WO2017080400A1 - 一种信息推荐方法及装置 - Google Patents

一种信息推荐方法及装置 Download PDF

Info

Publication number
WO2017080400A1
WO2017080400A1 PCT/CN2016/104492 CN2016104492W WO2017080400A1 WO 2017080400 A1 WO2017080400 A1 WO 2017080400A1 CN 2016104492 W CN2016104492 W CN 2016104492W WO 2017080400 A1 WO2017080400 A1 WO 2017080400A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
server
recommended
information recommendation
type data
Prior art date
Application number
PCT/CN2016/104492
Other languages
English (en)
French (fr)
Inventor
王兴驰
高国庆
Original Assignee
阿里巴巴集团控股有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 阿里巴巴集团控股有限公司 filed Critical 阿里巴巴集团控股有限公司
Priority to AU2016353806A priority Critical patent/AU2016353806C1/en
Priority to SG11201804033RA priority patent/SG11201804033RA/en
Priority to JP2018524730A priority patent/JP6860563B2/ja
Priority to KR1020187016867A priority patent/KR102268934B1/ko
Priority to EP16863577.9A priority patent/EP3376401A4/en
Priority to MYPI2018000720A priority patent/MY194652A/en
Publication of WO2017080400A1 publication Critical patent/WO2017080400A1/zh
Priority to US15/976,560 priority patent/US11017451B2/en
Priority to PH12018501016A priority patent/PH12018501016A1/en
Priority to US16/722,202 priority patent/US11113743B2/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0631Item recommendations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/205Parsing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements
    • G06Q30/0251Targeted advertisements
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements
    • G06Q30/0251Targeted advertisements
    • G06Q30/0269Targeted advertisements based on user profile or attribute
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01Social networking
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/04Real-time or near real-time messaging, e.g. instant messaging [IM]

