CN111104590A - Information recommendation method, device, medium and electronic equipment - Google Patents
Information recommendation method, device, medium and electronic equipmentDownload PDFInfo
- Publication number
- CN111104590A CN111104590ACN201911135367.3ACN201911135367ACN111104590ACN 111104590 ACN111104590 ACN 111104590ACN 201911135367 ACN201911135367 ACN 201911135367ACN 111104590 ACN111104590 ACN 111104590A
- Authority
- CN
- China
- Prior art keywords
- current user
- user
- information
- research
- data
- 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
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Recommending goods or services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an information recommendation method, an information recommendation device, an information recommendation medium and electronic equipment.
Background
With the rapid development of internet technology, a user can perform a series of operations on line. For example, a user may browse products online, purchase products, rate products, and so forth. Currently, in order to attract more users, each platform usually returns some product information to the users according to the evaluation of the products after the users complete the purchase. However, the current research data collection and management system generally forms a report on the data processing method, calculates the average score of the net recommendation value according to the net recommendation value in the report, and then evaluates the customer experience level of the company according to the scores, but the reason for the net recommendation value fed back by the customer is generally to provide detailed list information, so that the analysis needs to be performed by personnel in related departments, the analysis has a large dependence on the subjective ability of the analysts, and has the problem of long time effectiveness, and the methods are all post-analysis.
It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present invention and therefore may include information that does not constitute prior art known to a person of ordinary skill in the art.
Disclosure of Invention
The embodiment of the invention aims to provide an information recommendation method, an information recommendation device, an information recommendation medium and electronic equipment, and further the defects that in the related technology, the accuracy of information recommended to a user is low, the information is easy to be worn by users, and the user experience is reduced can be solved at least to a certain extent.
Additional features and advantages of the invention will be set forth in the detailed description which follows, or may be learned by practice of the invention.
According to a first aspect of the embodiments of the present invention, there is provided an information recommendation method, including: acquiring research data of a current user; extracting key words from the research data of the current user; determining the similarity between the research data of the current user and preset content according to the keyword and the preset content, wherein the preset content comprises evaluation content of a historical user, portrait information of the historical user and research characteristic information of the historical user; and determining information recommended to the current user according to the similarity between the research data of the current user and the preset content.
In some embodiments of the invention, the research data comprises any one or more of: the evaluation content of the current user, the portrait information of the current user and the research characteristic information of the current user.
In some embodiments of the present invention, determining the similarity between the research data of the current user and the preset content according to the keyword and the preset content includes: and determining the similarity of the research data of the current user and preset content according to the keywords extracted from the evaluation content of the current user, the keywords extracted from the portrait information of the current user, the keywords extracted from the research characteristic information of the current user, the evaluation content of the historical user, the portrait information of the historical user and the research characteristic information of the historical user.
In some embodiments of the present invention, the formula for calculating the similarity is:
wherein N (i) is a set of keywords, i is a keyword in the set of keywords, N (j) is preset content, j is evaluation content of the historical user, portrait information of the historical user and research characteristic information of the historical user, and W isijAnd obtaining the similarity between the research data of the current user and preset content.
In some embodiments of the present invention, determining the information recommended to the current user according to the similarity between the research data of the current user and the preset content includes: determining the matching degree of similar data and information in a recommendation message pool according to the similarity between the research data of the current user and the preset content and the information in the recommendation message pool, wherein the similar data comprises the data of the preset content similar to the research data of the current user; and determining information recommended to the current user according to the matching degree.
In some embodiments of the present invention, the formula for calculating the matching degree is:
wherein i is a keyword in the set of keywords, L (a) is a set of recommendation messages, and a is information in the set of recommendation messages; s is data of K historical users similar to the research data of the current user in the preset content, b is one piece of data in the data of the K historical users, and W isijSimilarity of the research data of the current user and preset content, RaiFor a predetermined degree of recommendation for keyword i, PabK matching degrees of data of K historical users and information in L (a).
In some embodiments of the present invention, the evaluation content of the current user includes a net recommendation value; before extracting keywords from the research data of the current user, the method further comprises: classifying the investigation data of the current user according to the net recommended value; and determining the range of the preset content according to the classification result.
According to a second aspect of the embodiments of the present invention, there is provided an information recommendation apparatus including: the acquisition module is used for acquiring the research data of the current user; the extraction module is used for extracting keywords from the research data of the current user; the first determining module is used for determining the similarity between the research data of the current user and preset content according to the keyword and the preset content, wherein the preset content comprises evaluation content of a historical user, portrait information of the historical user and research characteristic information of the historical user; and the second determining module is used for determining the information recommended to the current user according to the similarity between the research data of the current user and the preset content.
In some embodiments of the invention, the research data comprises any one or more of: the evaluation content of the current user, the portrait information of the current user and the research characteristic information of the current user.
