CN111080339B - Scene-based category preference data generation method and device - Google Patents
Scene-based category preference data generation method and device Download PDFInfo
- Publication number
- CN111080339B CN111080339B CN201911128690.8A CN201911128690A CN111080339B CN 111080339 B CN111080339 B CN 111080339B CN 201911128690 A CN201911128690 A CN 201911128690A CN 111080339 B CN111080339 B CN 111080339B
- Authority
- CN
- China
- Prior art keywords
- data
- user
- search
- scene
- behavior
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 74
- 230000006399 behavior Effects 0.000 claims abstract description 354
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000004891 communication Methods 0.000 claims description 28
- 238000004220 aggregation Methods 0.000 claims description 10
- 230000002776 aggregation Effects 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 8
- 238000005065 mining Methods 0.000 abstract description 4
- 235000021152 breakfast Nutrition 0.000 description 18
- 238000010586 diagram Methods 0.000 description 14
- 235000015278 beef Nutrition 0.000 description 4
- 235000013410 fast food Nutrition 0.000 description 4
- 241001122767 Theaceae Species 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 235000012054 meals Nutrition 0.000 description 2
- 238000011022 operating instruction Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 239000002537 cosmetic Substances 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 235000015219 food category Nutrition 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 235000021395 porridge Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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—Item recommendations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a scene-based category preference data generation method and device, wherein the method comprises the following steps: collecting user behavior historical data related to search behaviors, wherein the user behavior historical data comprises user behavior scene historical data and corresponding user behavior target entity historical data; performing scene recognition processing according to the user behavior scene history data to obtain user search scene data; according to the historical data of the user behavior target entity, determining category data and behavior preference data corresponding to the user behavior target entity; and generating category preference data under the user search scene according to the user search scene data, the category data and the behavior preference data, and storing offline. The method achieves the purpose of mining the category preference of the user in different scenes by big data, combines the category preference of the user search scene, enables the mined user preference to be more suitable for the actual preference habit of the user, is higher in accuracy, and can improve the search recommendation effect when the search recommendation is carried out subsequently.
Description
Technical Field
The invention relates to the technical field of Internet, in particular to a scene-based category preference data generation method and device.
Background
In the traditional searching mode, the user preference content is usually mined according to the searching log to conduct searching recommendation, but in the O2O field, because the user consumes on line, the content of interest of the user in different scenes is different, and therefore the searching recommendation mode of searching scenes of the user is not considered to be poor in effect.
The prior art (CN 105975522A) discloses a multi-domain content recommendation method, which calculates the preference degree of each user for different domains under each situation through a server, and selects a domain with the preference degree greater than a set preference degree threshold as a preference domain; then, obtaining the preference degree of each user for all contents in all fields, and sequencing the preference degrees from high to low to obtain a preference content list; then, selecting the content belonging to the preference field from the preference content list to obtain a recommended content list of each user in each scene. Finally, the server searches a recommended content list corresponding to the current scene in the recommended list according to the current scene and sends the recommended content list to the client.
However, the inventors found in the course of implementing the present invention that: the prior art aims at each user, and the preference of the user under different scenes is mined based on the browsing records of the user, so that the user is searched and recommended with reference to the preference of the user under different scenes. The method is characterized in that portrait description is carried out on the user according to the historical browsing record of the user, search recommendation is carried out according to the portrait of the user, and for a certain user, the data source is the browsing record of the user, the data source is single, the mined user preference content also lacks diversity and has poor accuracy, so that the search recommendation effect is poor.
Disclosure of Invention
The present invention has been made in view of the above problems, and it is an object of the present invention to provide a scene-based category preference data generating method and apparatus that overcomes or at least partially solves the above problems.
According to an aspect of the present invention, there is provided a scene-based category preference data generation method including:
collecting user behavior historical data related to search behaviors, wherein the user behavior historical data comprises user behavior scene historical data and corresponding user behavior target entity historical data;
performing scene recognition processing according to the user behavior scene history data to obtain user search scene data;
according to the historical data of the user behavior target entity, determining category data and behavior preference data corresponding to the user behavior target entity;
and generating category preference data under the user search scene according to the user search scene data, the category data and the behavior preference data, and storing offline.
Optionally, the user behavior scene history data includes: time data, location data, and/or search terms;
performing scene recognition processing according to the user behavior scene history data to obtain user search scene data further comprises:
And obtaining a time period label, a position label and/or a search intention label in the user search scene according to the time data, the position data and/or the search word.
Optionally, the period label comprises: a plurality of time period grading tags, a workday time period tag, and/or a veto decision time period tag;
the position tag includes: a plurality of location type tags, whether a location is resident tags, and/or a distance tag of a search location from a current location;
the search intention label includes: entity intent tags, category intent tags, address intent tags, and/or content intent tags.
Optionally, the user behavior target entity history data includes: user browsing behavior data and user consumption behavior data of the target entity related to the search behavior;
the behavior preference data includes: the user browses the behavior data and the data amount of the user consumption behavior data.
Optionally, generating the category preference data in the user search scene according to the user search scene data, the category data and the behavior preference data further includes:
generating category preference data under the user search scenes with different priorities according to the user search scene data, the category data and the behavior preference data;
The user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
Optionally, after obtaining the user search scene data, the method further comprises:
and carrying out aggregation processing on the user search scene data, and screening out the user search scene data of which the data quantity is smaller than a preset data quantity threshold value.