Definitions

  • the present application relates to the field of computer technologies, and in particular, to an information recommendation method and apparatus.
  • the information to be recommended is often targeted.
  • the information to be recommended may be information that a particular group of people (such as a white-collar, student, or female group) is likely to identify or be interested in.
  • information recommenders tend to recommend information to as many users as possible.
  • an advertisement recommendation on an e-commerce website suppose that it is desired to push an advertisement for a skirt to a female user.
  • the e-commerce website will send the advertisement to all users of the website. Since the users of the website are not all female users, when the advertisement is pushed, it is bound to consume a large amount of resources of the website server to implement advertisement push to other users outside the female user.
  • the embodiment of the present invention provides an information recommendation method, which is used to solve the problem of requiring more processing resources in order to achieve information recommendation to a specific group of people when performing information recommendation in the prior art.
  • the embodiment of the present application further provides an information recommendation device, which is used to solve the problem of requiring more processing resources in order to achieve information recommendation to a specific group of people when performing information recommendation in the prior art.
  • An information recommendation method includes: obtaining text type data sent by a client to a first server; and determining, in a preset information recommendation rule set, whether there is an information recommendation rule that matches the text type data;
  • the set of information is composed of information recommendation rules; the information recommendation rule is set according to the information to be recommended; and when the judgment result is yes, the recommendation information provided by the second server and matching the matched information rule is obtained.
  • An information recommendation device comprising: a text type data obtaining unit, configured to obtain text type data sent by a client to a first server; and an information recommendation rule determining unit, configured to determine whether a preset information recommendation rule set exists The information recommendation rule that matches the text type data; wherein the set is composed of information recommendation rules; the information recommendation rule is set according to information to be recommended; and the recommendation information obtaining unit is configured to: when the judgment result is yes, The recommendation information provided by the second server that matches the matching information rule is obtained.
  • the information recommendation method provided by the embodiment of the present application, from the “if the text type data sent by the client matches the information recommendation rule set according to the information to be recommended, the user is likely to belong to the information to be recommended or the specific one of interest. Starting from the characteristics of the crowd, when there is an information recommendation rule that matches the text type data sent by the client, the information to be recommended provided by the server is obtained, so that the information can be recommended to a specific group.
  • the selective information recommendation avoids the problem that the prior art needs to consume more processing resources in order to achieve the purpose of recommending information to a specific group of people.
  • FIG. 1 is a schematic flowchart of a specific implementation process of an information recommendation method according to an embodiment of the present application
  • FIG. 2 is a schematic structural diagram of a Trie tree provided by an embodiment of the present application.
  • FIG. 3 is a schematic structural diagram of a Trie tree according to an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of an information recommendation apparatus according to an embodiment of the present application.
  • the embodiment of the present invention provides a method for recommending information, which is used to solve the problem that the prior art requires more processing resources when performing information recommendation to a specific group of people.
  • the execution subject of the information recommendation method provided by the embodiment of the present application may be, but not limited to, a smartphone, a tablet, a personal computer (PC), a server, and the like.
  • the executor of the present invention does not constitute a limitation on the present application.
  • the embodiment of the present application is described by taking an execution subject as a client (hereinafter referred to as an information recommendation client) as an example. It can be understood that the execution of the method is only an exemplary description of the smartphone, and should not be construed as limiting the method.
  • FIG. 1 The schematic diagram of the specific implementation process of the method is shown in FIG. 1 and mainly includes the following steps:
  • Step 11 The information recommendation client obtains text type data sent by the client (hereinafter referred to as a data providing client) to the first server;
  • the information recommendation client and the data providing client described in step 11 may be any client installed on a device such as a personal computer, a tablet computer, a smart phone, or a smart TV.
  • the data providing client may be the information recommendation client, or the data providing client may be another client different from the information recommendation client.
  • the first server generally refers to a background server of a data providing client.
  • the first server may also be another server capable of data transmission with the data providing client.
  • the text type data may be, for example, a microblog, a log, a chat content, and the like sent by the data providing client.
  • the data providing client uses the chat application (Application, APP) installed on the mobile phone as an example.
  • the chat application Application, APP
  • the text content of the chat can be obtained (the text content is text)
  • the text content of the microblog can be obtained.
  • obtaining text-type data sent by the data providing client to the first server may include, but is not limited to, the following two methods:
  • Method 1 The information recommendation client acquires data from the first server to provide text type data sent by the client to the first server.
  • the first server may perform the chat content.
  • the information recommendation client can directly send a chat content acquisition request to the first server (the request may include the chat content identifier that needs to be acquired, such as the sending time of the chat content and the user account.
  • the identifier is formed together, so that the first server can find the chat content required by the user according to the identifier, and send the text type data of the chat content to the information recommendation client.
  • Manner 2 The information recommendation client receives the text-type data sent by the client.
  • the data providing client can copy the text type data and copy the obtained text type data by calling the specified interface. Send the information to the recommended client installed on the user's phone.
  • the specified interface may be an access interface of the information recommendation client.
  • the data providing client can have the calling permission of the specified interface.
  • the text type data (such as the user chat content) can be obtained locally in the information recommendation client, and does not need to go through the first server, so that it can be relatively avoided from the server through the Internet.
  • the risk of information disclosure that may be faced with textual data can be obtained locally in the information recommendation client, and does not need to go through the first server, so that it can be relatively avoided from the server through the Internet.
  • the text type data sent by the data providing client to the first server can be obtained by one of the above two methods in the following two cases:
  • Case 1 When the user sends the text type data through the terminal, the text type data sent by the user is obtained.
  • the terminal used by the user is a mobile phone
  • the user uses the chat APP installed on the mobile phone as an example.
  • the user inputs a piece of chat content by using the APP, and clicks the “send” button, when the user clicks the “send” button, the above
  • the text type data sent by the user when the click button is clicked is obtained.
  • the terminal used by the user is a mobile phone
  • the user uses the microblog APP installed on the mobile phone as an example.
  • the user desires to use the APP to post a microblog that is "Happy everyone, happy birthday, seven days of long vacation fun”.
  • the user inputs the text using the APP and does not click the "send" button
  • the text currently input by the user through the user terminal can also be obtained at this time.
  • the paragraph text is the text type data to be sent as described.
  • Step 12 The information recommendation client determines whether there is an information recommendation rule that matches the text type data in the preset information recommendation rule set; when the determination result is yes, step 13 is performed; when the judgment result is no, The process can be ended.
  • the information recommendation rule set is composed of information recommendation rules.
  • the information recommendation rule is a rule for determining whether it is necessary to obtain the information to be recommended according to the information to be recommended.
  • the information recommendation rule set may be provided by the second server, or may be preset in the information recommendation client local.
  • the second server generally refers to an information recommendation client
  • the background server of the end of course, the second server may also be another server capable of data transmission with the information recommendation client.
  • the information recommendation client may send an information recommendation rule download request to the second server, so that the second server sends the information recommendation rule set to the information recommendation client in response to the download request.
  • a topic may be set for the information to be recommended, and a keyword corresponding to the topic may be determined according to the content of the information to be recommended.
  • the specific implementation manner of the information recommendation rule according to the information to be recommended may include:
  • the information recommendation rule is set to be composed of the theme set by the information to be recommended + the keyword corresponding to the theme; or, the information recommendation rule may be set to be composed only of keywords.
  • the information recommendation rule can generally adopt the following two formats:
  • A is the subject of the information to be recommended, and A1, A2, and A3 are keywords corresponding to A.
  • B1, B2, and B3 are keywords.
  • the subject of the information to be recommended may be set to "basketball". If it is found through statistics, when the user's chat content includes the words “Kobe”, “Jordan” and “NBA”, the user's chat content is generally related to basketball, and thus the subject of the information recommendation rule related to basketball can be selected. Set to: “Basketball”, the keywords are set to: “Kobe”, “Jordan”, “NBA”, then the information recommendation rules can be: basketball, Kobe, Jordan, NBA.
  • the text type data matches the information recommendation rule, and the text type data has the same words as the keywords in the information recommendation rule.
  • the text type data and the information recommendation rule may be determined. Match.
  • the theme set for the information to be recommended is: Basketball.
  • the text-type data sent by the data providing client to the first server is: “Kobe and Jordan are two of my favorite two athletes", because the text data is obtained.
  • the above-mentioned keywords “Kobe”, “Jordan”, “NBA”: “Kobe”, “Jordan”, “NBA”
  • the set information recommendation rule that is, In the set of information recommendation rules, There is an information recommendation rule that matches the obtained text type data.
  • the embodiment of the present application can construct a dictionary tree (Trie tree, Trie tree) by using keywords in the information recommendation rule, and achieve text type data obtained by using keyword filtering in the information recommendation rule to determine the obtained data. Whether the text type data has a word matching the keyword, and thereby determining whether the text type data conforms to the information recommendation rule.
  • Trie tree Trie tree
  • the Trie tree can be constructed using keywords in the information recommendation rules.
  • each Chinese character (or each letter) constituting a keyword in the information recommendation rule may be respectively allocated to each node of the Trie tree, and the first Chinese character (or letter) constituting the keyword is located.
  • the node is set to the start node of the Trie tree, and the node where the last Chinese character (or letter) constituting the keyword is located is set as the termination node of the Trie tree.
  • the two keywords may be constructed into one Trie tree. For example, assuming the keywords are: "his", “he", "her”, a Trie tree as shown in FIG. 2 can be constructed.
  • the information recommendation rule for setting the theme is: "Theme: Comic; Keywords: One Piece, Death and Death Note”.
  • the Trie tree constructed according to the information recommendation rule is as shown in FIG. 3.
  • the dark node represents the terminating node.
  • the Trie tree constructed by the keyword in the information recommendation rule is used to determine whether the text recommendation type exists in the preset information recommendation rule set.
  • the information recommendation rule that the data matches may specifically include:
  • the Chinese characters that are the same as the Chinese characters allocated on the starting node of the Trie tree are retrieved; when the Chinese characters that are assigned the same Chinese characters as the starting node are retrieved (the matching Chinese characters of the starting node are hereinafter referred to as the matching characters) "), continue to obtain the Chinese characters allocated on the child nodes corresponding to the starting node, and further retrieve whether the Chinese characters immediately after the "matching Chinese characters" of the starting node in the text type data and the "matching Chinese characters” are The Chinese characters assigned to the child nodes are the same (it is to be noted that when the Chinese characters that are the same as the Chinese characters assigned on the Trie tree node are retrieved in the text type data, the node is called a "matching node", which is called The Chinese character is "matching Chinese characters”; if they are the same, the Chinese characters allocated on the child nodes corresponding to the "matching nodes” are continuously obtained, and according to the obtained Chinese characters, whether the text type data has the same "match”
  • the Chinese characters allocated on each node in the Trie tree can retrieve the matched Chinese characters in the obtained text type data according to the above manner, it can be said that the obtained text type data conforms to constitute the Trie tree.
  • the information recommendation rule to which the keyword belongs is not limited.
  • the recommended information recommendation rules are: “Theme: Comics; Keywords: One Piece, Chess Soul and Death Note”, and construct three Trie trees according to the above keywords;
  • step 11 the textual data obtained is: "I like Xiao Qijian's "Hikaru” and “Death Note”, as well as Oda Eiichiro's "One Piece.”