In some embodiments of the invention, the first determining module is configured to: and determining the similarity of the research data of the current user and preset content according to the keywords extracted from the evaluation content of the current user, the keywords extracted from the portrait information of the current user, the keywords extracted from the research characteristic information of the current user, the evaluation content of the historical user, the portrait information of the historical user and the research characteristic information of the historical user.
In some embodiments of the present invention, the formula for calculating the similarity is:
wherein N (i) is a set of keywords, i is a keyword in the set of keywords, N (j) is preset content, j is evaluation content of the historical user, portrait information of the historical user and research characteristic information of the historical user, and W isijAnd obtaining the similarity between the research data of the current user and preset content.
In some embodiments of the invention, the second determining module includes: a matching degree determining module, configured to determine, according to the similarity between the research data of the current user and the preset content and the information in the recommendation message pool, the matching degree between similar data and the information in the recommendation message pool, where the similar data includes data in which the preset content is similar to the research data of the current user; and the information determining module is used for determining the information recommended to the current user according to the matching degree.
In some embodiments of the present invention, the formula for calculating the matching degree is:
wherein i is a keyword in the set of keywords, L (a) is a set of recommendation messages, and a is information in the set of recommendation messages; s is data of K historical users similar to the research data of the current user in the preset content, b is one piece of data in the data of the K historical users, and W isijSimilarity of the research data of the current user and preset content, RaiFor a predetermined degree of recommendation for keyword i, PabK matching degrees of data of K historical users and information in L (a).
In some embodiments of the present invention, the evaluation content of the current user includes a net recommendation value; before extracting keywords from the research data of the current user, the apparatus further comprises: the classification module is used for classifying the investigation data of the current user according to the net recommendation value; and the third determining module is used for determining the range of the preset content according to the classification result.
According to a third aspect of embodiments of the present invention, there is provided an electronic apparatus, including: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method of constructing a knowledge graph as described in the first aspect of the embodiments above.
According to a fourth aspect of embodiments of the present invention, there is provided a computer readable medium, on which a computer program is stored, which when executed by a processor, implements the method of constructing a knowledge graph as described in the first aspect of the embodiments above.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
according to the technical scheme provided by some embodiments of the invention, the research data of the current user is obtained, the keyword is extracted from the research data of the current user, the similarity between the research data of the current user and the preset content is further determined according to the keyword and the preset content, the preset content comprises the evaluation content of the historical user, the portrait information of the historical user and the research characteristic information of the historical user, and then the information recommended to the current user is determined according to the similarity between the research data of the current user and the preset content.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:
fig. 1 is a schematic diagram illustrating an exemplary system architecture to which an information recommendation method or an information recommendation apparatus according to an embodiment of the present invention may be applied;
FIG. 2 schematically shows a flow chart of an information recommendation method according to an embodiment of the invention;
FIG. 3 schematically shows a flow diagram of an information recommendation method according to another embodiment of the invention;
FIG. 4 schematically shows a flow diagram of an information recommendation method according to another embodiment of the invention;
fig. 5 schematically shows a block diagram of an information recommendation apparatus according to an embodiment of the present invention;
fig. 6 schematically shows a block diagram of an information recommendation apparatus according to another embodiment of the present invention;
fig. 7 schematically shows a block diagram of an information recommendation apparatus according to another embodiment of the present invention;
FIG. 8 illustrates a schematic structural diagram of a computer system suitable for use with the electronic device to implement an embodiment of the invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to provide a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations or operations have not been shown or described in detail to avoid obscuring aspects of the invention.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
Fig. 1 is a schematic diagram illustrating an exemplary system architecture to which an information recommendation method or an information recommendation apparatus according to an embodiment of the present invention may be applied.
As shown in fig. 1, thesystem architecture 100 may include one or more ofterminal devices network 104, and aserver 105. Thenetwork 104 serves as a medium for providing communication links between theterminal devices server 105.Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example,server 105 may be a server cluster comprised of multiple servers, or the like.
The user may use theterminal devices server 105 via thenetwork 104 to receive or send messages or the like. Theterminal devices
Theserver 105 may be a server that provides various services. For example, a user uploads research data of a current user to theserver 105 by using the terminal device 103 (or theterminal device 101 or 102), theserver 105 may extract keywords from the research data of the current user, and determine a similarity between the research data of the current user and preset content according to the keywords and the preset content, where the preset content includes evaluation content of a historical user, portrait information of the historical user, and research characteristic information of the historical user, and further determine information recommended to the current user according to the similarity between the research data of the current user and the preset content, in this way, accurate recommendation information to the user may be pertinently recommended, so that the user is more satisfied after receiving the recommendation information, and thus the stickiness of a platform and the user is improved.
In some embodiments, the information recommendation method provided by the embodiments of the present invention is generally executed by theserver 105, and accordingly, the information recommendation device is generally disposed in theserver 105. In other embodiments, some terminals may have similar functionality as the server to perform the method. Therefore, the information recommendation method provided by the embodiment of the invention is not limited to be executed at the server side.
Fig. 2 schematically shows a flow chart of an information recommendation method according to an embodiment of the invention.
