CN113343091A - Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program - Google Patents
Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program Download PDFInfo
- Publication number
- CN113343091A CN113343091A CN202110675859.2A CN202110675859A CN113343091A CN 113343091 A CN113343091 A CN 113343091A CN 202110675859 A CN202110675859 A CN 202110675859A CN 113343091 A CN113343091 A CN 113343091A
- Authority
- CN
- China
- Prior art keywords
- search
- recommendation
- enterprise
- data
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 40
- 238000005516 engineering process Methods 0.000 title claims description 35
- 239000013598 vector Substances 0.000 claims description 55
- 230000011218 segmentation Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 11
- 238000011161 development Methods 0.000 claims description 10
- 230000018109 developmental process Effects 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 4
- 238000000034 method Methods 0.000 abstract description 36
- 230000008569 process Effects 0.000 abstract description 8
- 230000015654 memory Effects 0.000 description 19
- 238000010586 diagram Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 8
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000007115 recruitment Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/258—Heading extraction; Automatic titling; Numbering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a scientific and technological service recommendation calculation method, a medium and a program for industries and enterprises, wherein the method comprises the following steps: after an enterprise user logs in a search engine and inputs search contents, acquiring current user data and current search data; based on the current user data, generating active recommendation content by using an active recommendation model; generating search recommendation content by using a search recommendation model based on the current search data; arranging and displaying the active recommended content and the search recommended content according to a preset rule; the information recommendation accuracy in the scientific and technological service recommendation process of the industry and the enterprise is improved, the potential requirements of enterprise users are met, the service recommendation mode combining the search recommendation content and the active recommendation content is realized, the capability of accurately acquiring the scientific and technological services of the industry and the enterprise is improved, and the experience of the enterprise users is improved.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a scientific and technological service recommendation calculation method, medium, and program for industries and enterprises.
Background
With the development of internet technology, enterprise users have more and more requirements for obtaining information, and network search technology occupies more and more important position. In the prior art, all network resources in the internet are generally searched according to keywords input by a user, and a search result meeting the search intention is returned to the user; however, the potential requirements of the enterprise user are not well utilized, for example, if the enterprise user inputs talent recruitment in a search box, the search tool only displays relevant information of the recruitment; however, in the prior art, the potential and interested contents of the enterprise user cannot be displayed, so that the requirements of the enterprise user cannot be well met, the services which may be needed by the enterprise user cannot be more intelligently recommended for the enterprise use, and the user experience is poor.
Disclosure of Invention
In view of this, embodiments of the present application provide a scientific and technological service recommendation calculation method, medium, and program for industries and enterprises, so as to improve accuracy and intelligence of information recommendation in a scientific and technological service recommendation process of industries and enterprises, and better meet potential requirements of enterprise users.
The embodiment of the application provides a scientific and technological service recommendation calculation method facing industries and enterprises, which is applied to a search engine and comprises the following steps:
after an enterprise user logs in a search engine and inputs search contents, acquiring current user data and current search data;
based on the current user data, generating active recommendation content by using an active recommendation model;
generating search recommendation content by using a search recommendation model based on the current search data;
and arranging and displaying the active recommended content and the search recommended content according to a preset rule.
In an embodiment, before the step of generating actively-recommended content by using an active recommendation model based on the current user data, the method includes:
constructing the active recommendation model specifically comprises:
acquiring historical user data, enterprise data related to historical users, historical search webpage click results and corresponding relations between the historical user data, the enterprise data related to the historical users and the historical search webpage click results;
inputting the historical user data, the enterprise data associated with the historical user, the historical search webpage click result and the corresponding relation between the historical user data, the enterprise data associated with the historical user and the historical search webpage click result into a neural network for training, and generating the active recommendation model after iterative updating.
In an embodiment, the generating actively-recommended content based on the current user data by using an active recommendation model includes:
inputting the current user data into the active recommendation model to generate a current search webpage click result;
and executing filtering operation on the current search webpage clicking result according to a preset condition to generate the active recommendation content.
In one embodiment, before the step of generating search recommendation content using a search recommendation model based on the search data, the method includes:
the constructing of the search recommendation model specifically includes:
acquiring historical search data and titles of click web pages in historical search results;
preprocessing the historical search data to generate a first text vector;
preprocessing the titles of the clicked web pages in the historical search results to generate a plurality of second text vectors;
respectively calculating the similarity between the first text vector and a plurality of second text vectors;
and when the similarity is higher than a similarity threshold value, the webpage corresponding to the second text vector is combined with industry and industry information corresponding to the historical user and industry attributes corresponding to the service required by the historical user to serve as search recommendation content, and a search recommendation model is constructed and obtained.