  • the obtained text type data is searched to determine whether the chat text meets the information recommendation rule, and specifically includes:
  • the text type data is retrieved using the Trie tree constructed according to the keyword "One Piece", then the same Chinese character can be retrieved in the text type data for the "sea” word assigned on the starting node of the Trie tree; Further, for the "thief" word assigned to the child node corresponding to the starting node, the Chinese character “thief” arranged after the "sea” word and adjacent to the "sea” word may be retrieved in the text type data. And so on, the same Chinese character that is assigned to the Chinese character "king" on the Tere tree termination node can be retrieved from the text type data, thereby ending the retrieval, and determining the obtained keyword data and the keyword in the information recommendation rule. "One Piece" matches.
  • the chat text is searched by using the Trie tree constructed by the keyword “death note” and the keyword “chuck soul” in sequence. If the corresponding search result is that the chat text matches the keywords "death note” and “chuck soul” in the above information recommendation rule, it can be determined that the chat text conforms to the information recommendation rule.
  • different information recommendation rules may be set according to the information to be recommended of the same topic.
  • the theme of the information to be recommended is “basketball” as an example.
  • the user's chat content includes the words “Kobe”, “Jordan” and “NBA”
  • the user's chat content includes “slam dunk", “cap” and " In the three words of "rebound”
  • the user's chat content is also related to basketball. Then you can set the following two information recommendation rules for the information to be recommended related to "basketball”:
  • the same set of keywords may also correspond to different topics.
  • step 13 the information recommendation client obtains the information to be recommended provided by the second server.
  • the second server mentioned here is a server that provides the information to be recommended. It may be the first server or a second server different from the first server.
  • the information to be recommended may be, for example, advertisements, news, pictures, movies, and the like related to the theme of the information recommendation rule.
  • the information to be recommended may be obtained by, but not limited to, the following two methods:
  • the information recommendation client triggers the second server to push the information to be recommended to the information recommendation client; and obtains the information to be recommended pushed by the second server.
  • the information recommendation client determines that the text type data sent to the first server conforms to the information recommendation rule whose theme is “basketball”, the information recommendation client sends a “basketball” topic information acquisition request to the second server. And the second server receives, in response to the request, recommending, to the information recommendation client, the information to be recommended of the “basketball” theme.
  • the information recommendation client installed on the mobile phone as an example, when the step 12 is executed, it is determined that the text type data sent by the data providing client conforms to the information recommendation rule set with the theme “basketball”, and the information recommendation client will The information acquisition request of the "basketball” theme is sent to the second server, and the second server receives the information to be recommended of the "basketball” theme to the mobile phone in response to the request.
  • the information obtaining request may include the feature of the information to be recommended, for example, the following may be included. At least one of: a subject of the information to be recommended, a keyword of the information to be recommended, a number of the information to be recommended, and an identifier of the information recommendation rule corresponding to the information to be recommended, and the like. That is, after receiving the information acquisition request, the second server may search for the information to be recommended according to the identifier of the information to be recommended included in the request.
  • Mode 2 Download the information to be recommended from the second server.
  • the information recommendation client determines that the text type data sent to the first server conforms to the information recommendation rule whose theme is “basketball”, and the information recommendation client downloads the “basketball” theme from the second server. Information to be recommended.
  • the keyword and the information recommendation rule there may be different relevance between the keyword and the information recommendation rule, that is, the information to be recommended corresponding to the keyword and the information recommendation rule.
  • the keyword “Slam Dunk” information recommendation rule 1 (the theme is “manga”) and information Referring to recommendation rule 2 (the subject is "basketball”) as an example, the relevance of the keyword to the information recommendation rule 1 is often greater than the association with the information recommendation rule 2, and therefore, at least the presence of the information recommendation rule set is determined.
  • the information recommendation client sends the information acquisition request to the second server, which may include: when it is determined that there are at least two information recommendation rules in the set that match the text type data, The weights respectively set by the keywords set in the at least two information recommendation rules are selected from the at least two information recommendation rules; the topics set in the selected information recommendation rules are carried in the information In the acquisition request, the second server is sent.
  • the subsequent second server may provide the information recommendation client with the information to be recommended with the topic according to the topic in the request.
  • the subject of the information to be recommended A is: basketball, and the recommended information recommendation rules are: information recommendation rule 1: "theme: basketball; keyword: slam dunk";
  • the theme of the information to be recommended B is: comics "Slam Dunk”, the recommended information recommendation rules are: Information recommendation rule 2: “Theme: comics "slam dunk”; Keywords: slam dunk”;
  • step 11 the text data sent by the information providing client is: "Yesterday's slam dunk contest is very exciting";
  • the weight of the judgment result of setting rule 1 is 2; the weight of the judgment result of setting rule 2 is 1;
  • the embodiment of the present application further provides a restriction policy for the information recommendation client to obtain information to be recommended from the second server.
  • the embodiment of the present application may limit the information recommendation client to obtain the information to be recommended from the second server by using the following two policies, including:
  • Strategy a When the number of words in the text type data (generally referred to as a text type data) described in step 12 that is the same as the keyword in the information recommendation rule is not less than the preset number, the information recommendation client can The information to be recommended corresponding to the information recommendation rule is obtained from the second server and displayed to the user.
  • a text type data generally referred to as a text type data
  • the information recommendation rule mentioned herein may be any information recommendation rule that matches the text type data, or may be recommended from at least two pieces of information matching the text type data by adopting the scheme introduced in the foregoing.
  • a rule of information recommendation determined in the rules may be any information recommendation rule that matches the text type data, or may be recommended from at least two pieces of information matching the text type data by adopting the scheme introduced in the foregoing.
  • the subject of the information to be recommended is: basketball
  • the recommended information recommendation rules are: information recommendation rule 1: "theme: basketball; keyword: slam dunk";
  • the information recommendation client may obtain the to-be-recommended information of the topic from the second server. And then show it to the user.
  • the policy recommendation b is that the information recommendation client can obtain the to-be-recommended information corresponding to the information recommendation rule from the second server and display the information to the user after the number of the text-type data matching the same information recommendation rule is not less than the preset number.
  • the "same information recommendation rule” mentioned herein may be any information recommendation rule that matches the text type data described in step 12, or may be adopted from the text type described above by adopting the scheme introduced in the foregoing.
  • the "text-type data matching the same information recommendation rule” as used herein generally includes the text-type data described in step 12, and may also include other text-type data sent by the data providing client to the first server.
  • the term "the number of text-type data matching the same information recommendation rule” as used herein generally means that the data providing client sends the same to the first server within a preset length of time (for example, 30 minutes). The number of text-type data matched by a message recommendation rule.
  • the subject of the information to be recommended is: basketball
  • the recommended information recommendation rules are: information recommendation rule 1: "theme: basketball; keyword: slam dunk";
  • the preset time length is 30 minutes; the preset number is 2.
  • the execution bodies of the steps of the method provided in Embodiment 1 may all be the same device, or the method may also be performed by different devices.
  • the execution body of step 11 and step 12 may be device 1, and the execution body of step 13 may be device 2; for example, the execution body of step 11 may be device 1, and the execution body of step 12 and step 13 may be device 2. ;and many more.
  • Embodiment 1 of the present application “if the text type data sent by the client matches the information recommendation rule set according to the information to be recommended, the user is likely to belong to the information to be recommended or is interested in the information.
  • the information to be recommended provided by the server is obtained, so that the information recommendation to a specific group can be achieved.
  • the selective information recommendation is realized, and the problem that the prior art needs to consume more processing resources in order to achieve information recommendation to a specific group is avoided.
  • the embodiment of the present application provides an information recommendation device, which is used to solve the problem that the prior art requires more processing resources when recommending information to a specific group of people.
  • a schematic diagram of a specific structure of the apparatus is shown in FIG. 4, and includes a text type data obtaining unit 21, an information recommendation rule judging unit 22, and a recommendation information obtaining unit 23.
  • the text type data obtaining unit 21 is configured to obtain text type data sent by the client to the first server;
  • the information recommendation rule determining unit 22 is configured to determine whether there is an information recommendation rule that matches the text type data in the preset information recommendation rule set; wherein the set is composed of the information recommendation rule; the information recommendation rule is Set according to the information to be recommended;
  • the recommendation information obtaining unit 23 is configured to obtain, when the determination result is yes, recommendation information that is provided by the second server and that matches the matching information rule.
  • the information to be recommended may be provided by the server.
  • the recommendation information obtaining unit 23 is configured to trigger the second server to push the information to be recommended, and obtain the second.
  • the information to be recommended pushed by the server; or downloading the information to be recommended from the second server.
  • the recommendation information obtaining unit 23 is configured to directly send an information acquisition request to the second server, and receive the information to be recommended sent by the second server in response to the information acquisition request; or trigger information push
  • the application sends an information acquisition request to the second server, and receives the information to be recommended sent by the second server in response to the information acquisition request sent by the information push application.
  • the information acquisition request includes the feature of the information to be recommended.
  • the feature of the information to be recommended includes at least one of: a subject of the information to be recommended; a keyword of the information to be recommended; a number of the information to be recommended; The identifier of the information recommendation rule corresponding to the information to be recommended.
  • the recommendation information obtaining unit 23 is used in the set.
  • at least one keyword is set in each information recommendation rule and at least one keyword corresponding to the one topic
  • the second server is sent.
  • the text type data may be actively acquired or passively received.
  • the text type data obtaining unit 21 may be configured to: acquire, from the first server, text type data sent by the client to the first server; or receive the Text-type data, wherein the text-type data sent by the client is obtained by copying text-type data sent by the client to the first server.
  • the information recommendation The rule judging unit is further configured to: obtain and save the set provided by the second server before determining whether there is an information recommendation rule that matches the text type data in the set.
  • the information recommendation apparatus provided in Embodiment 2 of the present application, “if the text type data sent by the client matches the information recommendation rule set according to the information to be recommended, the user is likely to belong to the information to be recommended or is interested in the information.
  • the information to be recommended provided by the server is obtained, so that the information recommendation to a specific group can be achieved.
  • the selective information recommendation is realized, and the problem that the prior art needs to consume more processing resources in order to achieve information recommendation to a specific group is avoided.
  • embodiments of the present invention can 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 a combination of software and hardware. Moreover, the invention may be implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer usable program code embodied therein. The form of a computer program product.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, tape/disk storage or other magnetic storage devices or any other non-transportable media that can be used to store information that can be accessed by computing devices.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Databases & Information Systems (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Tourism & Hospitality (AREA)
  • Primary Health Care (AREA)
  • Computing Systems (AREA)
  • Human Resources & Organizations (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Information Transfer Between Computers (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种信息推荐方法和装置,该方法包括:获得客户端向第一服务器发送的文本型数据(11);判断预设的信息推荐规则集合中,是否存在与所述文本型数据相匹配的信息推荐规则(12);其中,所述集合由信息推荐规则构成;信息推荐规则,是根据待推荐的信息设置的;在判断结果为是时,获得所述第二服务器提供的、与所述相匹配的信息规则匹配的推荐信息(13)。该方法用以解决现有技术向特定人群进行信息推荐时,需要耗费较多的处理资源的问题。