As shown in fig. 2, the information recommendation method may include steps S210 to S240.
In step S210, research data of the current user is acquired.
In step S220, keywords are extracted from the research data of the current user.
In step S230, determining a similarity between the research data of the current user and a preset content according to the keyword and the preset content, where the preset content includes evaluation content of a historical user, portrait information of the historical user, and research characteristic information of the historical user.
In step S240, information recommended to the current user is determined according to the similarity between the research data of the current user and the preset content.
According to the method, the research data of the current user can be obtained, the keywords are extracted from the research data of the current user, the similarity between the research data of the current user and the preset content is further determined according to the keywords and the preset content, the preset content comprises the evaluation content of the historical user, the portrait information of the historical user and the research characteristic information of the historical user, and then the information recommended to the current user is determined according to the similarity between the research data of the current user and the preset content.
In an embodiment of the present invention, the manner of obtaining the above-mentioned current user call data generally includes two manners, which are a contact type investigation and a relationship investigation. Among them, the relational investigation is the traditional low frequency investigation, and the period is generally longer. The contact type investigation is real-time investigation in the interaction process of the client and the platform through different scenes, for example, corresponding investigation and interaction are carried out with the client in a specific link, the real-time performance and the scene of the interaction are more accurate, and the result information of the investigation can be more effectively utilized. By way of example only, in an insurance platform, a relational investigation may be sending questionnaires to customers who have not visited the insurance platform for a period of time to obtain research data of the customers. The contact type questionnaire may be a questionnaire that is pushed to the user in real time as the customer performs some operation on the insurance platform. For example, a customer is currently underwriting a policy on an insurance platform, in which case a questionnaire may be sent to the user to see if the user has problems in the current contact session, or if the user is satisfied in the current contact session, and so on. Additionally, the policy acceptance herein may be referred to as a contact.
In an embodiment of the invention, the survey data comprises any one or more of: the evaluation content of the current user, the portrait information of the current user and the research characteristic information of the current user. For example, the evaluation content of the current user may refer to answers given by the current user for a questionnaire of a relational type survey or a questionnaire of a contact type survey. The current user representation information may refer to basic information of the current user, such as, but not limited to, the age of the user, the name of the user, the city in which the user lives, the marital status of the user, the gender of the user, the religious beliefs of the user, the highest scholastic calendar of the user, the occupation of the user, the identity of the user on the platform, whether the user is a VIP of the platform, the financial profile of the user, personal preferences of the user, and so forth. The research characteristic information of the current user may refer to a manner in which the current user is researched, for example, a relational type research or a contact type research. If the mode adopted by the research current user is relational research, the research characteristic information may further include the sending time of the questionnaire of the relational research, the questionnaire sent to the user in what specific mode, and the like. If the current user is conducting a contact type survey, the survey characteristics information may also include a questionnaire to be sent to the user at which contact, the time at which the questionnaire was sent, and a description of the contact, etc.
In one embodiment of the present invention, extracting keywords from the research data of the current user may include keywords extracted from the evaluation content of the current user, keywords extracted from the portrait information of the current user, and keywords extracted from the research characteristic information of the current user. For example, the evaluation content of the current user is "the profits of the financial products of the precious company are stable too good", and the keywords extracted for the evaluation content may be "the precious company", "the financial products", "the profits are stable", "too good". For another example, the keywords extracted from the current user portrait information may be a name of the user, personal preferences of the user, financial status of the user, and the like, and may be obtained according to actual situations. As another example, the keywords extracted from the research feature information of the current user may be the type of research, the time when the research was initiated, and feature information for a relational research or feature information for a contact research.
In one embodiment of the invention, the preset content comprises evaluation content of a historical user, portrait information of the historical user and research characteristic information of the historical user. The evaluation content of the historical user may refer to answers given by the historical user in the past to a questionnaire of a relational investigation or a questionnaire of a contact type investigation. The historical user representation information may refer to basic information of the historical user, such as, but not limited to, the age of the user, the name of the user, the city in which the user lives, the marital status of the user, the gender of the user, the religious beliefs of the user, the highest scholastic calendar of the user, the occupation of the user, the identification of the user on the platform, whether the user is a VIP of the platform, the financial profile of the user, the personal preferences of the user, and so forth. The research profile of the historical user may refer to the manner in which the historical user was researched, such as a relational or a contact type research. If the mode adopted by the research history user is relational research, the research characteristic information may further include the sending time of the questionnaire of the relational research, the questionnaire sent to the user by what specific mode, and the like. If the user of the research history takes the form of a contact type research, the research characteristic information may also include a questionnaire to be sent to the user at which contact, the time at which the questionnaire was sent, and a description of the contact, etc. In this example, the historical user may include the current user, that is, the current user has performed an evaluation behavior on the platform in the past, so the preset content may include the evaluation content obtained by the current user through research in the past, which is more targeted in pushing information to the user, and further improves user experience.