In one embodiment, the generating search recommendation content using a search recommendation model based on the current search data includes:
calculating the similarity between the current search data and the historical search data;
obtaining the historical search data corresponding to the maximum similarity;
and inputting the historical search data into the search recommendation model to generate search recommendation content corresponding to the historical search data.
In one embodiment, the calculating the similarity between the current search data and the historical search data includes:
performing word segmentation processing on the current search data;
converting the word segmentation processing result by using a vector conversion tool to generate a target text vector;
calculating a similarity between the target text vector and the first text vector.
In one embodiment, the current user data includes at least: enterprise name, industry, segment, development stage, population size, and enterprise needs.
In an embodiment, the performing, according to a preset condition, a filtering operation on the current search webpage click result to generate the actively recommended content includes:
and executing filtering operation on the current search page clicking result according to the enterprise requirement of the current user data and the enterprise and industry attributes corresponding to the required service to generate the active recommendation content.
To achieve the above object, there is also provided a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the steps of any of the above-mentioned industrial and enterprise-oriented scientific and technological service recommendation calculation methods.
In order to achieve the above object, there is also provided a computer storage medium having stored thereon a scientific and technological service recommendation calculation method program for industry and enterprise, wherein the scientific and technological service recommendation calculation method program for industry and enterprise realizes any of the steps of the scientific and technological service recommendation calculation method for industry and enterprise when being executed by a processor.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: after an enterprise user logs in a search engine and inputs search contents, acquiring current user data and current search data; acquiring correct current user data and current search data through the unique identifier of the enterprise user login, and providing correct data support for subsequently generating active recommended content and searching the recommended content;
based on the current user data, generating active recommendation content by using an active recommendation model; generating active recommendation content of potential requirements of a user through an active recommendation model;
generating search recommendation content by using a search recommendation model based on the current search data; generating search recommendation content currently searched by a user through a search recommendation model;
arranging and displaying the active recommended content and the search recommended content according to a preset rule; the active recommended content and the search recommended content are arranged and displayed, so that good experience is brought to the user. The method and the device improve the information recommendation accuracy in the scientific and technological service recommendation process, meet the potential requirements of enterprise users, realize a service recommendation mode combining search recommendation content and active recommendation content, and improve the experience of the enterprise users.
Drawings
FIG. 1 is a flowchart illustrating a first embodiment of a method for computing recommendations for industrial and enterprise-oriented scientific and technological services according to the present application;
FIG. 2 is a flowchart illustrating a second embodiment of the method for computing recommendations for industrial and enterprise-oriented scientific and technological services according to the present application;
FIG. 3 is a flowchart illustrating a step S220 of a second embodiment of a method for computing recommendation of science and technology services for industry and enterprise according to the present application;
FIG. 4 is a flowchart illustrating a step S230 of a second embodiment of the method for computing recommendation of science and technology services oriented to industry and enterprise according to the present application;
FIG. 5 is a flowchart illustrating a step S240 of a second embodiment of a method for computing recommendations of industrial and enterprise-oriented scientific and technological services according to the present application;
FIG. 6 is a flowchart illustrating a step S250 of a second embodiment of a method for computing recommendation of science and technology services oriented to industry and enterprise according to the present application;
FIG. 7 is a flowchart illustrating a step S251 of the industrial and enterprise-oriented scientific and technological service recommendation calculation method according to the present application;
fig. 8 is a schematic diagram of a hardware architecture of the science and technology service recommendation device for industry and enterprises according to the present application.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The main solution of the embodiment of the invention is as follows: after an enterprise user logs in a search engine and inputs search contents, acquiring current user data and current search data; based on the current user data, generating active recommendation content by using an active recommendation model; generating search recommendation content by using a search recommendation model based on the current search data; arranging and displaying the active recommended content and the search recommended content according to a preset rule; the method and the device improve the information recommendation accuracy in the enterprise service recommendation process, meet the potential requirements of enterprise users, realize a service recommendation mode combining search recommendation content and active recommendation content, and improve the experience of the enterprise users.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Referring to fig. 1, fig. 1 is a first embodiment of a science and technology service recommendation calculation method for industry and enterprise, applied to a search engine, the method including:
the scientific and technological service recommendation calculation method for the industry and the enterprises stores various enterprise resource information by taking an enterprise resource library as a data center of a system.
