity; to calculate the semantic similarity between hidden needs and technological resources based on pre-acquired service text keywords to obtain the hidden needs similarity; and to generate an overall similarity based on the explicit needs similarity, implicit needs similarity, and hidden needs similarity.

[0158] In the solution of this invention embodiment, a science and technology resource demand dictionary is generated based on pre-generated user needs and a science and technology professional dictionary. The science and technology resource demand dictionary includes multiple demand keywords. By matching the demand keywords with the pre-generated service category dictionary, service keywords in the service category dictionary are obtained to obtain demand-service matching pairs. Each service matching pair includes the demand keyword and the corresponding service keyword. Target science and technology resources are generated based on the science and technology resources corresponding to the user needs and service keywords. These resources can be integrated into the science and technology professional dictionary and pushed based on user needs, thereby improving the accuracy and applicability of science and technology resource identification.

[0159] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer device, specifically, a computer device can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0160] This invention provides a computer device, including a memory and a processor. The memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions. When the program instructions are loaded and executed by the processor, they implement the steps of the above-described embodiment of the technology resource push method based on demand text. For a detailed description, please refer to the above-described embodiment of the technology resource push method based on demand text.

[0161] The following is for reference. Figure 5 It shows a schematic diagram of the structure of a computer device 600 suitable for implementing the embodiments of this application.

[0162] like Figure 5As shown, the computer device 600 includes a central processing unit (CPU) 601, which can perform various appropriate tasks and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the computer device 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0163] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal feedback (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed in storage section 608 as needed.

[0164] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program including program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611.

[0165] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0166] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0167] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0168] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0169] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0170] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0171] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0172] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0173] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0174] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0175] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A demand text-based science and technology resource pushing method, characterized in that, The method comprises: According to the pre-generated user demand and the science and technology professional dictionary, a science and technology resource demand dictionary is generated, which comprises a plurality of demand keywords; Through the science and technology resource demand dictionary and the pre-generated service category dictionary, the demand keywords and the service keywords in the service category dictionary are matched to obtain a demand service matching pair, which comprises demand keywords and corresponding service keywords; According to the science and technology resources corresponding to the user demand and the service keywords, target science and technology resources are generated, specifically comprising: The user demand comprises explicit demand, implicit demand and hidden demand; The science and technology resources corresponding to the user demand and the service keywords are subjected to semantic similarity calculation to generate an overall similarity, specifically comprising: According to the pre-constructed science and technology service category tree, the explicit demand and the science and technology resources are subjected to semantic similarity calculation to obtain an explicit demand similarity; according to the pre-acquired other user information, the implicit demand and the science and technology resources are subjected to semantic similarity calculation to obtain an implicit demand similarity; according to the pre-acquired service text keywords, the hidden demand and the science and technology resources are subjected to semantic similarity calculation to obtain a hidden demand similarity; According to the explicit demand similarity, the implicit demand similarity and the hidden demand similarity, an overall similarity is generated, which is the similarity between the user demand and the science and technology resources; The overall similarity is sorted to obtain an ordered overall similarity; According to the ordered overall similarity, the corresponding target science and technology resources are matched out; Before the step of generating the science and technology resource demand dictionary according to the pre-generated user demand and the science and technology professional dictionary, the science and technology resource demand dictionary comprising a plurality of demand keywords, the method further comprises: Receiving the explicit demand input by the user, the explicit demand being the text actively expressed by the current user to be analyzed in the platform; According to the basic information of the user, similar users are matched out, specifically comprising: through a text similarity matching algorithm, the user information of the current user to be analyzed and the user information recorded by the science and technology resource platform are subjected to similarity matching to match out similar users; According to the historical browsing information of the similar users, the implicit demand of the user is generated, the implicit demand being the subconscious determined by the characteristics of the user and the demand range being the service category information that the user may demand; The service text of the acquired historical service is subjected to keyword extraction to generate the hidden demand of the user, the hidden demand being the deeper demand of the user triggered by the platform content, specifically comprising: through a keyword extraction algorithm, the service text of the historical service is subjected to keyword extraction, and the extracted keywords are the hidden demand of the user. 2.The demand-based text technology resource pushing method according to claim 1, characterized in that, Before the step of generating the science and technology resource demand dictionary according to the pre-generated user demand and the science and technology professional dictionary, the science and technology resource demand dictionary comprising a plurality of demand keywords, the method further comprises: The third-party professional word library is subjected to data crawling and de-duplication processing to construct the science and technology professional dictionary. 3.The demand-text-based science and technology resource pushing method according to claim 1, wherein, The step of generating the science and technology resource demand dictionary according to the pre-generated user demand and the science and technology professional dictionary, the science and technology resource demand dictionary comprising a plurality of demand keywords, comprises: The user demand is accurately segmented by a segmentation tool according to the scientific and technological professional dictionary, and a plurality of demand keywords are obtained.