Based on the scheme, the similarity between the research data of the current user and the preset content is determined according to the keywords and the preset content, and the similarity can be specifically divided into calculating the comprehensive similarity between the evaluation content of the current user, the portrait information of the current user, the research characteristic information of the current user, the evaluation content of the historical user, the portrait information of the historical user and the research characteristic information of the historical user, wherein the similarity reflects the content in the research data of the current user and the content similar to the research data of the current user in the preset content, and information is pushed to the user more pertinently and accurately based on the similarity.
In an embodiment of the present invention, the evaluation content of the current user may further include a net recommendation value, which is used to reflect the satisfaction degree of the user on the product in the platform.
In an embodiment of the present invention, before calculating the similarity between the research data of the current user and the preset content, the method may further classify the research data of the current user according to the net recommendation value, and then determine the range of the preset content according to the classification result. For example, the net recommendation value in the research data of the current user is 9, the research data of the current user can be classified into a category which is satisfied with the products in the platform according to the net recommendation value, and in this case, because the research data of the current user is classified into a category which is satisfied with the products in the platform, the range of the preset content can also be the category which is satisfied with the products in the platform by the historical user, so that the similarity between the research data of the current user and the preset content is calculated in the following process, the information pushed to the current user is more targeted, the information pushed to the current user is closer to the information which the actual user wants to see, and the viscosity between the platform and the user is further improved.
Fig. 3 schematically shows a flow chart of an information recommendation method according to another embodiment of the present invention.
Before step S220, the method further includes step S310 and step S320, as shown in fig. 3.
In step S310, the research data of the current user is classified according to the net recommendation value.
In step S320, the range of the preset content is determined according to the classification result.
The method can classify the research data of the current user according to the net recommendation value, and then determine the range of the preset content according to the classification result, so that the similarity between the research data of the current user and the preset content is calculated in the follow-up process in a more targeted manner, the information pushed to the current user is closer to the information which the actual user wants to see, and the viscosity of the platform and the user is further improved.
For example, the net recommendation value in the research data of the current user is 9, the research data of the current user can be classified into a category which is satisfied with the products in the platform according to the net recommendation value, and in this case, because the research data of the current user is classified into a category which is satisfied with the products in the platform, the range of the preset content can also be the category which is satisfied with the products in the platform by the historical user, so that the similarity between the research data of the current user and the preset content is calculated in the following process, the information pushed to the current user is more targeted, the information pushed to the current user is closer to the information which the actual user wants to see, and the viscosity between the platform and the user is further improved.
For another example, for example, the net recommendation value in the research data of the current user is 3, the research data of the current user may be classified into a category that is not satisfied with the product in the platform according to the net recommendation value, in this case, since the research data of the current user is classified into a category that is not satisfied with the product in the platform, the range of the preset content may also be a category that the historical user is not satisfied with the product in the platform, so that it is more targeted when the similarity between the research data of the current user and the preset content is subsequently calculated, so that the information pushed to the current user is closer to the information that the actual user wants to see, and the viscosity between the platform and the user is further improved.
In an embodiment of the present invention, determining the similarity between the research data of the current user and the preset content according to the keyword and the preset content includes: according to the keywords extracted from the evaluation content of the current user, the keywords extracted from the portrait information of the current user, the keywords extracted from the research characteristic information of the current user, the evaluation content of the historical user, the portrait information of the historical user and the research characteristic information of the historical user, the similarity between the research data of the current user and the preset content is determined, the similarity reflects the content in the research data of the current user and the content similar to the research data of the current user in the preset content, and information is pushed to the user more specifically and more accurately based on the similarity.
In one embodiment of the invention, the search engine Lucene-based algorithm for text keyword extraction is utilized to extract keywords from the research data of the current user. For example, the keyword with higher term frequency is extracted from the Lucene index based on the research data of the current user, and the keyword is the keyword of the research data of the current user, for example, the keyword may be a term related to the name of a product, information of the user, and satisfaction degree of the product. When the Lucene extracts keywords, a semantic label can be labeled for each keyword, so as to reflect the quality of the evaluation content of the user. In addition, the Lucene indexing process is a process of living inverted index with lexical items, which can remove more text information from the text, such as punctuation marks, stop words, word strength words, and the like, and finally generate lexical items, i.e. keywords of the research data of the current user.
In one embodiment of the invention, the similarity between the research data of the current user and the preset content is calculated through a collaborative filtering recommendation algorithm, and the information recommended to the current user is determined according to the similarity between the research data of the current user and the preset content. In this embodiment, two formulas in the collaborative filtering recommendation algorithm are adopted, a formula (1) for calculating the similarity between the research data of the current user and the preset content, and a formula (2) for determining the information recommended to the current user according to the similarity between the research data of the current user and the preset content. The information recommended to the current user by using the collaborative filtering recommendation algorithm may specifically be considered whether the research data of the current user is matched with preset content, for example, keyword matching, classification matching, source matching, topic matching, contact matching, and the like.