The enterprise resource library comprises a large amount of user data and search history records, wherein the search history records comprise corresponding relations between search data and search result click pages and the like.
Step S110: after an enterprise user logs in a search engine and inputs search contents, current user data and current search data are obtained.
Specifically, the search engine is a retrieval technology that retrieves formulated information from the internet by using a specific strategy according to user requirements and a certain algorithm and feeds the information back to a user. The search engine relies on various technologies, such as a web crawler technology, a retrieval sorting technology, a web page processing technology, a big data processing technology, a natural language processing technology and the like, and provides quick and high-relevance information service for information retrieval users.
Furthermore, the enterprise user can log in by using the unique identifier, specifically, can log in by using a user name and a password, and can also log in by using a mobile phone verification code, which is not limited herein; after the enterprise user logs in, acquiring data filled in when the enterprise user registers through a user name, and taking the data as current user data; and taking the search content input into the search engine box by the enterprise user as the current search data.
Step S120: and generating active recommendation content by using an active recommendation model based on the current user data.
Specifically, the current user data is input into an active recommendation model, and the active recommendation model performs calculation and matching to generate active recommendation content.
Step S130: and generating search recommendation content by utilizing a search recommendation model based on the current search data.
Specifically, the current search data is input into a search recommendation model, and the search recommendation model performs similarity calculation on the current search data and historical search data to obtain recommended content corresponding to the historical search data, which is used as the search recommended content corresponding to the current search data.
Step S140: and arranging and displaying the active recommended content and the search recommended content according to a preset rule.
Specifically, the actively recommended content and the search recommended content may be displayed according to a category, or the actively recommended content and the search recommended content may be alternately displayed.
In the above embodiment, there are advantageous effects of: after an enterprise user logs in a search engine and inputs search contents, acquiring current user data and current search data; acquiring correct current user data and current search data through the unique identifier of the enterprise user login, and providing correct data support for subsequently generating active recommended content and searching the recommended content;
based on the current user data, generating active recommendation content by using an active recommendation model; generating active recommendation content of potential requirements of a user through an active recommendation model;
generating search recommendation content by using a search recommendation model based on the current search data; generating search recommendation content currently searched by a user through a search recommendation model;
arranging and displaying the active recommended content and the search recommended content according to a preset rule; the active recommended content and the search recommended content are arranged and displayed, so that good experience is brought to the user. The method and the device improve the information recommendation accuracy in the enterprise service recommendation process, meet the potential requirements of enterprise users, realize a service recommendation mode combining search recommendation content and active recommendation content, and improve the experience of the enterprise users.
Referring to fig. 2, fig. 2 is a second embodiment of a science and technology service recommendation calculation method for industry and enterprise, applied to a search engine, the method including:
step S210: after an enterprise user logs in a search engine and inputs search contents, current user data and current search data are obtained.
Step S220: constructing an active recommendation model;
specifically, the active recommendation model may be a mathematical model based on statistics, or may be a neural network model, and is specifically adjusted according to business requirements.
Step S230: and generating active recommendation content by using an active recommendation model based on the current user data.
Step S240: constructing a search recommendation model;
in particular, the search recommendation model may be a mathematical model based on similarity calculations.
Step S250: and generating search recommendation content by utilizing a search recommendation model based on the current search data.
Step S260: and arranging and displaying the active recommended content and the search recommended content according to a preset rule.
Compared with the first embodiment, the second embodiment includes step S220 and step S240, and other steps are already described in the first embodiment and are not repeated herein.
In the above embodiment, there are advantageous effects: by constructing the active recommendation model and the search recommendation model, the accuracy of actively recommending content and searching recommended content is improved, and recommendation of potential demand services of the user is met.
Referring to fig. 3, fig. 3 is a detailed implementation step of step S220 in the second embodiment of the science and technology service recommendation calculation method for industry and enterprise, including:
step S221: the method comprises the steps of obtaining historical user data, enterprise data related to historical users, historical search webpage click results and corresponding relations between the historical user data, the enterprise data related to the historical users and the historical search webpage click results.