According to another aspect of the present invention, there is provided a scene-based search recommendation method, including:
receiving user behavior real-time data related to search behaviors, wherein the user behavior real-time data comprises user behavior scene real-time data;
inquiring user real-time searching scene data matched with the user behavior scene real-time data;
inquiring category preference data which is stored offline and corresponds to the user real-time searching scene data;
recommending search results according to category preference data;
and returning the recommended search results to the client so that the client can display the search results.
Optionally, the user behavior scene real-time data includes: time data, location data, and/or search terms;
Querying the user real-time search scene data that matches the user behavior scene real-time data further includes:
and obtaining a time period label, a position label and/or a search intention label of the user in a real-time search scene according to the time data, the position data and/or the search word.
Optionally, querying category preference data corresponding to the user real-time search scene data stored offline specifically includes:
inquiring category preference data under the user search scene with highest priority corresponding to the user real-time search scene data in category preference data under the user search scenes with different priorities stored offline;
the user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
Optionally, the recommending search results according to the category preference data specifically includes:
and recommending the search results by taking the category preference data as a ranking factor.
According to another aspect of the present invention, there is provided a scene-based category preference data generating apparatus including:
The acquisition module is suitable for acquiring user behavior historical data related to search behaviors, wherein the user behavior historical data comprises user behavior scene historical data and corresponding user behavior target entity historical data;
the scene recognition module is suitable for performing scene recognition processing according to the user behavior scene history data to obtain user search scene data;
the data analysis module is suitable for determining category data and behavior preference data corresponding to the user behavior target entity according to the user behavior target entity history data;
the scene preference analysis module is suitable for generating category preference data in a user search scene according to the user search scene data, the category data and the behavior preference data, and storing the category preference data offline.
Optionally, the user behavior scene history data includes: time data, location data, and/or search terms;
the scene recognition module is further adapted to: and obtaining a time period label, a position label and/or a search intention label in the user search scene according to the time data, the position data and/or the search word.
Optionally, the period label comprises: a plurality of time period grading tags, a workday time period tag, and/or a veto decision time period tag; the position tag includes: a plurality of location type tags, whether a location is resident tags, and/or a distance tag of a search location from a current location; the search intention label includes: entity intent tags, category intent tags, address intent tags, and/or content intent tags.
Optionally, the user behavior target entity history data includes: user browsing behavior data and user consumption behavior data of the target entity related to the search behavior;
the behavior preference data includes: the user browses the behavior data and the data amount of the user consumption behavior data.
Optionally, the scene preference analysis module is further adapted to: generating category preference data under the user search scenes with different priorities according to the user search scene data, the category data and the behavior preference data;
the user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
Optionally, the apparatus further comprises:
and the aggregation processing module is suitable for carrying out aggregation processing on the user search scene data and screening out the user search scene data of which the data quantity is smaller than a preset data quantity threshold value.
According to another aspect of the present invention, there is provided a scene-based search recommendation apparatus, including:
the receiving module is suitable for receiving user behavior real-time data related to the search behavior, wherein the user behavior real-time data comprises user behavior scene real-time data;
The matching module is suitable for inquiring the user real-time searching scene data matched with the user behavior scene real-time data;
the query module is suitable for querying category preference data which is stored offline and corresponds to the user real-time search scene data;
the search recommendation module is suitable for recommending search results according to category preference data;
and the return module is suitable for returning recommended search results to the client so that the client can display the search results.
Optionally, the user behavior scene real-time data includes: time data, location data, and/or search terms;
the matching module is further adapted to: and obtaining a time period label, a position label and/or a search intention label of the user in a real-time search scene according to the time data, the position data and/or the search word.
Optionally, the query module is further adapted to:
inquiring category preference data under the user search scene with highest priority corresponding to the user real-time search scene data in category preference data under the user search scenes with different priorities stored offline;
the user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
Optionally, the search recommendation module is further adapted to:
and recommending the search results by taking the category preference data as a ranking factor.
According to yet another aspect of the present invention, there is provided a computing device comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction, where the executable instruction causes the processor to execute operations corresponding to the above-mentioned scene-based category preference data generating method and the scene-based search recommendation method.
According to still another aspect of the present invention, there is provided a computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the above-described scene-based category preference data generation method and scene-based search recommendation method.
According to the scene-based category preference data generation method and device, user behavior history data related to search behaviors are collected, wherein the user behavior history data comprises user behavior scene history data and corresponding user behavior target entity history data; performing scene recognition processing according to the user behavior scene history data to obtain user search scene data; according to the historical data of the user behavior target entity, determining category data and behavior preference data corresponding to the user behavior target entity; and generating category preference data under the user search scene according to the user search scene data, the category data and the behavior preference data, and storing offline. According to the method, the historical data of the user behaviors related to the search behaviors are analyzed and processed to generate the user search scene data, the category data and the user preference data, the category preference data of the user in the search scene are generated according to the search scene data and the user preference data, the purpose of mining the category preference of the user in different scenes by big data is achieved, the category preference of the user in the search scene is combined, the user preference data can be mined to be more suitable for actual preference habits of the user, the accuracy is higher, and therefore the search recommendation effect can be improved when the user is subjected to search recommendation in the follow-up process.