In one embodiment of the present invention, the common formula (1) for calculating the similarity is:
wherein N (i) is a set of keywords, i is a keyword in the set of keywords, N (j) is preset content, j is evaluation content of the historical user, portrait information of the historical user and research characteristic information of the historical user, and W isijAnd obtaining the similarity between the research data of the current user and preset content.
By the formula (1), similarity among the keywords extracted from the evaluation content of the current user, the keywords extracted from the portrait information of the current user, the keywords extracted from the research characteristic information of the current user, the evaluation content of the historical user, the portrait information of the historical user and the research characteristic information of the historical user can be calculated, the similarity reflects the content in the research data of the current user and the content similar to the research data of the current user in the preset content, and information is pushed to the user more pertinently and accurately based on the similarity.
Fig. 4 schematically shows a flow chart of an information recommendation method according to another embodiment of the present invention.
As shown in fig. 4, the step S240 may include a step S410 and a step S420.
In step S410, determining a matching degree between similar data and information in the recommendation message pool according to the similarity between the research data of the current user and the preset content and the information in the recommendation message pool, where the similar data includes data in which the preset content is similar to the research data of the current user.
In step S420, information recommended to the current user is determined according to the matching degree.
The method can determine the matching degree of the similar data and the information in the recommendation message pool according to the similarity of the research data of the current user and the preset content and the information in the recommendation message pool, and then determine the information recommended to the current user according to the matching degree.
In an embodiment of the present invention, the similar data includes data with preset content similar to the research data of the current user. For example, the similarity calculated by the above formula (1) specifically indicates that the research data of the current user is similar to the evaluation content, the user portrait information, and the research characteristic information of a part of historical users in the preset content, and the evaluation content, the user portrait information, and the research characteristic information of the part of historical users are taken as the similar data. Wherein, the similar data includes the research data of the current user.
In one embodiment of the present invention, the information in the recommendation message pool includes any one or more of the following items: information title, keywords, content abstract, text, propagation depth, heat, effective time and conversion rate. Wherein, the information title may be "toothache is a incident? Neglecting oral lesion signals in millions of cases, the keywords can be "health risk and oral cavity", and the content abstract is "toothache is a incident? The oral lesion signal is ignored in millions, the text is 'the reason of oral lesions', the propagation depth is 6, the heat is 8, the effective time is 2019, and the conversion rate is 12%. In this embodiment, the matching degree between the similar data and the information in the recommended message pool is determined according to the similarity between the research data of the current user and the preset content and the information in the recommended message pool, which can help to solve the problem that the algorithm is more narrow and more narrow to a certain extent, for example, the collaborative filtering recommendation algorithm is used to analyze the similarity between different users, such as click similarity, interest classification similarity, propagation depth similarity and conversion rate similarity, instead of considering the existing history of the user, so as to expand the exploration capability of the model.
The propagation depth in this example may be the number of times of forwarding due to the history user forwarding the message after receiving the message, the popularity may be 8 times of browsing the message by different history users, and the conversion rate may be 12% of the probability of whether the history user has a next action due to the message after receiving the message, for example, the next action is to purchase a product in the message.
In one embodiment of the present invention, formula (2) for calculating the matching degree is:
wherein i is a keyword in the set of keywords, L (a) is a set of recommendation messages, and a is information in the set of recommendation messages; s is data of K historical users similar to the research data of the current user in the preset content, b is one piece of data in the data of the K historical users, and W isijSimilarity of the research data of the current user and preset content, RaiFor a predetermined degree of recommendation for keyword i, PabK matching degrees of data of K historical users and information in L (a).
In one embodiment of the present invention, R isaiMay be determined based on the propagation depth, heat, and/or conversion rate in each of the aforementioned recommendation messages.
In an embodiment of the present invention, the matching degree between the similar data and the information in the recommended message pool can be determined according to the similarity between the research data of the current user and the preset content and the information in the recommended message pool through the formula (2). For example, the similar data is data of K historical users similar to research data of the current user in preset content, K matching degrees of the data of the K historical users and the information in l (a) can be obtained through the formula (2), the K matching degrees are ranked, the maximum matching degree is used as the matching degree of the similar data and the information in the recommendation message pool, and the information recommended to the current user is determined from the recommendation message pool according to the maximum matching degree, so that the accuracy of pushing the information to the user is further improved.
Fig. 5 schematically shows a block diagram of an information recommendation apparatus according to an embodiment of the present invention.
As shown in fig. 5, theinformation recommendation apparatus 500 includes anacquisition module 510, anextraction module 520, afirst determination module 530, and asecond determination module 540.
Specifically, the obtainingmodule 510 is configured to obtain research data of a current user.
An extractingmodule 520, configured to extract keywords from the research data of the current user.
A first determiningmodule 530, configured to determine, according to the keyword and preset content, a similarity between the research data of the current user and the preset content, where the preset content includes evaluation content of a historical user, portrait information of the historical user, and research characteristic information of the historical user.
A second determiningmodule 540, configured to determine, according to the similarity between the research data of the current user and the preset content, information recommended to the current user.