Specifically, the historical user data may be user registration data of a historical user, or user profile data; the enterprise data associated with the historical user may be data associated with an enterprise by the enterprise user; the historical search webpage clicking result can be a search webpage clicked by a corresponding historical user; the correspondence between the historical user data and the search webpage click result may be a correspondence between a user registration data and a user search webpage click result.
Step S222: inputting the historical user data, the enterprise data associated with the historical user, the historical search webpage click result and the corresponding relation between the historical user data, the enterprise data associated with the historical user and the historical search webpage click result into a neural network for training, and generating the active recommendation model after iterative updating.
In particular, the neural network model may specifically be a neural network prediction model; the neural network prediction model adopts a model for predicting unknown data by using a neural network model. The neural network prediction model includes, but is not limited to, a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a long-term memory network (LSTM), and the like.
Specifically, parameters of the neural network can be corrected and updated in a back propagation mode, so that the accuracy of the active recommendation model is further improved.
In the above embodiment, there are advantageous effects: and inputting the data and the corresponding relation between the data into the neural network model, so that the neural network learns the relation characteristics, and the correctness of the actively recommended content is provided.
Referring to fig. 4, fig. 4 is a detailed implementation step of step S230 in a second embodiment of a science and technology service recommendation calculation method for industry and enterprise, where the generating of actively recommended content by using an active recommendation model based on the current user data includes:
step S231: and inputting the current user data into the active recommendation model to generate a current search webpage click result.
Step S232: and executing filtering operation on the current search webpage clicking result according to a preset condition to generate the active recommendation content.
Specifically, the current search webpage click result can be filtered according to the development stage in the user data; comparing the development stages of the current user data and the historical user data to generate active recommended contents with the same development stages; meanwhile, the click result of the current search webpage can be filtered according to the industry in the user data; comparing the industry of the current user data with the industry of the historical user data to generate active recommendation content with the same industry form; specifically, the filtering operation executed under the preset condition is not limited herein, and may be executed according to the number of people, the enterprise demand, and the like.
In the above embodiment, there are advantageous effects: through further filtering operation, the generated active recommendation content is ensured to be more accurate, and the experience of enterprise service recommendation is further improved.
Referring to fig. 5, fig. 5 is a detailed implementation step of step S240 in the second embodiment of the science and technology service recommendation calculation method for industry and enterprise, including:
step S241: and acquiring historical search data and titles of clicked web pages in historical search results.
Step S242: and preprocessing the historical search data to generate a first text vector.
Specifically, the first text vector may be generated through operations such as word segmentation, denoising, and vector transformation.
Step S243: and preprocessing the titles of the clicked web pages in the historical search results to generate a plurality of second text vectors.
Specifically, word segmentation, denoising, vector conversion and other operations can be performed on the title of the clicked webpage to generate a second text vector; the keywords can also be extracted in a preset number by extracting the keywords of the clicked web pages in the historical search results, and vector conversion operation is performed on the keywords to generate a second text vector; wherein the preset number may be consistent with the number after the word segmentation operation in the search data.
Note that since the history search data corresponds to a plurality of clicked web pages, a plurality of second text vectors are generated.
Step S244 is to calculate the similarity between the first text vector and the plurality of second text vectors respectively.
Specifically, the similarity between the first text vector and the plurality of second text vectors may be calculated using cosine similarity.
Step S245: and when the similarity is higher than a similarity threshold value, the webpage corresponding to the second text vector is used as search recommendation content by combining industry and industry information corresponding to the historical user and industry attributes corresponding to the service required by the historical user, so that a search recommendation model is constructed.
Specifically, the similarity threshold may be set to 0.88 according to expert experience and multiple search test result analysis; the specific similarity threshold may also be other values, and may be adjusted according to the service requirement.
Specifically, the industry and industry information corresponding to the historical user may be the industry and industry information where the enterprise user is located; the industry and industry attributes corresponding to the service required by the historical user can be the industry and industry attributes where the service required by the enterprise user is located.
In the above embodiment, there are advantageous effects of: the search recommendation model can more accurately acquire the search webpages corresponding to the historical search data through learning the similarity between the historical search data and the titles of the clicked webpages in the historical search results, and the accuracy of the search recommendation model is improved.
Referring to fig. 6, fig. 6 is a detailed implementation step of step S250 in a second embodiment of a science and technology service recommendation calculation method for industry and enterprise, where the generating of search recommendation content by using a search recommendation model based on the current search data includes:
step S251: and calculating the similarity between the current search data and the historical search data.