According to the scene-based search recommendation method and device, user behavior real-time data related to search behaviors are received, wherein the user behavior real-time data comprise user behavior scene real-time data; inquiring user real-time searching scene data matched with the user behavior scene real-time data; and querying category preference data which is stored offline and corresponds to the user real-time search scene data. According to the method, the user search scene is identified by combining the information of three dimensions of time, space and search intention, and search ranking is performed according to category preference data corresponding to the user search scene, so that search recommendation combined with the search scene is realized, and the effect of the search recommendation can be improved.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 illustrates a flow diagram of a method for generating scene-based category preference data according to one embodiment of the invention;
FIG. 2 shows a flow diagram of a method for generating scene-based category preference data according to another embodiment of the invention;
FIG. 3 is a flow diagram of a scenario-based search recommendation method according to another embodiment of the present invention;
FIG. 4 is a flow diagram of a scenario-based search recommendation process in another embodiment of the present invention;
FIG. 5 shows a functional block diagram of a scene-based category preference data generating apparatus according to still another embodiment of the present invention;
FIG. 6 is a functional block diagram of a scenario-based search recommendation apparatus according to another embodiment of the present invention;
FIG. 7 illustrates a schematic diagram of a computing device, according to an embodiment of the invention;
FIG. 8 illustrates a schematic diagram of a computing device, according to an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In the existing search scenes, the first type of search scenes are that the search targets of the user are obvious in direction, if the user inputs a search word 'Kenderstyle', the category directions of the search word 'Kenderstyle' are obvious, the search targets of the user are very clear, namely 'Kenderstyle' is searched, and then the system directly recommends corresponding search results according to the search targets of the user; the second type of search scene is that the search target of the user is not obvious enough, for example, the user inputs the search word 'beef', the search word has different preference of the category of the user for searching the target under the search scenes of different time, space and intention, the user can also find beef steamed stuffed bun which is prone to be light in the morning and beef chafing dish which is prone to be dinner in the noon, and the like, the category of the search word 'beef' is not obvious, and the search scene of the user about time, space and intention needs to be determined, so that the preference of the category of the user under the search scene can be further determined; when searching for addresses, the second category of search scenarios is more different, for example, when searching for addresses with a larger distance, it is more likely to find restaurants with higher consumption and higher quality, the category preference is relatively high-grade, and when searching for addresses with a smaller distance, the consumption is less obvious.
Based on the method, the device and the system, the scene of time, space and search intention when the user searches is identified, particularly the search intention is identified aiming at the search words with unobvious category directions, category preference under different search scenes is generated, and the obtained scene category preference is applied to search sequencing.
FIG. 1 is a flow chart of a scenario-based category preference data generation method according to one embodiment of the present invention, which is implemented based on big data, as shown in FIG. 1, and includes:
step S101, collecting user behavior historical data related to search behaviors, wherein the user behavior historical data comprises user behavior scene historical data and corresponding user behavior target entity historical data.
Various behaviors of the user in the search system are recorded in a behavior data manner, and in this embodiment, historical user behavior data related to the search behavior is collected, where the search behavior specifically refers to the historical search behavior of the user. The user behavior scene history data related to the search behavior may include time data, location data, and/or scene related data such as search words corresponding to the user history search behavior, that is, time, location, and/or used search words when the user performs the search. The corresponding user behavior target entity historical data specifically refers to various behavior data which is generated after the user searches and is aimed at a target entity, such as behavior data generated when the user clicks and browses the entity behavior, behavior data generated when the user purchases the entity behavior, and the like, wherein the entity refers to: objectively existing and distinguishable things, including in particular merchandise, shops, coupons, and the like.
Step S102, scene recognition processing is carried out according to the user behavior scene history data, and user search scene data is obtained.
Through the step, the search scene where the user searches is identified, for example, the historical data of the user behavior scene is labeled based on a scene understanding method, so that the user search scene data is obtained.
Step S103, according to the historical data of the user behavior target entity, category data and behavior preference data corresponding to the user behavior target entity are determined.
And counting historical data of the target entity of the user behavior to obtain category data and behavior preference data corresponding to the target entity aimed at by the historical behavior of the user. For example, the categories to which the target entity for which the user purchase behavior is directed and the number of times each category is purchased are counted.
Step S104, generating category preference data in the user search scene according to the user search scene data, the category data and the behavior preference data, and storing the category preference data offline.
According to the above, it can be known that there is a correspondence between the user search scene data and the category data and the behavior preference data, then the user search scene is determined according to the correspondence between the data, the category data is scored according to the category preference data in the user search scene, so as to obtain the category preference data in the user search scene, and then the generated category preference data in the user search scene is stored offline.