Theinformation recommendation device 500 can determine the similarity between the research data of the current user and the preset content by acquiring the research data of the current user and extracting the keywords from the research data of the current user according to the keywords and the preset content, wherein the preset content comprises the evaluation content of the historical user, the portrait information of the historical user and the research characteristic information of the historical user, and then determine the information recommended to the current user according to the similarity between the research data of the current user and the preset content.
According to an embodiment of the present invention, theinformation recommendation apparatus 500 may be used to implement the information recommendation method described in the embodiment of fig. 2.
FIG. 6 schematically shows a block diagram of an apparatus for constructing a knowledge-graph according to another embodiment of the present invention.
As shown in fig. 6, theinformation recommendation apparatus 500 further includes aclassification module 550 and athird determination module 560.
Specifically, the classifyingmodule 550 is configured to classify the research data of the current user according to the net recommendation value.
And a third determiningmodule 560, configured to determine the range of the preset content according to the classification result.
Theinformation recommendation device 500 may classify the research data of the current user according to the net recommendation value, and then determine the range of the preset content according to the classification result, so that the similarity between the research data of the current user and the preset content is calculated in the following process, the information pushed to the current user is more targeted, the information expected to be watched by the actual user is closer to the information, and the viscosity between the platform and the user is further improved.
According to an embodiment of the present invention, theinformation recommendation apparatus 500 may be used to implement the information recommendation method described in the embodiment of fig. 3.
Fig. 7 schematically shows a block diagram of an information recommendation apparatus according to another embodiment of the present invention.
As shown in fig. 7, the second determiningmodule 540 includes a matchingdegree determining module 541 and aninformation determining module 542.
Specifically, the matchingdegree determining module 541 is configured to determine, according to the similarity between the research data of the current user and the preset content and the information in the recommendation message pool, the matching degree between similar data and the information in the recommendation message pool, where the similar data includes data in which the preset content is similar to the research data of the current user.
And aninformation determining module 542, configured to determine, according to the matching degree, information recommended to the current user.
The second determiningmodule 540 may determine the matching degree of the similar data and the information in the recommendation message pool according to the similarity between the research data of the current user and the preset content and the information in the recommendation message pool, and then determine the information recommended to the current user according to the matching degree.
According to an embodiment of the present invention, the second determiningmodule 540 may be used to implement the information recommendation method described in the embodiment of fig. 4.
For details that are not disclosed in the embodiments of the apparatus of the present invention, please refer to the above-described embodiments of the information recommendation method of the present invention for the details that are not disclosed in the embodiments of the apparatus of the present invention, because each module of the information recommendation apparatus of the exemplary embodiment of the present invention can be used to implement the steps of the exemplary embodiments of the information recommendation method described in the above-described 2 to 4.
It is understood that the obtainingmodule 510, the extractingmodule 520, the first determiningmodule 530, the second determiningmodule 540, the matchingdegree determining module 541, theinformation determining module 542, the classifyingmodule 550, and the third determiningmodule 560 may be combined into one module to be implemented, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present invention, at least one of the obtainingmodule 510, the extractingmodule 520, the first determiningmodule 530, the second determiningmodule 540, the matchingdegree determining module 541, theinformation determining module 542, the classifyingmodule 550, and the third determiningmodule 560 may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or in a suitable combination of three implementations of software, hardware, and firmware. Alternatively, at least one of theacquisition module 510, theextraction module 520, thefirst determination module 530, thesecond determination module 540, the matchingdegree determination module 541, theinformation determination module 542, theclassification module 550, and thethird determination module 560 may be at least partially implemented as a computer program module that, when executed by a computer, may perform the functions of the respective modules.
Referring now to FIG. 8, shown is a block diagram of acomputer system 600 suitable for use with the electronic device implementing an embodiment of the present invention. Thecomputer system 600 of the electronic device shown in fig. 8 is only an example, and should not bring any limitation to the function and the scope of use of the embodiments of the present invention.
As shown in fig. 8, thecomputer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from astorage section 608 into a Random Access Memory (RAM) 603. In theRAM 603, various programs and data necessary for system operation are also stored. The CPU601,ROM 602, andRAM 603 are connected to each other via abus 604. An input/output (I/O)interface 605 is also connected tobus 604.
The following components are connected to the I/O interface 605: aninput portion 606 including a keyboard, a mouse, and the like; anoutput portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; astorage section 608 including a hard disk and the like; and acommunication section 609 including a network interface card such as a LAN card, a modem, or the like. Thecommunication section 609 performs communication processing via a network such as the internet. Thedriver 610 is also connected to the I/O interface 605 as needed. Aremovable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on thedrive 610 as necessary, so that a computer program read out therefrom is mounted in thestorage section 608 as necessary.
In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the invention include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through thecommunication section 609, and/or installed from theremovable medium 611. The above-described functions defined in the system of the present application are executed when the computer program is executed by the Central Processing Unit (CPU) 601.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present invention may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.
As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to implement the information recommendation method as described in the above embodiments.