Specifically, in the prior art, similarity between current search data and all current pages is generally calculated, and recommendation is performed according to results, so that the calculation efficiency of recommendation results is greatly influenced; in the embodiment, the similarity between the current search data and the historical search data is used, so that the calculation efficiency of the search engine is improved.
Step S252: and obtaining the historical search data corresponding to the maximum similarity.
Specifically, the history search data corresponding to the maximum value of the similarity between the current search data and the history search data is input as the current search data into the search recommendation model.
Step S253: and inputting the historical search data into the search recommendation model to generate search recommendation content corresponding to the historical search data.
In the above embodiment, there are advantageous effects of: the current search data is converted into historical search data with the highest similarity, and the click web page in the corresponding historical search result in the historical search data is obtained, so that the calculation efficiency of the search engine is greatly improved.
Referring to fig. 7, fig. 7 is a detailed implementation step of step S251 of the industrial and enterprise-oriented scientific and technological service recommendation calculation method of the present application, where the calculating of the similarity between the current search data and the historical search data includes:
step S2511: and performing word segmentation processing on the current search data.
Specifically, word segmentation is a process of recombining continuous word sequences into word sequences according to a certain specification. Existing word segmentation algorithms can be divided into three major categories: a word segmentation method based on character string matching, a word segmentation method based on understanding and a word segmentation method based on statistics. Whether the method is combined with the part-of-speech tagging process or not can be divided into a simple word segmentation method and an integrated method combining word segmentation and tagging. In this embodiment, a statistical machine learning-based method may be used, in which a large number of texts with words already segmented are given, and a statistical machine learning model is used to learn the rules of word segmentation, so as to implement segmentation of unknown texts. Meanwhile, a word segmentation device based on a neural network can be used, and a bidirectional LSTM (Long Short-Term Memory) and a CRF (conditional random field algorithm) are combined to realize the word segmentation device.
Step S2512: and converting the word segmentation processing result by using a vector conversion tool to generate a target text vector.
In particular, the vector transformation tool may be word2vec, where word2vec is a group of related models used to generate word vectors. These models are shallow, two-layer neural networks that are trained to reconstruct linguistic word text. The network is represented by words and the input words in adjacent positions are guessed, and the order of the words is unimportant under the assumption of the bag-of-words model in word2 vec. After training is completed, the word2vec model can be used to map each word to a vector, which can be used to represent the word-to-word relationship, and the vector is a hidden layer of the neural network; word2vec may complete the word to vector conversion. The vector conversion tool is not limited to the above.
Step S2513: calculating a similarity between the target text vector and the first text vector.
Specifically, a plurality of word vectors in the target text vector may be averaged to obtain a target average text vector; averaging a plurality of word vectors in the first text vector to obtain a first average text vector; the similarity between the target text vector and the first text vector is measured by calculating the distance between the target average text vector and the first average text vector. Meanwhile, the cosine similarity (cosine similarity) may also be utilized to evaluate the similarity between the target average text vector and the first average text vector by calculating the cosine value of the included angle between the two text vectors.
In the above embodiment, there are advantageous effects: the search recommendation content is obtained by calculating the similarity between the current search data and the historical search data, so that the calculation amount of the similarity between the current search data and a large number of webpages is greatly reduced, the efficiency of the scientific and technological service recommendation calculation method for industries and enterprises is improved, the search time of a user is saved, and the user experience is improved.
In one embodiment, the user data includes at least: enterprise name, industry, segment, development stage, population size, and enterprise needs.
Specifically, the development stage may correspond to the financing round, including the seed wheel, the angel wheel, the A wheel, the B wheel, the C wheel, the D wheel, the E wheel, etc., and may also be the startup period, the maturity period, and the sustained development period; the development stages are different, and enterprise requirements are also different, for example, the enterprise is in the startup period, and the enterprise may be more interested in financing, sites and the like, so that the user interest requirements are mined through user registration data, and the user experience brought by enterprise service recommendation is further improved.
In one embodiment, the performing, according to a preset condition, a filtering operation on the current search webpage click result to generate the active recommended content includes:
and executing filtering operation on the current search page clicking result according to the enterprise requirements of the current user data and the enterprise and industry attributes corresponding to the required service to generate the active recommendation content.