According to the scene-based category preference data generation method provided by the embodiment, user behavior history data related to search behaviors are collected, wherein the user behavior history data comprises user behavior scene history data and corresponding user behavior target entity history data; performing scene recognition processing according to the user behavior scene history data to obtain user search scene data; according to the historical data of the user behavior target entity, determining category data and behavior preference data corresponding to the user behavior target entity; and generating category preference data under the user search scene according to the user search scene data, the category data and the behavior preference data, and storing offline. According to the method, the historical data of the user behaviors related to the search behaviors are analyzed and processed to generate the user search scene data, the category data and the user preference data, the category preference data of the user in the search scene are generated according to the search scene data and the user preference data, the purpose of mining the category preference of the user in different scenes by big data is achieved, the category preference of the user in the search scene is combined, the user preference data can be mined to be more suitable for actual preference habits of the user, the accuracy is higher, and therefore the search recommendation effect can be improved when the user is subjected to search recommendation in the follow-up process.
FIG. 2 shows a flow diagram of a scenario-based category preference data generation method according to another embodiment of the present invention, as shown in FIG. 2, the method comprising:
step S201, collecting user behavior history data related to the search behavior, where the user behavior history data includes user behavior scene history data and corresponding user behavior target entity history data, and the user behavior scene history data includes: time data, location data, and/or search terms.
Various behaviors of the user in the search system are recorded in a behavior data manner, and in this embodiment, historical user behavior data related to the search behavior is collected, where the search behavior specifically refers to the historical search behavior of the user. The user behavior scene history data related to the search behavior comprises time data, position data and/or search words corresponding to the user history search behavior, namely time, position and/or used search words when the user searches. The user behavior target entity historical data corresponding to the user behavior scene historical data specifically refers to various behavior data which are generated after the user searches and are aimed at a target entity.
For example, the user searches seven points in the morning in the office using the search term "nearby eat", and finally purchases the commodity ticket entity "kender breakfast ticket" in the search result after browsing the store entity "breakfast shop" and the "open breakfast" in the search result, and then the collected user behavior scene history data related to the current search behavior includes: time data- "seven points in the morning", location data- "office building" and "eating near search term", corresponding user behavior target entity history data includes: browsing behavior data generated by browsing store entities "breakfast porridge" and "open breakfast" and consumption behavior data generated by purchasing commodity ticket entities "kender breakfast ticket" behaviors.
Optionally, the user behavior scene history data and the corresponding user behavior target entity history data related to the location data are collected, where the location data related indicates that the location corresponding to the location data is located in the same area, for example, in the same city, the same administrative area, the same country, and the like. In practical application, in an O2O scene, cities serve as basic units of life of people, distribution of categories can be produced in city dimensions, and then preference of the categories is produced by taking the distribution of the categories of the cities as a benchmark.
Step S202, obtaining a time period label, a position label and/or a search intention label in a user search scene according to the time data, the position data and/or the search word.
In this embodiment, the user search scene data is obtained by tagging the user behavior scene history data related to the history search behavior, that is, tagging the time, the position and the search word when the user searches.
For understanding the time period of the time data, namely identifying the time period to which the time data corresponding to the search behavior belongs, determining a time period label of the search behavior, wherein the time period label comprises: a multiple time period ranking tag, a workday time period tag, and/or a veto time period tag. Wherein the plurality of time period grading tags comprises: breakfast time period labels, lunch time period labels, afternoon tea time period labels, dinner time period labels and night time period labels, wherein the time period labels correspond to one time period, and when labeling, determining which time period the time data belongs to, and labeling the time period labels corresponding to the time period. For the decision time period label, two pieces of time information are combined to judge, namely, the time information of clicking browsing behavior data aiming at a target entity is generated, and the time information of consuming behavior data aiming at the target entity is generated, for example, the time when a user clicks a browsing store and the time consumed in the store are determined to be in a decision time period according to the time interval between the two, if the time interval exceeds a preset threshold, the time period label is determined to be the decision time period label, and if the time interval does not exceed the preset threshold, the time period label is determined to be the non-decision time period label.
And carrying out space understanding on the position data, namely identifying the place to which the position data corresponding to the search behavior belongs, and determining the position label of the search behavior. If the user searches, based on the POI engine, the name, type and other information of the position where the user is located are obtained according to the geographic position information of the user, the WiFi information connected with the terminal and the like, so that position data corresponding to the searching behavior are obtained, and the position label is further determined according to the position data. The position tag includes: a plurality of location type tags, a resident tag, and/or a search location distance tag from the current location. Wherein the plurality of location type tags comprises: office area tags, residential area tags, mall tags, office building tags, school area tags, transportation hub tags, and the like. For whether the resident tag is, the resident data can be determined according to the position data contained in the historical behavior data of the user, and the position data corresponding to the search behavior is compared with the resident data, so that whether the position data is the resident tag can be determined. For the distance labels of the searching place and the current place, setting a close distance label, a middle distance label and a long distance label according to different distance intervals in advance, wherein the close distance label corresponds to within 500 meters, the middle distance label corresponds to between 500 meters and 1000 meters, the long distance label corresponds to over 1000 meters, and the like, and determining the distance label of the searching place and the current place according to the distance interval of the distance between the position corresponding to the position data and the position corresponding to the searching position data when the labels are marked.