For example, the electronic device may implement the following as shown in fig. 2: in step S210, research data of the current user is acquired. In step S220, keywords are extracted from the research data of the current user. In step S230, determining a similarity between the research data of the current user and a preset content according to the keyword and the preset content, where the preset content includes evaluation content of a historical user, portrait information of the historical user, and research characteristic information of the historical user. In step S240, information recommended to the current user is determined according to the similarity between the research data of the current user and the preset content.
It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the invention. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiment of the present invention.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. An information recommendation method, comprising:
acquiring research data of a current user;
extracting key words from the research data of the current user;
determining the similarity between the research data of the current user and preset content according to the keyword and the preset content, wherein the preset content comprises evaluation content of a historical user, portrait information of the historical user and research characteristic information of the historical user; and
and determining information recommended to the current user according to the similarity between the research data of the current user and the preset content.
2. The method of claim 1, wherein the research data comprises any one or more of: the evaluation content of the current user, the portrait information of the current user and the research characteristic information of the current user.
3. The method of claim 3, wherein determining the similarity between the research data of the current user and the preset content according to the keyword and the preset content comprises:
and determining the similarity of the research data of the current user and preset content according to the keywords extracted from the evaluation content of the current user, the keywords extracted from the portrait information of the current user, the keywords extracted from the research characteristic information of the current user, the evaluation content of the historical user, the portrait information of the historical user and the research characteristic information of the historical user.
4. The method of claim 3, wherein the similarity is calculated by the formula:
wherein N (i) is a set of keywords, i is a keyword in the set of keywords, N (j) is preset content, and j isThe evaluation content of the historical user, the historical user portrait information, and the research characteristic information of the historical user, WijAnd obtaining the similarity between the research data of the current user and preset content.
5. The method of claim 1, wherein determining the information recommended to the current user according to the similarity between the research data of the current user and the preset content comprises:
determining the matching degree of similar data and information in a recommendation message pool according to the similarity between the research data of the current user and the preset content and the information in the recommendation message pool, wherein the similar data comprises the data of the preset content similar to the research data of the current user;
and determining information recommended to the current user according to the matching degree.
6. The method of claim 5, wherein the matching degree is calculated by the formula:
wherein i is a keyword in the set of keywords, L (a) is a set of recommendation messages, and a is information in the set of recommendation messages; s is data of K historical users similar to the research data of the current user in the preset content, b is one piece of data in the data of the K historical users, and W isijSimilarity of the research data of the current user and preset content, RaiFor a predetermined degree of recommendation for keyword i, PabK matching degrees of data of K historical users and information in L (a).
7. The method according to claim 2, wherein the evaluation content of the current user comprises a net recommendation value;
before extracting keywords from the research data of the current user, the method further comprises:
classifying the investigation data of the current user according to the net recommended value;
and determining the range of the preset content according to the classification result.
8. An information recommendation apparatus, comprising:
the acquisition module is used for acquiring the research data of the current user;
the extraction module is used for extracting keywords from the research data of the current user;
the first determining module is used for determining the similarity between the research data of the current user and preset content according to the keyword and the preset content, wherein the preset content comprises evaluation content of a historical user, portrait information of the historical user and research characteristic information of the historical user; and
and the second determination module is used for determining the information recommended to the current user according to the similarity between the research data of the current user and the preset content.
9. An electronic device, comprising:
one or more processors; and
storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to carry out a method according to any one of claims 1 to 7.
10. A computer-readable medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911135367.3ACN111104590A (en) | 2019-11-19 | 2019-11-19 | Information recommendation method, device, medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911135367.3ACN111104590A (en) | 2019-11-19 | 2019-11-19 | Information recommendation method, device, medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111104590Atrue CN111104590A (en) | 2020-05-05 |
Family
ID=70420837