Description

一种信息推荐方法及装置
本申请要求2015年11月13日递交的申请号为201510780621.0、发明名称为“一种信息推荐方法及装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及计算机技术领域,尤其涉及一种信息推荐方法及装置。
背景技术
随着互联网技术的不断发展,人们在互联网上可以进行的活动也越来越丰富,通过互联网进行信息推荐也变得越来越常见。
一般地,信息推荐方在进行信息推荐时,待推荐的信息往往具有一定的针对性。比如,待推荐的信息可能是特定人群(比如白领、学生或女性群体等)容易认同或者感兴趣的信息。
目前,为了使尽可能多的特定人群成员能够获得待推荐的信息,信息推荐方往往会向尽可能多的用户进行信息推荐。
例如,以电商网站进行广告推荐为例,假设期望向女性用户推送一款裙子的广告,基于现有技术,为了达到该目的,电商网站会向该网站的所有用户均发送该广告。由于该网站的用户并不全为女性用户,因此在进行广告推送时,势必会耗费网站服务器大量的资源来实现向女性用户外的其他用户进行广告推送。
可见,采用上述现有技术进行信息推荐时,为了达到向特定人群进行信息推荐的目的,需要耗费较多的处理资源。
发明内容
本申请实施例提供一种信息推荐方法,用以解决现有技术进行信息推荐时,为了达到向特定人群进行信息推荐的目的,需要耗费较多的处理资源的问题。
本申请实施例还提供一种信息推荐装置,用以解决现有技术进行信息推荐时,为了达到向特定人群进行信息推荐的目的,需要耗费较多的处理资源的问题。
本申请实施例采用下述技术方案:
一种信息推荐方法,包括:获得客户端向第一服务器发送的文本型数据;判断预设的信息推荐规则集合中,是否存在与所述文本型数据相匹配的信息推荐规则;其中,所 述集合由信息推荐规则构成;信息推荐规则,是根据待推荐的信息设置的;在判断结果为是时,获得第二服务器提供的、与所述相匹配的信息规则匹配的推荐信息。
一种信息推荐装置,包括:文本型数据获得单元,用于获得客户端向第一服务器发送的文本型数据;信息推荐规则判断单元,用于判断预设的信息推荐规则集合中,是否存在与所述文本型数据相匹配的信息推荐规则;其中,所述集合由信息推荐规则构成;信息推荐规则,是根据待推荐的信息设置的;推荐信息获得单元,用于在判断结果为是时,获得第二服务器提供的、与所述相匹配的信息规则匹配的推荐信息。
本申请实施例采用的上述至少一个技术方案能够达到以下有益效果:
本申请实施例提供的信息推荐方法,从“若客户端发送的文本型数据与根据待推荐的信息设置的信息推荐规则匹配,则说明用户很有可能属于对待推荐的信息认同或者感兴趣的特定人群”这一特点出发,当存在与客户端发送的文本型数据相匹配的信息推荐规则时,才获得服务器提供的待推荐的信息,从而在能够达到向特定人群进行信息推荐的前提下,实现了有选择性的信息推荐,避免了现有技术为了达到向特定人群进行信息推荐的目的,需要耗费较多的处理资源的问题。
附图说明
此处所说明的附图用来提供对本申请的进一步理解,构成本申请的一部分,本申请的示意性实施例及其说明用于解释本申请,并不构成对本申请的不当限定。在附图中:
图1为本申请实施例提供的一种信息推荐方法的具体实现流程示意图;
图2为本申请实施例提供的Trie树的具体结构示意图;
图3为本申请实施例提供的Trie树的具体结构示意图;
图4为本申请实施例提供的一种信息推荐装置的具体结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚,下面将结合本申请具体实施例及相应的附图对本申请技术方案进行清楚、完整地描述。显然,所描述的实施例仅是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
以下结合附图,详细说明本申请各实施例提供的技术方案。
实施例1
本申请实施例提供一种信息推荐方法,用以解决现有技术向特定人群进行信息推荐时,需要耗费较多的处理资源的问题。
本申请实施例提供的信息推荐方法的执行主体可以但不限于为智能手机、平板电脑、个人电脑(Personal Computer,PC)以及服务器,等等。所述的执行主体并不构成对本申请的限定,为了便于描述,本申请实施例均以执行主体是客户端(后文称信息推荐客户端)为例进行说明。可以理解,该方法的执行主体为智能手机只是一种示例性的说明,并不应理解为对该方法的限定。
该方法的具体实现流程示意图如图1所示,主要包括下述步骤:
步骤11,信息推荐客户端获得客户端(后称数据提供客户端)向第一服务器发送的文本型数据;
其中,步骤11中所述的信息推荐客户端和数据提供客户端,均可以是个人电脑、平板电脑、智能手机或智能电视等等设备上安装的任意客户端。
数据提供客户端可以是所述的信息推荐客户端,或者,数据提供客户端也可以是不同于所述信息推荐客户端的其他客户端。
所述的第一服务器,一般指数据提供客户端的后台服务器。当然,该第一服务器也可以是能够与数据提供客户端进行数据传输的其他服务器。
所述的文本型数据,比如可以是数据提供客户端发送的微博、日志以及聊天内容等。例如,假设以数据提供客户端为手机上安装的聊天应用(Application,APP)为例,当用户通过该聊天APP输入聊天的文字内容时,则可以获得该聊天的文字内容(该文字内容为文本型数据的一种);还比如,当用户通过微博APP发送一条微博时,则可以获得该微博的文字内容(该文字内容为文本型数据的一种)。
在一种实施方式中,获得数据提供客户端向第一服务器发送的文本型数据,可以包括但不限于以下两种方式:
方式1:信息推荐客户端从第一服务器获取数据提供客户端向第一服务器发送的文本型数据。
例如,假设以用户使用手机上安装的聊天APP进行聊天为例,当用户通过该APP输入聊天内容,并通过第一服务器向信息接收方用户的手机发送时,第一服务器可以对该聊天内容进行保存,则信息推荐客户端可以直接向第一服务器发送聊天内容获取请求(该请求中可以包括需要获取的聊天内容标识,如由聊天内容的发送时间以及用户账号 共同构成的该标识,等),以使得第一服务器可以根据该标识查找到用户所需的聊天内容,并将所述聊天内容的文本型数据发送至信息推荐客户端。
方式2:信息推荐客户端接收数据提供客户端发送来的所述文本型数据。
例如,当用户通过手机上安装的数据提供客户端向第一服务器发送文本型数据时,数据提供客户端可以将所述文本型数据进行复制,并通过调用指定接口,将复制得到的文本型数据发送至用户手机上安装的信息推荐客户端。其中,所述的指定接口,比如可以是信息推荐客户端的访问接口。当然,数据提供客户端,可以具备该指定接口的调用权限。
需要说明的是,采用方式2提供的方法,文本型数据(比如用户聊天内容)可以在信息推荐客户端本地获得,不需要经过第一服务器,从而相对而言,可以避免通过互联网从服务器获取该文本型数据而可能面临的信息泄露风险。
还需要说明的是,可以在以下两种情况下,通过上述两种方式之一获得数据提供客户端向第一服务器发送的文本型数据:
情况1:当用户通过终端发送文本型数据后,获得用户发送的文本型数据。
例如,假设用户使用的终端为手机,用户使用手机上安装的聊天APP为例,假设用户使用该APP输入一段聊天内容,并点击“发送”按键,则在用户点击“发送”按键时,通过上述两种方式获得用户当次点击发送按键所触发发送的文本型数据。
情况2:当用户通过终端输入文本型数据后,在发送该文本型数据前,获得该文本型数据(后文称待发送的文本型数据)。
例如,假设用户使用的终端为手机,用户使用手机上安装的微博APP为例,假设用户期望使用该APP发布一条内容为“祝大家国庆节快乐,七天小长假玩的开心”的微博,则当用户使用该APP输入了这段文字,且并未点击“发送”按钮时,此时也可以获得用户通过用户终端当前输入的这段文字。该段文字即为所述的待发送的文本型数据。
步骤12,信息推荐客户端判断预设的信息推荐规则集合中,是否存在与所述文本型数据相匹配的信息推荐规则;在判断结果为是时,执行步骤13;在判断结果为否时,可以结束流程。
其中,所述信息推荐规则集合由信息推荐规则构成。信息推荐规则,是根据待推荐的信息设置的、用于判断是否需要获得该待推荐的信息的规则。
需要说明的是,所述的信息推荐规则集合可以是由第二服务器提供的,或者可以是预先设置在信息推荐客户端本地的。其中,所述的第二服务器,一般是指信息推荐客户 端的后台服务器,当然该第二服务器也可以是能够与信息推荐客户端进行数据传输的其他服务器。信息推荐客户端可以向第二服务器发送信息推荐规则下载请求,以使得第二服务器响应于所述下载请求,向信息推荐客户端发送信息推荐规则集合。
一般地,可以为待推荐的信息设置主题,并根据待推荐的信息的内容,确定与所述主题对应的关键词。相应的,在一种实施方式中,根据待推荐的信息设置信息推荐规则的具体实现方式,可以包括:
将信息推荐规则设置为由待推荐的信息设置的主题+所述主题对应的关键词组成;或者,也可以将信息推荐规则设置为仅由关键词组成。
本申请实施例中,信息推荐规则一般可以采用以下两种格式:
格式1:A,A1、A2、A3
其中,A为待推荐的信息的主题,A1、A2、A3为A对应的关键词。
格式2:B1、B2、B3
其中,B1、B2、B3为关键词。