And carrying out understanding of the search intention aiming at the search word, namely identifying the search intention according to the search word corresponding to the search behavior to obtain a search intention label of the search behavior. The search intention label includes: entity intent tags, category intent tags, address intent tags, and/or content intent tags. When a user searches, the user usually inputs a search word, and identifies the search word to determine whether the user's search intention is to search for a store, a menu, a category, an address or content, thereby determining a search intention label. For example, if the search term is "nearby eating", and it is determined that the search intention of the user is to find a store, the corresponding search intention label is an entity intention label, and if the search term is "mini-singing bar", the user may be to find a nearby "mini-singing bar", and it is determined that the search intention of the user is to find an address of "mini-singing bar", the search intention address intention label of the user is determined. Therefore, the invention can label the category search intention for the search word with fuzzy category input by the user based on the understanding of the search intention, and accurately identify the search intention of the user.
Preferably, after obtaining the user search scene data, performing aggregation processing on the user search scene data, and screening out the user search scene data with the data amount smaller than the preset data amount threshold. The data size can represent the occurrence times of the user searching scene, and many users search under a certain searching scene, so that the data size of the user searching scene of the searching scene is larger. For example, for the search scene data of "night time period tag+very resident tag+long distance tag", usually such a search scene is less likely to occur, and the reference value of the user behavior data in such a search scene is not great, so that the search scene data with a small data amount is filtered out, and in this way, the influence of a small number of special search scene data is eliminated, thereby improving the accuracy of scene category preference.
Step S203, according to the historical data of the user behavior target entity, category data and behavior preference data corresponding to the user behavior target entity are determined.
The historical data of the target entity of the user behavior in this embodiment specifically refers to various behavior data generated after the user searches for the target entity, that is, the user browsing behavior data related to the historical searching behavior, and in this embodiment specifically includes the user browsing behavior data and the user consumption behavior data, where, of course, in practical application, the user clicking behavior data, the user collecting behavior data and the like can be all used as the basis of the output behavior preference data.
According to the user browsing behavior data related to the historical searching behavior, determining category data of a target entity aimed at by the user browsing behavior, and according to the user consumption behavior data related to the historical searching behavior, determining categories of the target entity aimed at by the user consumption behavior, thereby obtaining category data corresponding to the target entity of the user behavior. The behavior preference data corresponding to the user behavior target entity comprises: the user browses the behavior data and the data amount of the user consumption behavior data. Accordingly, the data volume of the user browsing behavior data can also represent the number of times of the user browsing behavior, and the data volume of the user consumption behavior data can also represent the number of times of the user consumption behavior, and the larger the data volume is, the more times are indicated.
In short, this step is to count the categories to which the target entity browsed and consumed by the user after searching belongs, and the number of browses and consumed times corresponding to each category.
Wherein the categories can be divided into a primary category, a secondary category, and a tertiary category, the primary category comprising: food, recreational, etc., and secondary categories include: chinese, western, cosmetic massage, etc., three categories include: jiang Zhe Cai, ben's help, fang Ding, spa, etc. The specific meaning and classification mode of the category can be set according to actual needs, and the invention is not limited to this.
Step S204, category preference data under the user search scene with different priorities are generated according to the time period labels, the position labels and/or the search intention labels under the user search scene, the category data and the behavior preference data, and the category preference data are stored offline.
Determining a user search scene according to the user search scene data, determining category data and behavior preference data in the user search scene, and scoring each category contained in the category data according to the behavior preference data to obtain preference scores of each category in the user search scene, wherein the higher the preference score of each category indicates the stronger the preference degree of the user for the category. Alternatively, since the user browsing behavior and the user purchasing behavior represent user preferences of different degrees, the browsing behavior represents the user may be interested, and the purchasing behavior represents the user really needs, different weight values are respectively set for the user browsing behavior data and the user purchasing behavior data when the categories are classified under the user scene according to the behavior preference data, and the preference score of each category is calculated according to the data amount of the user browsing behavior data and the weight value thereof, and the data amount of the user purchasing behavior data and the weight value thereof. Optionally, the weight value of the user browsing behavior data is lower than the weight value of the user purchasing behavior data.
In this embodiment, in order to prevent the sparse problem of the category preference data, a hierarchical category preference construction mode is adopted to set the priority of the user search scene, so that category preference data under user search scenes with different priorities are generated. Optionally, the user searching scenes are in order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
For example, a user search scene including a search intention tab, a period tab, and a location tab is determined as a primary user search scene, a user search scene including a period tab and a location tab is determined as a secondary user search scene, and a user search scene including a period tab is determined as a tertiary user search scene.
The method of this embodiment will be described by way of example. Firstly, acquiring user behavior history data of a user A related to search behaviors, wherein the user A searches nearby at 7 am on the working day, browses a celebration steamed stuffed bun, and determines that user search scene data are: breakfast time period tag + office building tag + entity intent tag ". According to the search scene data of the user A, the determined user search scenes with different priorities comprise: first-level user search scenarios: breakfast time period tag + office building tag + entity intent tag ", the secondary user searches for a scene: "breakfast time period tag+office building tag", three-level user search scenario: "weekday time tag". The user behavior target entity history data corresponding to the user searching scene data comprises browsing data generated by browsing the celebration steamed stuffed bun by the user A.