The present application further provides a computer program product, comprising a computer program, which when executed by a processor, implements any of the steps of the industrial and enterprise oriented scientific and technological service recommendation calculation method described above.
The present application further provides a computer storage medium, where an industry and enterprise oriented science and technology service recommendation calculation method program is stored on the computer storage medium, and when executed by a processor, the industry and enterprise oriented science and technology service recommendation calculation method program implements any of the steps of the industry and enterprise oriented science and technology service recommendation calculation method described above.
The application also provides scientific and technological service recommendation equipment for industries and enterprises, which comprises a memory, a processor and a scientific and technological service recommendation calculation method program for industries and enterprises, wherein the scientific and technological service recommendation calculation method program for industries and enterprises is stored in the memory and can run on the processor, and the processor realizes any step of the scientific and technological service recommendation calculation method for industries and enterprises when executing the scientific and technological service recommendation calculation method program for industries and enterprises.
The present application relates to an enterprise service recommendation device 010, including as shown in fig. 8: at least one processor 012, memory 011.
The processor 012 may be an integrated circuit chip having signal processing capability. In implementation, the steps of the method may be performed by hardware integrated logic circuits or instructions in the form of software in the processor 012. The processor 012 may be a general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 011, and the processor 012 reads the information in the memory 011 and completes the steps of the method in combination with the hardware.
It is to be understood that the memory 011 in embodiments of the present invention can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. The non-volatile Memory may be a Read Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double data rate Synchronous Dynamic random access memory (ddr DRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 011 of the systems and methods described in connection with the embodiments of the invention is intended to comprise, without being limited to, these and any other suitable types of memory.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may 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, and the like) having computer-usable program code embodied therein.
The present 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 flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable 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, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A scientific and technological service recommendation calculation method oriented to industry and enterprises is applied to a search engine, and is characterized by comprising the following steps:
after an enterprise user logs in a search engine and inputs search contents, acquiring current user data and current search data;
based on the current user data, generating active recommendation content by using an active recommendation model;
generating search recommendation content by using a search recommendation model based on the current search data;
and arranging and displaying the active recommended content and the search recommended content according to a preset rule.
2. The industry and enterprise oriented science and technology service recommendation calculation method of claim 1 wherein the step of generating actively recommended content using an active recommendation model based on the current user data is preceded by the step of:
constructing the active recommendation model specifically comprises:
acquiring historical user data, enterprise data related to historical users, historical search webpage click results and corresponding relations between the historical user data, the enterprise data related to the historical users and the historical search webpage click results;
inputting the historical user data, the enterprise data associated with the historical user, the historical search webpage click result and the corresponding relation between the historical user data, the enterprise data associated with the historical user and the historical search webpage click result into a neural network for training, and generating the active recommendation model after iterative updating.
3. The industry and enterprise oriented science and technology service recommendation calculation method of claim 2 wherein the generating actively recommended content using an active recommendation model based on the current user data comprises:
inputting the current user data into the active recommendation model to generate a current search webpage click result;
and executing filtering operation on the current search webpage clicking result according to a preset condition to generate the active recommendation content.
4. The industry and enterprise oriented science and technology service recommendation calculation method of claim 1 wherein the step of generating search recommendation content using a search recommendation model based on the search data comprises, prior to the step of:
the constructing of the search recommendation model specifically includes:
acquiring historical search data and titles of click web pages in historical search results;
preprocessing the historical search data to generate a first text vector;
preprocessing the titles of the clicked web pages in the historical search results to generate a plurality of second text vectors;
respectively calculating the similarity between the first text vector and a plurality of second text vectors;
and when the similarity is higher than a similarity threshold value, the webpage corresponding to the second text vector is combined with industry and industry information corresponding to the historical user and industry attributes corresponding to the service required by the historical user to serve as search recommendation content, and a search recommendation model is constructed and obtained.
5. The industry and enterprise oriented science and technology service recommendation calculation method of claim 4 wherein the generating search recommendation content using a search recommendation model based on the current search data comprises:
calculating the similarity between the current search data and the historical search data;
obtaining the historical search data corresponding to the maximum similarity;
and inputting the historical search data into the search recommendation model to generate search recommendation content corresponding to the historical search data.
6. The industry and enterprise oriented science and technology service recommendation calculation method of claim 5 wherein the calculating the similarity between the current search data and the historical search data comprises:
performing word segmentation processing on the current search data;
converting the word segmentation processing result by using a vector conversion tool to generate a target text vector;
calculating a similarity between the target text vector and the first text vector.