例如,假设待推荐的信息是与篮球运动相关的信息,则可以将该待推荐的信息的主题设置为“篮球”。若经统计发现,当用户的聊天内容包含“科比”、“乔丹”以及“NBA”这三个词时,用户的聊天内容一般与篮球有关,进而可以将与篮球运动相关的信息推荐规则的主题设置为:“篮球”,关键词设置为:“科比”、“乔丹”、“NBA”,则该信息推荐规则可以为:篮球,科比、乔丹、NBA。
本申请实施例中,文本型数据与信息推荐规则相匹配,是指文本型数据中具有与信息推荐规则中关键词完全相同的词语。
比如,以某个信息推荐规则为例,当通过执行步骤11获得的文本型数据中,存在与该信息推荐规则中的各关键词相同的词语时,可以判断该文本型数据与该信息推荐规则相匹配。
例如,假设信息推荐规则集合中,存在满足下述条件的一条信息推荐规则:
1、为待推荐的信息设置的主题为:篮球。
2、针对主题“篮球”设置的关键词为:“科比”、“乔丹”、“NBA”。
则当通过执行步骤11,获得数据提供客户端向第一服务器发送的文本型数据为:“科比与乔丹是NBA中,我最喜爱的两名运动员”时,由于在获得的该文本型数据中,存在与上述关键词“科比”、“乔丹”、“NBA”相同的词语:“科比”、“乔丹”、“NBA”,则可以确定获得的文本型数据符合设置的信息推荐规则,即所述信息推荐规则集合中, 存在与获得的文本型数据相匹配的信息推荐规则。
当通过执行步骤12,获得客户端发送的文本型数据为:“我最喜欢的篮球运动员是湖人队的科比”时,此时在该文本型数据中,仅有“科比”一词与主题“篮球”的信息推荐规则中的关键词相匹配,则可以确定所述的文本型数据不符合该信息推荐规则。
需要说明的是,本申请实施例可以通过使用信息推荐规则中的关键词构建字典树(Trie tree,Trie树),达到使用信息推荐规则中的关键词过滤获得的文本型数据,以确定获得的文本型数据中是否具有与所述关键词相匹配的词语,并以此判断文本型数据是否符合信息推荐规则。
在一种实施方式中,可以使用信息推荐规则中的关键词构建Trie树。具体的,可以将信息推荐规则中构成关键词的各汉字(或各字母),分别分配到Trie树的每个节点上,并将构成所述关键词的第一个汉字(或者字母)所在的节点设置为Trie树的起始节点,将构成所述关键词的最后一个汉字(或者字母)所在的节点设置为Trie树的终止节点。需要说明的是,当信息推荐规则中至少两个关键词的首字母(或者至少两个关键词的首字)相同时,则可以将这两个关键词构建到一个Trie树中。例如,假设关键词为:“his”、“he”“her”,则可以构建如图2所示的Trie树。
例如,假设待推荐信息的主题与漫画有关,且设置该主题的信息推荐规则为:“主题:漫画;关键词:海贼王、死神以及死亡笔记”。则根据该信息推荐规则构建的Trie树如图3所示。图3中,深色节点表示终止节点。
需要说明的是,假设信息推荐规则中关键词是由汉字组成为例,则使用由信息推荐规则中关键词构建的Trie树,判断预设的信息推荐规则集合中,是否存在与所述文本型数据相匹配的信息推荐规则,具体可以包括:
在获得的文本型数据中,检索与Trie树起始节点上被分配的汉字相同的汉字;当检索到与起始节点上被分配的汉字相同的汉字(后文称起始节点的“匹配汉字”)时,继续获得该起始节点对应的子节点上被分配的汉字,并进一步检索所述文本型数据中起始节点的“匹配汉字”之后且紧邻该“匹配汉字”的汉字是否与某个所述子节点上被分配的汉字相同(需要说明的是,当在文本型数据中检索到与Trie树节点上被分配的汉字相同的汉字时,称该节点为“匹配节点”,称该汉字为“匹配汉字”);若相同,则继续获得“匹配节点”对应的子节点上被分配的汉字,并根据获得的该汉字检索所述文本型数据中是否存在与该汉字相同的“匹配汉字”;然后依此类推,继续进行检索,直至从文本型数据中检索到与Trie树的终止节点被分配的汉字相同的汉字时,或者判断出文本 型数据中检索不到与非终止节点的匹配节点对应的子节点被分配的汉字相同的汉字时,终止检索。
一般地,当按照上述方式,确定Trie树中每个节点上被分配的汉字都能在获得的文本型数据中检索到相匹配的汉字时,可说明获得的文本型数据符合构成所述Trie树的关键词所属的信息推荐规则。
例如,假设下述条件成立:
1、待推荐信息的主题为“漫画”;
2、设置的信息推荐规则为:“主题:漫画;关键词:海贼王、棋魂以及死亡笔记”,并根据上述关键词分别构建三个Trie树;
3、通过执行步骤11,获得的文本型数据为:“我喜欢小畑健的《棋魂》和《死亡笔记》,还有尾田荣一郎的《海贼王》。”
则,通过构建的Trie树,对获得的文本型数据进行检索,判断聊天文本是否符合信息推荐规则,具体可以包括:
使用根据关键词“海贼王”构建的Trie树对该文本型数据进行检索,那么,针对该Trie树的起始节点上被分配的“海”字,在文本型数据中可以检索到相同的汉字;进一步地,针对该起始节点对应的子节点被分配的“贼”字,可以在该文本型数据中,检索到排列在“海”字后且与“海”字紧邻的汉字“贼”。依此类推,可以从该文本型数据中检索到与Trie树终止节点上被分配的汉字“王”相同的汉字,从而结束检索,并确定获得的该文本型数据与信息推荐规则中的关键词“海贼王”相匹配。
采用上述方法,依次使用由关键词“死亡笔记”以及关键词“棋魂”构建的Trie树,对该聊天文本进行检索。若相应的检索结果为聊天文本与上述信息推荐规则中的关键词“死亡笔记”以及“棋魂”均匹配,则可以判断该聊天文本符合该信息推荐规则。
需要说明的是,根据相同主题的待推荐信息,可以设置不同的信息推荐规则。比如,以待推荐信息的主题为“篮球”为例。若据统计,用户的聊天内容包含“科比”、“乔丹”以及“NBA”这三个词时,用户的聊天内容与篮球有关;而用户的聊天内容包含“灌篮”、“盖帽”以及“篮板”这三个词时,用户的聊天内容也与篮球有关。则可以设置以下两种针对与“篮球”相关的待推荐的信息的信息推荐规则:
规则1,主题:篮球;关键词:“科比”、“乔丹”、“NBA”。
规则2,主题:篮球;关键词:“灌篮”、“盖帽”、“篮板”。
还需要说明的是,同一组关键词也可能对应不同的主题。比如,关键词:“灌篮高 手”、“黑子的篮球”,所述关键词对应的主题可以为:“篮球”,也可以为:“漫画”。
步骤13,信息推荐客户端获得第二服务器提供的待推荐的信息。
这里所说的第二服务器,是提供所述待推荐的信息的服务器。其可以就是第一服务器,也可以是不同于第一服务器的第二服务器。
需要说明的是,所述待推荐的信息,比如可以是与信息推荐规则的主题相关的广告、新闻、图片以及电影,等信息。
在一种实施方式中,可以但不限于通过以下两种方式获得待推荐的信息:
方式1:信息推荐客户端触发第二服务器向信息推荐客户端推送待推荐的信息;获得第二服务器推送的待推荐的信息。
比如,若信息推荐客户端判断出向第一服务器发送的所述文本型数据符合主题为“篮球”的信息推荐规则,则该信息推荐客户端会向第二服务器发送“篮球”主题的信息获取请求,第二服务器接收响应于该请求,向该信息推荐客户端发送“篮球”主题的待推荐的信息。
还比如,以手机上安装的信息推荐客户端为例,当通过执行步骤12后,判断数据提供客户端发送的文本型数据符合设置有主题“篮球”的信息推荐规则时,信息推荐客户端会向第二服务器发送“篮球”主题的信息获取请求,第二服务器接收响应于该请求,向该手机发送“篮球”主题的待推荐的信息。
需要说明的是,当第二服务器保存的待推荐的信息较多时,为了便于第二服务器查找待推荐的信息,所述信息获取请求中可以包含待推荐的信息的特征,比如,可以包括下述至少一种:待推荐的信息的主题、待推荐的信息的关键词、待推荐的信息的编号以及待推荐的信息对应的信息推荐规则的标识,等等。即,第二服务器在接收到信息获取请求后,可以根据所述请求中包含的待推荐信息的标识,查找待推荐的信息。
方式2:从第二服务器下载所述待推荐的信息。
当通过执行步骤12后,信息推荐客户端判断向第一服务器发送的所述文本型数据符合主题为“篮球”的信息推荐规则,则信息推荐客户端将从第二服务器下载“篮球”主题的待推荐信息。
在实际应用中,不同的信息推荐规则中可能会设置有不同或相同的关键词。
一般地,当不同的信息推荐规则中设置了相同的关键词时,关键词与信息推荐规则之间,也即关键词与信息推荐规则对应的待推荐的信息之间,可能有不同的关联性。比如,以分别设置了关键词:“灌篮高手”的信息推荐规则1(主题为“漫画”)和信息 推荐规则2(主题为“篮球”)为例,该关键词与信息推荐规则1的关联性,据统计往往大于与信息推荐规则2的关联性,因此,在判断出信息推荐规则集合中至少存在两条信息推荐规则与文本型数据相匹配时,为了保证从第二服务器处获得的待推荐的信息,是相对而言与所述文本型数据的关联性最高的,本申请实施例中,可以分别为不同的信息推荐规则设置的各关键词分别设置权重。在这样的情况下,信息推荐客户端向第二服务器发送信息获取请求,具体可以包括:当判断出所述集合中存在与所述文本型数据相匹配的至少两个信息推荐规则时,根据为所述至少两个信息推荐规则中设置的各关键词所分别设置的权重,从所述至少两个信息推荐规则中选取信息推荐规则;将选取的信息推荐规则中设置的主题携带在所述信息获取请求中,向第二服务器进行发送。后续第二服务器根据该请求中的该主题,就可以向信息推荐客户端提供具备该主题的待推荐的信息。
例如,假设下述条件成立:
a、待推荐信息A的主题为:篮球,设置的信息推荐规则为:信息推荐规则1:“主题:篮球;关键词:灌篮”;
b、待推荐信息B的主题为:漫画《灌篮高手》,设置的信息推荐规则为:信息推荐规则2:“主题:漫画《灌篮高手》;关键词:灌篮”;