For another example, if the user a searches at twelve noon on weekdays using "nearby eat" and purchases "kendyke coupon", the user search scene data is determined as: "lunch period tag+office building tag+entity intention tag". The determined user search scenes with different priorities include: first-level user search scenarios: "lunch period tag+office building tag+entity intention tag", the secondary user searches for a scene: "lunch period tag+write building tag", three-level user search scenario: "lunch period label". That is, the user behavior target entity history data corresponding to the user search scene data includes browsing data generated by the user a purchasing a "kender coupon". Therefore, the user has different searching behaviors under different searching scenes, the user history searching scene can be identified according to the user behavior history data of the history searching behaviors, and the user behavior target entity data under the user history searching scene is acquired.
And then, according to the mapping relation between the user search scene data and the user behavior target entity historical data, category data and behavior preference data under each user search scene are determined, namely, according to browsing behaviors and purchasing behaviors actually generated by the user after the user searches under each search scene, category preference of the user under the search scene is determined.
For example, in a search scenario including "breakfast period tag+office building tag+entity intention tag", statistics is performed on user behavior target entity data to obtain: 300 users purchase the purchasing behavior data of the celebration steamed stuffed bun coupon, 100 users browse the browsing behavior data of the celebration steamed stuffed bun, 90 users purchase the purchasing behavior data of the Kenderstyle package, and 10 users browse the browsing behavior data of the Kenderstyle store. The categories corresponding to the celebration steamed stuffed bun coupon and the celebration steamed stuffed bun shop are Chinese meal, the categories corresponding to the kender package and the kender shop are fast food, and the category data in the search scene comprise: chinese and fast food. Obtaining user preference data corresponding to category data in the search scene according to the analysis method comprises the following steps: the corresponding user browsing behavior data quantity of the Chinese food category is 100, the data quantity proportion is 100/(100+300+10+90) =20%, the user purchasing behavior data quantity is 300, and the data quantity proportion is 300/(100+300+10+90) =60%; the corresponding user browsing behavior data volume of the category fast food is 10, the data volume ratio is 10/(100+300+10+90) =2%, the user purchasing behavior data volume is 90, and the data volume ratio is 90/(100+300+10+90) =18%. The weight value of the user browsing behavior data is set to be 0.5, and the weight value of the user purchasing behavior data is set to be 0.8. The preference score of the category Chinese meal in the finally calculated first-level user search scene is as follows: 20%. 0.5+60%. 0.8=0.58, preference scores for category fast food are: 2% ×0.5+18% ×0.8=0.154. Thus, category preference data of the first-level user search scene is obtained. The analysis modes of the category preference data of other user search scenes are consistent, and are not described in detail herein. Of course, this is merely an example of the present invention, and aspects of the present invention are not limited in this respect.
Further, after obtaining the category preference score of each category in the user search scene, the filtering may be further performed according to a preset threshold, so that the category preference score of each category in the category preference data is higher than the preset threshold.
In summary, the method of the embodiment is implemented based on the machine learning mode of big data, learning is performed according to the historical search data of the user to obtain preference data of the user category, different search scenes are identified by analyzing scene data including time, geographic position and scene information of three dimensions of the search word when the user searches, behavior data of a target entity is analyzed according to the user searching, preferences of the user for each category under different search scenes are mined, and the purpose of mining the preference of the user scene in the big data mode is achieved, so that the mined preference of the user scene can be more matched with the actual preference of the user, and accuracy is higher.
Fig. 3 is a schematic flow chart of a scenario-based search recommendation method according to another embodiment of the present invention, where the method of the present embodiment is implemented based on the scenario-based category preference data generation method in the above-mentioned embodiments, that is, the method according to the first two embodiments may generate category preference data in a user search scenario, and the method of the present embodiment applies the category preference data in the user search scenario to perform search recommendation. As shown in fig. 3, the method includes:
In step S301, user behavior real-time data related to the search behavior is received, where the user behavior real-time data includes user behavior scene real-time data.
The application scenario of the present embodiment is a real-time search scenario. In order to distinguish the above-mentioned historical search behaviors, the search behaviors of the real-time search scene in this embodiment are referred to as real-time search behaviors, and when the user searches, user behavior real-time data related to the real-time search behaviors is received, including user behavior scene real-time data, such as time data, location data and/or search terms.
Step S302, inquiring user real-time searching scene data matched with the user behavior scene real-time data.
The purpose of this step is to identify a user real-time search scenario from the user behavior scenario real-time data. Specifically, a time period label, a position label and/or a search intention label in a user search scene are obtained according to time data, position data and/or search words. Referring to the description of the above embodiment, the period to which the time data corresponding to the real-time search behavior belongs is identified, the period label of the real-time search behavior is determined, the location to which the location data corresponding to the real-time search behavior belongs is identified, the location label of the real-time search behavior is determined, and/or the search intention is identified according to the search word corresponding to the real-time search behavior, so as to obtain the search intention label of the real-time search behavior. The specific meaning of the time slot label, the location label and the search intention label are described in the above embodiments, and are not described herein. Specifically, for the decision period label, when the real-time search scene is identified, whether the decision period is in the decision period is determined according to the distance between the search place and the current place, if the distance exceeds the preset threshold value, the decision period is determined, otherwise, the decision period is not in the decision period, and therefore whether the decision period label is determined.
Step S303, inquiring category preference data corresponding to the user real-time searching scene data stored offline.