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911135367.3APendingCN111104590A (en) | 2019-11-19 | 2019-11-19 | Information recommendation method, device, medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111104590A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931049A (en)* | 2020-08-02 | 2020-11-13 | 吕维东 | Business processing method and blockchain financial platform based on big data and artificial intelligence |
| CN112581230A (en)* | 2020-12-24 | 2021-03-30 | 安徽航天信息科技有限公司 | Commodity recommendation method and device |
| CN112733042A (en)* | 2021-02-03 | 2021-04-30 | 北京百度网讯科技有限公司 | Recommendation information generation method, related device and computer program product |
| CN115917533A (en)* | 2020-08-07 | 2023-04-04 | 三菱电机株式会社 | Cooperation link creation system and cooperation link creation method |
| CN116823406A (en)* | 2023-08-24 | 2023-09-29 | 国品优选(北京)品牌管理有限公司 | Nutrient tablet recommendation method and system based on big data |
| CN118333655A (en)* | 2024-05-08 | 2024-07-12 | 广州若羽臣科技股份有限公司 | E-commerce product shopping guide method and device based on artificial intelligence |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970857A (en)* | 2014-05-07 | 2014-08-06 | 百度在线网络技术（北京）有限公司 | Recommended content determining system and method |
| US9390168B1 (en)* | 2010-09-28 | 2016-07-12 | Amazon Technologies, Inc. | Customer keyword-based item recommendations |
| CN108491529A (en)* | 2018-03-28 | 2018-09-04 | 百度在线网络技术（北京）有限公司 | Information recommendation method and device |
| CN109685560A (en)* | 2018-12-17 | 2019-04-26 | 泰康保险集团股份有限公司 | Big data processing method, device, medium and electronic equipment |
| CN109871483A (en)* | 2019-01-22 | 2019-06-11 | 珠海天燕科技有限公司 | A kind of determination method and device of recommendation information |
- 2019
- 2019-11-19CNCN201911135367.3Apatent/CN111104590A/enactivePending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9390168B1 (en)* | 2010-09-28 | 2016-07-12 | Amazon Technologies, Inc. | Customer keyword-based item recommendations |
| CN103970857A (en)* | 2014-05-07 | 2014-08-06 | 百度在线网络技术（北京）有限公司 | Recommended content determining system and method |
| CN108491529A (en)* | 2018-03-28 | 2018-09-04 | 百度在线网络技术（北京）有限公司 | Information recommendation method and device |
| CN109685560A (en)* | 2018-12-17 | 2019-04-26 | 泰康保险集团股份有限公司 | Big data processing method, device, medium and electronic equipment |
| CN109871483A (en)* | 2019-01-22 | 2019-06-11 | 珠海天燕科技有限公司 | A kind of determination method and device of recommendation information |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931049A (en)* | 2020-08-02 | 2020-11-13 | 吕维东 | Business processing method and blockchain financial platform based on big data and artificial intelligence |
| CN115917533A (en)* | 2020-08-07 | 2023-04-04 | 三菱电机株式会社 | Cooperation link creation system and cooperation link creation method |
| CN112581230A (en)* | 2020-12-24 | 2021-03-30 | 安徽航天信息科技有限公司 | Commodity recommendation method and device |
| CN112733042A (en)* | 2021-02-03 | 2021-04-30 | 北京百度网讯科技有限公司 | Recommendation information generation method, related device and computer program product |
| CN116823406A (en)* | 2023-08-24 | 2023-09-29 | 国品优选(北京)品牌管理有限公司 | Nutrient tablet recommendation method and system based on big data |
| CN116823406B (en)* | 2023-08-24 | 2023-11-14 | 国品优选(北京)品牌管理有限公司 | Nutrient tablet recommendation method and system based on big data |
| CN118333655A (en)* | 2024-05-08 | 2024-07-12 | 广州若羽臣科技股份有限公司 | E-commerce product shopping guide method and device based on artificial intelligence |
| CN118333655B (en)* | 2024-05-08 | 2025-06-20 | 广州若羽臣科技股份有限公司 | An e-commerce product shopping guide method and device based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145280B (en) | Information pushing method and device | |
| CN111104590A (en) | Information recommendation method, device, medium and electronic equipment | |
| CN109299994B (en) | Recommendation method, device, equipment and readable storage medium | |
| US20170249389A1 (en) | Sentiment rating system and method | |
| US20190102374A1 (en) | Predicting future trending topics | |
| US9639846B2 (en) | System and method for providing targeted content | |
| CN110135901A (en) | A kind of enterprise customer draws a portrait construction method, system, medium and electronic equipment | |
| US20150379571A1 (en) | Systems and methods for search retargeting using directed distributed query word representations | |
| US20160140627A1 (en) | Generating high quality leads for marketing campaigns | |
| CN107193974B (en) | Regional information determination method and device based on artificial intelligence | |
| WO2018040068A1 (en) | Knowledge graph-based semantic analysis system and method | |
| US20230214679A1 (en) | Extracting and classifying entities from digital content items | |
| CN112733042A (en) | Recommendation information generation method, related device and computer program product | |
| US20170061448A1 (en) | Brand Personality Perception Gap Identification and Gap Closing Recommendation Generation | |
| CN107977678A (en) | Method and apparatus for output information | |
| KR102458510B1 (en) | Real-time complementary marketing system | |
| EP4116884A2 (en) | Method and apparatus for training tag recommendation model, and method and apparatus for obtaining tag | |
| CN111429161A (en) | Feature extraction method, feature extraction device, storage medium, and electronic apparatus | |
| CN110674404A (en) | Link information generation method, device, system, storage medium and electronic equipment | |
| Shahzad et al. | Quantification of productivity of the brands on social media with respect to their responsiveness | |
| US10394804B1 (en) | Method and system for increasing internet traffic to a question and answer customer support system | |
| CN114996579B (en) | Information push method, device, electronic device and computer readable medium | |
| CN119739987A (en) | Label system construction, label providing method, device, equipment and storage medium | |
| CN108256078B (en) | Information acquisition method and device | |
| Sharma et al. | Recommending who to follow in the software engineering twitter space |
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:20200505 |