4. The demand-based text technology resource pushing method according to claim 1, characterized in that, The demand keywords and service keywords in the service category dictionary are matched by the scientific and technological resource demand dictionary and the pre-generated service category dictionary, and a demand service matching pair is obtained, the service matching pair includes demand keywords and corresponding service keywords, including: The demand keywords and the service keywords are matched in vocabulary consistency; The demand keywords and the corresponding service keywords that are successfully matched are determined as the demand service matching pair; The demand keywords and the service keywords that fail to match are matched in similarity, and a demand service matching pair is obtained.

5. The demand-based text technology resource pushing method according to claim 4, characterized in that, The demand keywords and the service keywords that fail to match are matched in similarity, and a demand service matching pair is obtained, including: The demand keywords and the service keywords that fail to match are matched in similarity by a string fuzzy matching library, and a plurality of fuzzy similarities are obtained; The demand keywords and the service keywords corresponding to the largest fuzzy similarity screened out are determined as an initial matching pair; The initial matching pair is updated by a semantic similarity algorithm based on a scientific and technological service category tree, and a demand service matching pair is generated.

6. A demand text-based scientific resource pushing device, characterized in that, The device includes: A demand dictionary generation unit for generating a scientific and technological resource demand dictionary according to pre-generated user demand and a scientific and technological professional dictionary, the scientific and technological resource demand dictionary including a plurality of demand keywords; A first matching unit for matching the demand keywords and service keywords in the service category dictionary by the scientific and technological resource demand dictionary and the pre-generated service category dictionary, obtaining a demand service matching pair, the service matching pair including demand keywords and corresponding service keywords; A resource generation unit for generating target scientific and technological resources according to the user demand and service keywords corresponding to the scientific and technological resources; The user demand includes explicit demand, implicit demand and hidden demand; The resource generation unit is specifically configured to perform semantic similarity calculation on the explicit demand and the scientific and technological resources according to a pre-constructed scientific and technological service category tree, and obtain an explicit demand similarity; perform semantic similarity calculation on the implicit demand and the scientific and technological resources according to pre-acquired other user information, and obtain an implicit demand similarity; perform semantic similarity calculation on the hidden demand and the scientific and technological resources according to pre-acquired service text keywords, and obtain a hidden demand similarity; generate an overall similarity according to the explicit demand similarity, the implicit demand similarity and the hidden demand similarity, the overall similarity being a similarity between the user demand and the scientific and technological resources, sort the overall similarity to obtain an ordered overall similarity; and match the corresponding target scientific and technological resources according to the ordered overall similarity; The device further includes: A receiving unit for receiving explicit demand input by a user, the explicit demand being text actively expressed by a current user to be analyzed in a platform; The second matching unit is configured to match similar users according to the basic information of the user, specifically including: performing similarity matching on the user information of the current user to be analyzed and the user information recorded by the science and technology resource platform through a text similarity matching algorithm to match similar users. The implicit demand generation unit is configured to generate the implicit demand of the user according to the historical browsing information of the similar users, the implicit demand being the subconscious demand of the user determined by the characteristics of the user himself, and the demand range being the service category information that the user may demand. The hidden demand generation unit is configured to extract keywords from the service text of the obtained historical services to generate the hidden demand of the user, the hidden demand being the deeper demand of the user caused by the platform content, specifically including: extracting keywords from the service text of the historical services through a keyword extraction algorithm, and the extracted keywords being the hidden demand of the user.

7. The demand-based text technology resource pushing device according to claim 6, wherein, The device further includes: The data preprocessing unit is configured to perform data crawling and deduplication processing on the third-party professional word library to construct the science and technology professional dictionary.

8. The science and technology resource pushing device based on demand text according to claim 6, characterized in that The demand dictionary generation unit is specifically configured to accurately segment the user demand according to the science and technology professional dictionary through a segmentation tool to obtain a plurality of demand keywords.

9. The science and technology resource pushing device based on demand text according to claim 6, characterized in that The first matching unit is specifically configured to perform vocabulary consistency matching on the demand keywords and the service keywords, determine the demand keywords and the corresponding service keywords that pass the matching as a demand-service matching pair, and perform similarity matching on the demand keywords and the service keywords that fail the matching to obtain a demand-service matching pair.

10. The science and technology resource pushing device based on demand text according to claim 9, characterized in that The first matching unit is specifically configured to perform similarity calculation on the demand keywords and the service keywords that fail the matching through a string fuzzy matching library to obtain a plurality of fuzzy similarities, determine the demand keywords and the service keywords corresponding to the largest fuzzy similarity that pass the screening as an initial matching pair, and update the initial matching pair through a semantic similarity algorithm based on a science and technology service category tree to generate a demand-service matching pair.

11. A computer readable medium having stored thereon a computer program, characterized in that The program is executed by the processor to implement the science and technology resource pushing method based on demand text according to any one of claims 1 to 5.

12. A computer device comprising a memory for storing information including program instructions, and a processor for controlling execution of the program instructions, characterized in that, The program instructions are loaded and executed by the processor to implement the science and technology resource pushing method based on demand text according to any one of claims 1 to 5.

13. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instructions are executed by the processor to implement the science and technology resource pushing method based on demand text according to any one of claims 1 to 5.

Images