The step determines category preference data in a real-time search scenario. For example, a user searching breakfast in a writing building at seven points in the morning, and receiving user behavior scene real-time data related to real-time searching behavior includes: the time data- "seven points in the morning", the position data- "office building" and the search word "nearby" are processed by the scene recognition in step S302, so that the user real-time search scene data includes "breakfast time period tag+office building tag+entity intention tag". Then, searching the category preference data in the user search scene containing breakfast time period label, office building label and entity intention label in the category preference data stored offline.
Further, when the category preference data with different priorities is stored offline, the category preference data with the highest priority corresponding to the user real-time search scene data in the category preference data with different priorities in the user search scene stored offline is queried during query. The user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
That is, the category preference data of the user search scene having the highest priority is searched first, if the category preference data corresponding to the real-time search scene is not searched, the category preference data of the user search scene having the next level of priority is searched, and if the category preference data of the user search scene having the next level of priority is still not searched. The search ranking is performed by taking the category preference data of the user search scene with the highest priority as far as possible, because the category preference data is more matched with the real scene where the user is located, the effect of search recommendation can be improved, and the category preference data of the user search scene with lower priority is used for preventing the category preference data from being empty caused by data sparseness.
Along with the above example, if the real-time search scene data is "breakfast time period tag+office building tag+entity intention tag", the user searches for the category preference data corresponding to "breakfast time period tag+office building tag+entity intention tag", if the search is not successful, searches for the category preference data corresponding to "breakfast time period tag+office building tag", and if the search is not successful, continues to search for the category preference data of "breakfast time period tag".
And step S304, recommending search results according to the category preference data.
From the above, it can be seen that the category preference data in the search scene is substantially that the user searches for the category preference score of each category in the scene, and then makes a search result recommendation according to the category preference score of each category. That is, the category preference data is used as a ranking factor for search result recommendation.
For example, the ranking score for a category is increased for a category with a higher search category preference score, and the ranking score for a category is decreased appropriately for a category with a lower category preference score. An alternative embodiment is: the initial sorting score of each category is preset, and the sorting score of each category is calculated according to the category preference score of each category and the initial sorting score of each category in the real-time search scene. And finally, sorting the search results according to the sorting scores of the categories. In practical applications, the category preference data may be used as a unique ranking factor, or may be used as one of ranking factors, which is not limited in the present invention.
Step S305 returns the recommended search results to the client for the client to display.
And returning the recommended search results to the client, and displaying the recommended search results by the client.
According to the scene-based search recommendation method provided by the embodiment, the real-time search scene of the user is identified by combining the information of three dimensions of time, space and search intention, and search ranking is performed according to category preference data corresponding to the real-time search scene of the user, so that search recommendation combined with the search scene is realized, and the effect of search recommendation can be improved.
The method according to the embodiment of the present invention is described below with reference to a specific scenario, and fig. 4 is a schematic flow diagram of a scenario-based search recommendation process according to another embodiment of the present invention, where, as shown in fig. 4, the specific flow includes:
the first step, when a user initiates a search, acquiring real-time data of a user behavior scene related to the user search behavior, including: location data, time data, and search terms. In this example, the location data includes: the method comprises the steps that longitude and latitude information reported by a client side and WiFi information connected with user equipment during user searching are stored in a storage device, time data refer to searching time during user searching, and search words refer to queries input during user searching.
And secondly, understanding of a user search scene based on the user real-time behavior scene data.
In one aspect, the geographic location is understood. The method specifically comprises the following steps: and identifying longitude and latitude information based on the POI engine, and identifying WiFi information connected with the user equipment by utilizing a WiFi identification model to obtain information such as names, types and the like of the positions of the users, wherein the POI engine refers to an engine related to geographic position information, such as an engine of a map website or an engine of a map APP, and the WiFi identification model is an identification model constructed based on a WiFi positioning technology. The identified location information is then labeled to obtain a geographical location understanding result, "located city" shown in fig. 4: beijing city; the area where: a shopping mall is geographical location information of a user, and the type of a region where the shopping mall is located is: the business district/mall "is a geographic location tag.
On the other hand, time understanding. The method specifically comprises the following steps: determining which time period the user search time belongs to based on the five-degree time-stepping rule, and determining whether the user search time is a workday, thereby determining a time stamp, that is, "time period" shown in fig. 4: time for tea setting; whether it is a working day: and no (2).
In yet another aspect, intent recognition. The method specifically comprises the following steps: and carrying out understanding recognition on the user search query by utilizing the query understanding model and the store arrival recognition model, and determining whether the user is in a decision stage or a store arrival consumption stage to obtain an intention understanding result, wherein the intention understanding result shown in fig. 4 is represented by: the search term of the user is a hot pot, in a decision period and the search intention is a category intention.
And thirdly, searching for category preference matched with the user real-time searching scene according to the user real-time searching scene inquiry scene understanding engine, wherein the scene understanding engine is used for generating category preference data and storing the category preference data. The category preferences matching the search scenario of location (Beijing city, shopping mall A, mall/mall) +time (afternoon tea time, non-workday) +search intention (chafing dish, decision period, category intention) are found: sichuan chafing dish and chafing dish string.
And step four, recommending the search result, namely floating up the shop which hits the preference category, namely arranging the shop which is classified as Sichuan chafing dish and chafing dish string at the front position in the search result.