c、通过执行步骤11,获得信息提供客户端发送的文本型数据为:“昨天的灌篮大赛十分精彩”;
d、设置规则1的判断结果权重为2;设置规则2的判断结果权重为1;
e、当所述文本型数据与所述信息推荐规则相匹配时,所述文本型数据的计分=1,否则所述文本型数据的计分=0。
那么,通过对获得的文本型数据进行判断,得到该文本型数据与信息推荐规则1匹配时,则信息提供客户端发送的文本型数据的判断结果分数为:计分×权重=1×2=2分。类似地,该文本型数据也与信息推荐规则2匹配,则该文本型数据的判断结果分数为:计分×权重=1×1=1分。根据判断结果分数可以确定,该文本型数据与主题为“篮球”待推荐信息的关联性更高,从而获得第二服务器提供的“篮球”主题的待推荐信息。
还需要说明的是,为了避免频繁向用户进行信息推荐而导致用户产生不好的体验,本申请实施例中还提供信息推荐客户端从第二服务器获得待推荐的信息的限制策略。在一种实施方式中,针对步骤13,本申请实施例可以通过以下两种策略,来限制信息推荐客户端从第二服务器获得待推荐信息,具体包括:
策略a:步骤12中所述的文本型数据(一般指一条文本型数据)中出现的、与信息推荐规则中的关键词相同的词语的数量不小于预设数量时,信息推荐客户端才可以从第二服务器获得该信息推荐规则对应的待推荐信息进而展示给用户。
其中,这里所说的信息推荐规则,可以是与该文本型数据相匹配的任一信息推荐规则,也可以是通过采用前文介绍的方案,从与该文本型数据相匹配的至少两条信息推荐规则中确定出的一条信息推荐规则。
例如,假设下述条件成立:
条件1、待推荐信息的主题为:篮球,设置的信息推荐规则为:信息推荐规则1:“主题:篮球;关键词:灌篮”;
条件2、所述预设数量为2;
条件3、获得的文本型数据为:“这次灌篮大赛,我认为卡特的灌篮最帅”。
此时,所述获得的文本型数据中出现的、与信息推荐规则中关键词相同的词语“灌篮”的数量为2,则信息推荐客户端可以从第二服务器获得该主题的待推荐信息进而展示给用户。
策略b:与同一个信息推荐规则匹配的文本型数据的条数不小于预设条数时,信息推荐客户端才可以从第二服务器获得该信息推荐规则对应的待推荐信息进而展示给用户。
其中,这里所说的“同一个信息推荐规则”,可以是与步骤12中所述的文本型数据相匹配的任一信息推荐规则,也可以是通过采用前文介绍的方案,从与该文本型数据相匹配的至少两条信息推荐规则中确定出的一条信息推荐规则。这里所说的“与同一个信息推荐规则匹配的文本型数据”,一般包含步骤12所述的文本型数据在内,同时还可以包含数据提供客户端向第一服务器发送的其他文本型数据。这里所说的“与同一个信息推荐规则匹配的文本型数据的条数”,一般是指在预设时间长度(比如30分钟)内,由数据提供客户端向第一服务器发送的、与同一个信息推荐规则匹配的文本型数据的条数。
例如,假设下述条件成立:
条件1、待推荐信息的主题为:篮球,设置的信息推荐规则为:信息推荐规则1:“主题:篮球;关键词:灌篮”;
条件2、预设时间长度为30分钟;预设条数为2。
则,当获得数据提供客户端在30分钟内向第一服务器发送的、与该信息推荐规则匹配的文本型数据分别为:“这次灌篮大赛十分精彩”以及“我认为卡特的灌篮最帅”时, 此时获得的文本型数据中共有两条文本型数据与该信息推荐规则相匹配,则信息推荐客户端可以从第二服务器获得该主题的待推荐信息进而展示给用户。
需要说明的是,实施例1所提供方法的各步骤的执行主体均可以是同一设备,或者,该方法也由不同设备作为执行主体。比如,步骤11和步骤12的执行主体可以为设备1,步骤13的执行主体可以为设备2;又比如,步骤11的执行主体可以为设备1,步骤12和步骤13的执行主体可以为设备2;等等。
采用本申请实施例1提供的信息推荐方法,从“若客户端发送的文本型数据与根据待推荐的信息设置的信息推荐规则匹配,则说明用户很有可能属于对待推荐的信息认同或者感兴趣的特定人群”这一特点出发,当存在与客户端发送的文本型数据相匹配的信息推荐规则时,才获得服务器提供的待推荐的信息,从而在能够达到向特定人群进行信息推荐的前提下,实现了有选择性的信息推荐,避免了现有技术为了达到向特定人群进行信息推荐的目的,需要耗费较多的处理资源的问题。
实施例2
本申请实施例提供一种信息推荐装置,用以解决现有技术向特定人群进行信息推荐时,需要耗费较多的处理资源的问题。该装置的具体结构示意图如图4所示,包括文本型数据获得单元21、信息推荐规则判断单元22以及推荐信息获得单元23。
其中,文本型数据获得单元21,用于获得客户端向第一服务器发送的文本型数据;
信息推荐规则判断单元22,用于判断预设的信息推荐规则集合中,是否存在与所述文本型数据相匹配的信息推荐规则;其中,所述集合由信息推荐规则构成;信息推荐规则,是根据待推荐的信息设置的;
推荐信息获得单元23,用于在判断结果为是时,获得第二服务器提供的、与所述相匹配的信息规则匹配的推荐信息。
在一种实施方式中,所述待推荐的信息可以是由服务器提供的,在这样的场景下,推荐信息获得单元23,用于触发第二服务器推送所述待推荐的信息,并获得第二服务器推送的所述待推荐的信息;或从第二服务器下载所述待推荐的信息。
在一种实施方式中,推荐信息获得单元23,用于直接向第二服务器发送信息获取请求,并接收第二服务器响应于所述信息获取请求发送的所述待推荐的信息;或触发信息推送应用向第二服务器发送信息获取请求,并接收信息推送应用发来的、由第二服务器响应于所述信息获取请求发送的所述待推荐的信息。
当第二服务器保存的待推荐的信息较多时,为了便于第二服务器查找待推荐的信息,在一种实施方式中,所述信息获取请求中,包含所述待推荐的信息的特征。
在一种实施方式中,所述待推荐的信息的特征包括下述至少一种:所述待推荐的信息的主题;所述待推荐的信息的关键词;所述待推荐的信息的编号;所述待推荐的信息对应的信息推荐规则的标识。
为了保证从第二服务器处获得的待推荐的信息,是相对而言与所述文本型数据的关联性最高的,在一种实施方式中,推荐信息获得单元23,用于当所述集合中每个信息推荐规则中设置有一个主题,以及所述一个主题对应的至少一个关键词时,当判断出所述集合中存在与所述文本型数据相匹配的至少两个信息推荐规则时,根据针对所述至少两个信息推荐规则中设置的各关键词分别设置的权重,从所述至少两个信息推荐规则中选取信息推荐规则;将选取的信息推荐规则中设置的主题携带在所述信息获取请求中,向第二服务器进行发送。
所述文本型数据可以是主动获取的,也可以是被动接收的。比如,在一种实施方式中,文本型数据获得单元21,可以用于:从第一服务器获取所述客户端向第一服务器发送的文本型数据;或接收所述客户端发送来的所述文本型数据,其中,所述客户端发送来的文本型数据是通过复制客户端向第一服务器发送的文本型数据得到的。
为了可以更快捷的查找到预设的信息推荐规则集合,以判断预设的信息推荐规则集合中,是否存在与所述文本型数据相匹配的信息推荐规则,在一种实施方式中,信息推荐规则判断单元,还用于:在判断所述集合中,是否存在与所述文本型数据相匹配的信息推荐规则前,获得并保存由第二服务器提供的所述集合。
采用本申请实施例2提供的信息推荐装置,从“若客户端发送的文本型数据与根据待推荐的信息设置的信息推荐规则匹配,则说明用户很有可能属于对待推荐的信息认同或者感兴趣的特定人群”这一特点出发,当存在与客户端发送的文本型数据相匹配的信息推荐规则时,才获得服务器提供的待推荐的信息,从而在能够达到向特定人群进行信息推荐的前提下,实现了有选择性的信息推荐,避免了现有技术为了达到向特定人群进行信息推荐的目的,需要耗费较多的处理资源的问题。
本领域内的技术人员应明白,本发明的实施例可提供为方法、系统、或计算机程序产品。因此,本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的 计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中,计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器,随机存取存储器(RAM)和/或非易失性内存等形式,如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括,但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带,磁带/磁盘存储或其他磁性存储设备或任何其他非传输介质,可用于存储可以被计算设备访问的信息。按照本文中的界定,计算机可读介质不包括暂存电脑可读媒体(transitory media),如调制的数据信号和载波。
还需要说明的是,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白,本申请的实施例可提供为方法、系统或计算机程序产品。因此,本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且,本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
以上所述仅为本申请的实施例而已,并不用于限制本申请。对于本领域技术人员来说,本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等,均应包含在本申请的权利要求范围之内。