7. The industry and enterprise oriented science and technology service recommendation calculation method of claim 1 wherein the current user data includes at least: enterprise name, industry, segment, development stage, population size, and enterprise needs.
8. The industry and enterprise oriented science and technology service recommendation calculation method of claim 7, wherein the step of performing a filtering operation on the current search web page click result according to a preset condition to generate the active recommendation content comprises:
and executing filtering operation on the current search page clicking result according to the enterprise requirement of the current user data and the enterprise and industry attributes corresponding to the required service to generate the active recommendation content.
9. A computer program product comprising a computer program which, when being executed by a processor, carries out the steps of the industrial and business oriented scientific and technological service recommendation calculation method of any one of claims 1 to 8.
10. A computer storage medium, characterized in that the computer storage medium stores a program of a science and technology service recommendation calculation method for industry and enterprise, and the program of the science and technology service recommendation calculation method for industry and enterprise realizes the steps of the science and technology service recommendation calculation method for industry and enterprise as claimed in any one of claims 1-8 when being executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110675859.2A CN113343091A (en) | 2021-06-22 | 2021-06-22 | Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110675859.2A CN113343091A (en) | 2021-06-22 | 2021-06-22 | Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113343091A true CN113343091A (en) | 2021-09-03 |
Family
ID=77476498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110675859.2A Pending CN113343091A (en) | 2021-06-22 | 2021-06-22 | Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113343091A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115048152A (en) * | 2022-06-14 | 2022-09-13 | 厦门十三曜智能科技有限公司 | Method and system for determining starting-up interface, storage medium and server |
| WO2023151576A1 (en) * | 2022-02-08 | 2023-08-17 | 中兴通讯股份有限公司 | Search recommendation method, search recommendation system, computer device and storage medium |
| CN116720896A (en) * | 2023-08-10 | 2023-09-08 | 青岛阿斯顿工程技术转移有限公司 | Enterprise scientific and technological service personalized recommendation method and system based on big data |
| CN117194801A (en) * | 2023-11-06 | 2023-12-08 | 枣庄市云端互联网产业园管理有限公司 | Public service transferring system and method based on technology |
| CN118096325A (en) * | 2024-04-25 | 2024-05-28 | 深圳市城市公共安全技术研究院有限公司 | Enterprise safety product recommendation method, device, equipment and storage medium |
| CN118673201A (en) * | 2024-08-20 | 2024-09-20 | 杭州畅聚数字科技有限公司 | Enterprise service matching method and system based on large language model |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488789A (en) * | 2013-10-08 | 2014-01-01 | 百度在线网络技术（北京）有限公司 | Recommendation method, recommendation device and search engine |
| CN105809473A (en) * | 2016-02-29 | 2016-07-27 | 北京百度网讯科技有限公司 | Training method, service recommending method for coupling model parameters and associated apparatus |
| CN107330023A (en) * | 2017-06-21 | 2017-11-07 | 北京百度网讯科技有限公司 | Content of text based on focus recommends method and apparatus |
| CN110348930A (en) * | 2018-04-08 | 2019-10-18 | 阿里巴巴集团控股有限公司 | Business object data processing method, the recommended method of business object information and device |
| CN110543598A (en) * | 2019-09-06 | 2019-12-06 | 腾讯科技（深圳）有限公司 | information recommendation method and device and terminal |
| CN110727785A (en) * | 2019-09-11 | 2020-01-24 | 北京奇艺世纪科技有限公司 | Recommendation method, device and storage medium for training recommendation model and recommending search text |
-
2021
- 2021-06-22 CN CN202110675859.2A patent/CN113343091A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488789A (en) * | 2013-10-08 | 2014-01-01 | 百度在线网络技术（北京）有限公司 | Recommendation method, recommendation device and search engine |
| CN105809473A (en) * | 2016-02-29 | 2016-07-27 | 北京百度网讯科技有限公司 | Training method, service recommending method for coupling model parameters and associated apparatus |
| CN107330023A (en) * | 2017-06-21 | 2017-11-07 | 北京百度网讯科技有限公司 | Content of text based on focus recommends method and apparatus |
| CN110348930A (en) * | 2018-04-08 | 2019-10-18 | 阿里巴巴集团控股有限公司 | Business object data processing method, the recommended method of business object information and device |