Claims (16)

  1. 一种信息推荐方法,其特征在于,包括:
    获得客户端向第一服务器发送的文本型数据;
    判断预设的信息推荐规则集合中,是否存在与所述文本型数据相匹配的信息推荐规则;其中,所述信息推荐规则,是根据待推荐的信息设置的;
    在判断结果为是时,获得第二服务器提供的、与所述相匹配的信息规则匹配的推荐信息。
  2. 如权利要求1所述的方法,其特征在于,获得所述第二服务器提供的所述待推荐的信息,包括:
    触发第二服务器推送所述待推荐的信息,并获得第二服务器推送的所述待推荐的信息;或从第二服务器下载所述待推荐的信息。
  3. 如权利要求2所述的方法,其特征在于,触发第二服务器推送所述待推荐的信息,包括:
    直接向第二服务器发送信息获取请求,并接收第二服务器响应于所述信息获取请求发送的所述待推荐的信息;或触发信息推送应用向第二服务器发送信息获取请求,并接收信息推送应用发来的、由第二服务器响应于所述信息获取请求发送的所述待推荐的信息。
  4. 如权利要求3所述的方法,其特征在于,所述信息获取请求中,包含所述待推荐的信息的特征。
  5. 如权利要求4所述的方法,其特征在于,所述待推荐的信息的特征包括下述至少一种:
    所述待推荐的信息的主题;
    所述待推荐的信息的关键词;
    所述待推荐的信息的编号;
    所述待推荐的信息对应的信息推荐规则的标识。
  6. 如权利要求5所述的方法,其特征在于,所述信息推荐规则集合中每个信息推荐规则中设置有一个主题,以及所述一个主题对应的至少一个关键词;则向第二服务器发送信息获取请求,包括:
    当判断出所述信息推荐规则集合中存在与所述文本型数据相匹配的至少两个信息推荐规则时,根据针对所述至少两个信息推荐规则中设置的各关键词分别设置的权重, 从所述至少两个信息推荐规则中选取信息推荐规则;
    将选取的信息推荐规则中设置的主题携带在所述信息获取请求中,向第二服务器进行发送。
  7. 如权利要求1所述的方法,其特征在于,获得客户端向第一服务器发送的文本型数据,包括:
    从第一服务器获取所述客户端向第一服务器发送的文本型数据;或接收所述客户端发送来的所述文本型数据,其中,所述客户端发送来的文本型数据是通过复制客户端向第一服务器发送的文本型数据得到的。
  8. 如权利要求1所述的方法,其特征在于,判断所述信息推荐规则集合中,是否存在与所述文本型数据相匹配的信息推荐规则前,所述方法还包括:
    获得并保存由第二服务器提供的信息推荐规则集合。
  9. 一种信息推荐装置,其特征在于,包括:
    文本型数据获得单元,用于获得客户端向第一服务器发送的文本型数据;
    信息推荐规则判断单元,用于判断预设的信息推荐规则集合中,是否存在与所述文本型数据相匹配的信息推荐规则;其中,信息推荐规则,是根据待推荐的信息设置的;
    推荐信息获得单元,用于在判断结果为是时,获得第二服务器提供的、与所述相匹配的信息规则匹配的推荐信息。
  10. 如权利要求9所述的装置,其特征在于,推荐信息获得单元,用于:
    触发第二服务器推送所述待推荐的信息,并获得第二服务器推送的所述待推荐的信息;或从第二服务器下载所述待推荐的信息。
  11. 如权利要求10所述的装置,其特征在于,推荐信息获得单元,用于:
    直接向第二服务器发送信息获取请求,并接收第二服务器响应于所述信息获取请求发送的所述待推荐的信息;或触发信息推送应用向第二服务器发送信息获取请求,并接收信息推送应用发来的、由第二服务器响应于所述信息获取请求发送的所述待推荐的信息。
  12. 如权利要求11所述的装置,其特征在于,所述信息获取请求中,包含所述待推荐的信息的特征。
  13. 如权利要求12所述的装置,其特征在于,所述待推荐的信息的特征包括下述至少一种:
    所述待推荐的信息的主题;
    所述待推荐的信息的关键词;
    所述待推荐的信息的编号;
    所述待推荐的信息对应的信息推荐规则的标识。
  14. 如权利要求13所述的装置,其特征在于,推荐信息获得单元,用于:
    当所述信息推荐规则集合中每个信息推荐规则中设置有一个主题,以及所述一个主题对应的至少一个关键词时,若判断出所述信息推荐规则集合中存在与所述文本型数据相匹配的至少两个信息推荐规则,则根据针对所述至少两个信息推荐规则中设置的各关键词分别设置的权重,从所述至少两个信息推荐规则中选取信息推荐规则;将选取的信息推荐规则中设置的主题携带在所述信息获取请求中,向第二服务器进行发送。
  15. 如权利要求9所述的装置,其特征在于,文本型数据获得单元,用于:
    从第一服务器获取所述客户端向第一服务器发送的文本型数据;或接收所述客户端发送来的所述文本型数据,其中,所述客户端发送来的文本型数据是通过复制客户端向第一服务器发送的文本型数据得到的。
  16. 如权利要求9所述的装置,其特征在于,信息推荐规则判断单元,还用于:
    在判断所述信息推荐规则集合中,是否存在与所述文本型数据相匹配的信息推荐规则前,获得并保存由第二服务器提供的信息推荐规则集合。
PCT/CN2016/104492 2015-11-13 2016-11-04 一种信息推荐方法及装置 WO2017080400A1 (zh)

Priority Applications (9)

Application Number Priority Date Filing Date Title
AU2016353806A AU2016353806C1 (en) 2015-11-13 2016-11-04 Information recommendation method and device
SG11201804033RA SG11201804033RA (en) 2015-11-13 2016-11-04 Information recommendation method and apparatus
JP2018524730A JP6860563B2 (ja) 2015-11-13 2016-11-04 情報推薦方法及び装置
KR1020187016867A KR102268934B1 (ko) 2015-11-13 2016-11-04 정보 추천 방법 및 장치
EP16863577.9A EP3376401A4 (en) 2015-11-13 2016-11-04 Information recommendation method and device
MYPI2018000720A MY194652A (en) 2015-11-13 2016-11-04 Information recommendation method and apparatus
US15/976,560 US11017451B2 (en) 2015-11-13 2018-05-10 Information recommendation based on rule matching
PH12018501016A PH12018501016A1 (en) 2015-11-13 2018-05-15 Information recommendation method and apparatus
US16/722,202 US11113743B2 (en) 2015-11-13 2019-12-20 Information recommendation based on rule matching

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510780621.0 2015-11-13
CN201510780621.0A CN106708858A (zh) 2015-11-13 2015-11-13 一种信息推荐方法及装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/976,560 Continuation US11017451B2 (en) 2015-11-13 2018-05-10 Information recommendation based on rule matching

Publications (1)

Publication Number Publication Date
WO2017080400A1 true WO2017080400A1 (zh) 2017-05-18

Family

ID=58694509

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/104492 WO2017080400A1 (zh) 2015-11-13 2016-11-04 一种信息推荐方法及装置

Country Status (10)

Country Link
US (2) US11017451B2 (zh)
EP (1) EP3376401A4 (zh)
JP (1) JP6860563B2 (zh)
KR (1) KR102268934B1 (zh)
CN (1) CN106708858A (zh)
AU (1) AU2016353806C1 (zh)
MY (1) MY194652A (zh)
PH (1) PH12018501016A1 (zh)
SG (1) SG11201804033RA (zh)
WO (1) WO2017080400A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110362594A (zh) * 2019-07-15 2019-10-22 阿里巴巴集团控股有限公司 一种信息处理方法和系统
CN111354350A (zh) * 2019-12-26 2020-06-30 阿里巴巴集团控股有限公司 语音处理方法及装置、语音处理设备、电子设备
CN117436221A (zh) * 2023-12-20 2024-01-23 中冶南方工程技术有限公司 一种异形非标管道空间智能匹配的方法和系统