| CN110543598A (en) * | 2019-09-06 | 2019-12-06 | 腾讯科技（深圳）有限公司 | information recommendation method and device and terminal |
| CN110727785A (en) * | 2019-09-11 | 2020-01-24 | 北京奇艺世纪科技有限公司 | Recommendation method, device and storage medium for training recommendation model and recommending search text |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023151576A1 (en) * | 2022-02-08 | 2023-08-17 | 中兴通讯股份有限公司 | Search recommendation method, search recommendation system, computer device and storage medium |
| CN115048152A (en) * | 2022-06-14 | 2022-09-13 | 厦门十三曜智能科技有限公司 | Method and system for determining starting-up interface, storage medium and server |
| CN116720896A (en) * | 2023-08-10 | 2023-09-08 | 青岛阿斯顿工程技术转移有限公司 | Enterprise scientific and technological service personalized recommendation method and system based on big data |
| CN116720896B (en) * | 2023-08-10 | 2023-10-24 | 青岛阿斯顿工程技术转移有限公司 | Enterprise scientific and technological service personalized recommendation method and system based on big data |
| CN117194801A (en) * | 2023-11-06 | 2023-12-08 | 枣庄市云端互联网产业园管理有限公司 | Public service transferring system and method based on technology |
| CN117194801B (en) * | 2023-11-06 | 2024-03-08 | 枣庄市云端互联网产业园管理有限公司 | Public service transferring system and method based on technology |
| CN118096325A (en) * | 2024-04-25 | 2024-05-28 | 深圳市城市公共安全技术研究院有限公司 | Enterprise safety product recommendation method, device, equipment and storage medium |
| CN118096325B (en) * | 2024-04-25 | 2024-07-26 | 深圳市城市公共安全技术研究院有限公司 | Enterprise safety product recommendation method, device, equipment and storage medium |
| CN118673201A (en) * | 2024-08-20 | 2024-09-20 | 杭州畅聚数字科技有限公司 | Enterprise service matching method and system based on large language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10783361B2 (en) | Predictive analysis of target behaviors utilizing RNN-based user embeddings | |
| CN113343091A (en) | Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program | |
| CN109376222B (en) | Question-answer matching degree calculation method, question-answer automatic matching method and device | |
| US7853599B2 (en) | Feature selection for ranking | |
| CN111382361B (en) | Information pushing method, device, storage medium and computer equipment | |
| CN110597962B (en) | Search result display method and device, medium and electronic equipment | |
| US12020267B2 (en) | Method, apparatus, storage medium, and device for generating user profile | |
| CN111259647A (en) | Question and answer text matching method, device, medium and electronic equipment based on artificial intelligence | |
| CN111639247A (en) | Method, apparatus, device and computer-readable storage medium for evaluating quality of review | |
| CN110781396A (en) | Information recommendation method, device, equipment and storage medium | |
| CN112131261A (en) | Community query method and device based on community network and computer equipment | |
| Zhu | Network Course Recommendation System Based on Double‐Layer Attention Mechanism | |
| CN110321483A (en) | A kind of online course content of platform recommended method, device, system and storage medium based on user's sequence sexual behaviour | |
| Khan et al. | Comparative analysis on Facebook post interaction using DNN, ELM and LSTM | |
| Sajeev et al. | Effective web personalization system based on time and semantic relatedness | |
| CN109086463A (en) | A kind of Ask-Answer Community label recommendation method based on region convolutional neural networks | |
| CN117573985B (en) | Information pushing method and system applied to intelligent online education system | |
| US20240004888A1 (en) | Sorting method, apparatus and device, and computer storage medium | |
| CN116956183A (en) | Multimedia resource recommendation method, model training method, device and storage medium | |
| Roy et al. | Early prediction of promising expert users on community question answering sites | |
| CN116340481B (en) | Method and device for automatically replying to question, computer readable storage medium and terminal | |
| US20240152652A1 (en) | Systems providing user engagement with enhanced and processed data that maintain anonymity | |
| US20230297720A1 (en) | Computing systems generating and using hypergraphs and linked hypergraphs for processing data and as a basis for user engagement with the processed data | |
| Gonzalez-Bonorino et al. | Adaptive Kevin: A Multipurpose AI Assistant for Higher Education | |
| CN115880018A (en) | User personalized commodity recommendation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210903 |