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106708858A (zh) 2015-11-13 2017-05-24 阿里巴巴集团控股有限公司 一种信息推荐方法及装置
CN110955823B (zh) * 2018-09-26 2023-04-25 阿里巴巴集团控股有限公司 信息推荐方法、装置
CN109460944B (zh) * 2018-12-14 2024-05-03 平安健康保险股份有限公司 基于大数据的核保方法、装置、设备及可读存储介质
CN111368181A (zh) * 2018-12-25 2020-07-03 阿里巴巴集团控股有限公司 信息推荐方法、信息显示方法及装置
CN111241138B (zh) * 2020-01-14 2024-02-06 北京恒光信息技术股份有限公司 数据匹配方法及装置
CN111339411B (zh) * 2020-02-21 2023-09-29 京东科技控股股份有限公司 控制推荐策略使用的方法、装置、设备及存储介质
CN112000884A (zh) * 2020-08-13 2020-11-27 腾讯音乐娱乐科技(深圳)有限公司 一种用户内容推荐方法及装置、服务器、存储介质
CN112084291A (zh) * 2020-08-27 2020-12-15 广州新视展投资咨询有限公司 信息推荐方法及装置
CN115080835A (zh) * 2021-03-10 2022-09-20 阿里巴巴新加坡控股有限公司 信息推荐方法、装置、用户端及设备
CN113538048B (zh) * 2021-07-12 2022-10-14 深圳市明源云客电子商务有限公司 需求信息获得方法、装置、终端设备以及存储介质
CN115577125A (zh) * 2022-12-08 2023-01-06 中化现代农业有限公司 农业试验数据录入、检索方法和装置
CN117112857B (zh) * 2023-10-23 2024-01-05 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) 一种适用于工业智能制造的加工路径推荐方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102768685A (zh) * 2012-07-24 2012-11-07 杭州东方网升科技有限公司 一种基于关键字匹配的内容推荐方法
CN102984270A (zh) * 2012-12-12 2013-03-20 北京奇虎科技有限公司 一种消息推送服务器及方法
WO2014040516A1 (zh) * 2012-09-12 2014-03-20 腾讯科技(深圳)有限公司 信息推送方法及装置
CN103970857A (zh) * 2014-05-07 2014-08-06 百度在线网络技术(北京)有限公司 推荐内容确定系统和方法

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4581402B2 (ja) * 2003-12-26 2010-11-17 ソニー株式会社 投稿受信サーバ,投稿支援方法,およびそのプログラム
CN108133396A (zh) * 2006-03-03 2018-06-08 腾讯科技(深圳)有限公司 发布广告的方法和系统
CN101034455A (zh) * 2006-03-06 2007-09-12 腾讯科技(深圳)有限公司 一种实现在线广告的方法及系统
CN100556006C (zh) * 2007-03-30 2009-10-28 腾讯科技(深圳)有限公司 基于即时通信工具的在线广告互动系统及方法
CN101216825B (zh) * 2007-12-29 2010-10-27 朱廷劭 标引关键词提取/预测方法
CN102084363B (zh) * 2008-07-03 2014-11-12 加利福尼亚大学董事会 一种用于在结构化数据上高效地支持交互式模糊搜索的方法
JP5293301B2 (ja) * 2009-03-16 2013-09-18 富士通株式会社 検索装置、検索方法および記憶媒体
WO2012118997A2 (en) * 2011-03-03 2012-09-07 Brightedge Technologies, Inc. Optimization of social media engagement
JP5843581B2 (ja) * 2011-11-22 2016-01-13 Kddi株式会社 対話システム、対話方法およびプログラム
CN103136300B (zh) * 2011-12-05 2017-02-01 北京百度网讯科技有限公司 一种文本相关主题的推荐方法和装置
CN103176982B (zh) * 2011-12-20 2016-04-27 中国移动通信集团浙江有限公司 一种电子图书推荐的方法及系统
JP5571145B2 (ja) * 2012-10-03 2014-08-13 ヤフー株式会社 広告配信装置および広告配信方法
CN104135498B (zh) * 2013-05-03 2018-07-06 杭州诺霖信息科技有限公司 一种跨平台的信息推送系统及其推送方法
KR20150041674A (ko) * 2013-10-07 2015-04-17 주식회사 예스콜닷컴 온라인 종업원 공모 시스템 및 그 방법
CN104639420B (zh) * 2013-11-15 2019-06-07 腾讯科技(深圳)有限公司 即时通讯的信息处理方法和系统
CN104699696B (zh) * 2013-12-05 2018-12-28 深圳市腾讯计算机系统有限公司 文件推荐方法和装置
CN104794122B (zh) * 2014-01-20 2020-04-17 腾讯科技(北京)有限公司 一种位置信息推荐方法、装置和系统
CN104022940A (zh) * 2014-04-16 2014-09-03 华为技术有限公司 基于即时通信的信息处理方法、装置及系统
CN104123360B (zh) * 2014-07-18 2017-07-21 腾讯科技(深圳)有限公司 一种应用推荐数据获取方法、装置、电子设备及系统
CN106708858A (zh) 2015-11-13 2017-05-24 阿里巴巴集团控股有限公司 一种信息推荐方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102768685A (zh) * 2012-07-24 2012-11-07 杭州东方网升科技有限公司 一种基于关键字匹配的内容推荐方法
WO2014040516A1 (zh) * 2012-09-12 2014-03-20 腾讯科技(深圳)有限公司 信息推送方法及装置
CN102984270A (zh) * 2012-12-12 2013-03-20 北京奇虎科技有限公司 一种消息推送服务器及方法
CN103970857A (zh) * 2014-05-07 2014-08-06 百度在线网络技术(北京)有限公司 推荐内容确定系统和方法

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110362594A (zh) * 2019-07-15 2019-10-22 阿里巴巴集团控股有限公司 一种信息处理方法和系统
CN111354350A (zh) * 2019-12-26 2020-06-30 阿里巴巴集团控股有限公司 语音处理方法及装置、语音处理设备、电子设备
CN111354350B (zh) * 2019-12-26 2024-04-05 阿里巴巴集团控股有限公司 语音处理方法及装置、语音处理设备、电子设备
CN117436221A (zh) * 2023-12-20 2024-01-23 中冶南方工程技术有限公司 一种异形非标管道空间智能匹配的方法和系统
CN117436221B (zh) * 2023-12-20 2024-04-12 中冶南方工程技术有限公司 一种异形非标管道空间智能匹配的方法和系统

Also Published As

Publication number Publication date
JP6860563B2 (ja) 2021-04-14
PH12018501016A1 (en) 2018-11-05
KR102268934B1 (ko) 2021-06-28
US11113743B2 (en) 2021-09-07
MY194652A (en) 2022-12-10
SG11201804033RA (en) 2018-06-28
US20180260489A1 (en) 2018-09-13
US11017451B2 (en) 2021-05-25
JP2019500684A (ja) 2019-01-10
CN106708858A (zh) 2017-05-24
KR20180082570A (ko) 2018-07-18
AU2016353806B2 (en) 2021-04-01
AU2016353806A1 (en) 2018-06-28
US20200125615A1 (en) 2020-04-23
EP3376401A1 (en) 2018-09-19
AU2016353806C1 (en) 2021-10-07
EP3376401A4 (en) 2018-09-19

Similar Documents

Publication Publication Date Title
WO2017080400A1 (zh) 一种信息推荐方法及装置
JP5819412B2 (ja) コンテキストに基づいて選択したコンテンツ項目の提供
Chiu et al. Personalized blog content recommender system for mobile phone users
Wong et al. Accessing suicide-related information on the internet: a retrospective observational study of search behavior
US8909719B2 (en) Method of managing feeds based on classifications
US10394939B2 (en) Resolving outdated items within curated content
JP7119246B2 (ja) 動的アプリケーションコンテンツ分析
WO2014180196A1 (zh) 信息推荐处理方法及装置
CN107491465B (zh) 用于搜索内容的方法和装置以及数据处理系统
US9342578B1 (en) Organizing indications of approval for collections
US20180218079A1 (en) Method and system for generating phrase blacklist to prevent certain content from appearing in a search result in response to search queries
US8504545B2 (en) Apparatus and methods for managing a social media universe
KR20160042891A (ko) 검색 결과 증강 기법
US11218390B2 (en) Filtering content based on user mobile network and data-plan
US20180302761A1 (en) Recommendation System for Multi-party Communication Sessions
US9251273B2 (en) Delivering a filtered search result
US20170270195A1 (en) Providing token-based classification of device information
US9519710B1 (en) Dynamic classification of attribute relevance and classification
JP2010140195A (ja) 画像配信装置、画像配信システム及び画像配信方法
US20210109982A1 (en) Identifying and storing relevant user content in a collection accessible to user in website subscribed to service
US20230096274A1 (en) System for filtering displayed content at the os level
Michael et al. Using cloud storage to support reminiscence

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16863577

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 11201804033R

Country of ref document: SG

Ref document number: 2018524730

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 12018501016

Country of ref document: PH

WWE Wipo information: entry into national phase

Ref document number: 2016863577

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 20187016867

Country of ref document: KR

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 1020187016867

Country of ref document: KR

ENP Entry into the national phase

Ref document number: 2016353806

Country of ref document: AU

Date of ref document: 20161104

Kind code of ref document: A