And fifthly, returning the recommended search results to the client, and displaying the search results by the client. Thus, the whole process of search recommendation based on the user search scene is completed.
Fig. 5 shows a functional block diagram of a scene-based category preference data generating apparatus according to still another embodiment of the present invention, as shown in fig. 5, the apparatus includes:
the acquisition module 51 is adapted to acquire user behavior history data related to the search behavior, wherein the user behavior history data comprises user behavior scene history data and corresponding user behavior target entity history data;
the scene recognition module 52 is adapted to perform scene recognition processing according to the user behavior scene history data to obtain user search scene data;
the data analysis module 53 is adapted to determine category data and behavior preference data corresponding to the user behavior target entity according to the user behavior target entity history data;
the scene preference analysis module 54 is adapted to generate category preference data in the user search scene according to the user search scene data, the category data and the behavior preference data, and to store the generated category preference data offline.
Optionally, the user behavior scene history data includes: time data, location data, and/or search terms;
the scene recognition module 52 is further adapted to: and obtaining a time period label, a position label and/or a search intention label in the user search scene according to the time data, the position data and/or the search word.
Optionally, the period label comprises: a plurality of time period grading tags, a workday time period tag, and/or a veto decision time period tag; the position tag includes: a plurality of location type tags, whether a location is resident tags, and/or a distance tag of a search location from a current location; the search intention label includes: entity intent tags, category intent tags, address intent tags, and/or content intent tags.
Optionally, the user behavior target entity history data includes: user browsing behavior data and user consumption behavior data of the target entity related to the search behavior;
the behavior preference data includes: and the user browses the behavior data and the data quantity of the user consumption behavior data.
Optionally, the scene preference analysis module 54 is further adapted to: generating category preference data under the user search scenes with different priorities according to the user search scene data, the category data and the behavior preference data;
the user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
Optionally, the apparatus further comprises:
and the aggregation processing module is suitable for carrying out aggregation processing on the user search scene data and screening out the user search scene data of which the data quantity is smaller than a preset data quantity threshold value.
Fig. 6 is a functional block diagram of a scene-based search recommendation apparatus according to another embodiment of the present invention, as shown in fig. 6, the apparatus comprising:
the receiving module 61 is adapted to receive user behavior real-time data related to the search behavior, the user behavior real-time data comprising user behavior scene real-time data;
the matching module 62 is adapted to query the user real-time search scene data matched with the user behavior scene real-time data;
the query module 63 is adapted to query offline stored category preference data corresponding to the user's real-time search scene data;
a search recommendation module 64 adapted to make search result recommendations based on category preference data;
the return module 65 is adapted to return the recommended search results to the client for the client to present the search results.
Optionally, the user behavior scene real-time data includes: time data, location data, and/or search terms;
the matching module 62 is further adapted to: and obtaining a time period label, a position label and/or a search intention label of the user in a real-time search scene according to the time data, the position data and/or the search word.
Optionally, the query module 63 is further adapted to:
inquiring category preference data under the user search scene with highest priority corresponding to the user real-time search scene data in category preference data under the user search scenes with different priorities stored offline;
the user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
Optionally, the search recommendation module 64 is further adapted to:
and recommending the search results by taking the category preference data as a ranking factor.
Embodiments of the present application provide a non-volatile computer storage medium storing at least one executable instruction that may perform the method for generating scene-based category preference data in any of the method embodiments described above.
Embodiments of the present application provide a non-volatile computer storage medium storing at least one executable instruction that may perform the scene-based search recommendation method in any of the method embodiments described above.
FIG. 7 illustrates a schematic diagram of a computing device, according to an embodiment of the invention, the particular embodiment of the invention not being limited to a particular implementation of the computing device.
As shown in fig. 7, the computing device may include: a processor 702, a communication interface (Communications Interface), a memory 706, and a communication bus 708.
Wherein:
processor 702, communication interface 704, and memory 706 perform communication with each other via a communication bus 708.
A communication interface 704 for communicating with network elements of other devices, such as clients or other servers.
The processor 702 is configured to execute the program 710, and may specifically perform relevant steps in the above-described embodiment of the method for generating scene-based category preference data.
In particular, program 710 may include program code including computer-operating instructions.
The processor 702 may be a Central Processing Unit (CPU), or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included by the computing device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 706 for storing programs 710. The memory 706 may comprise high-speed RAM memory or may further comprise non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 710 may be specifically configured to cause the processor 702 to: collecting user behavior historical data related to search behaviors, wherein the user behavior historical data comprises user behavior scene historical data and corresponding user behavior target entity historical data;
performing scene recognition processing according to the user behavior scene history data to obtain user search scene data;
according to the historical data of the user behavior target entity, determining category data and behavior preference data corresponding to the user behavior target entity;
and generating category preference data under the user search scene according to the user search scene data, the category data and the behavior preference data, and storing offline.
In an alternative way, the user behavior scene history data includes: time data, location data, and/or search terms;
the program 710 may also be specifically operable to cause the processor 702 to: and obtaining a time period label, a position label and/or a search intention label in the user search scene according to the time data, the position data and/or the search word.
In an alternative way, the period label comprises: a plurality of time period grading tags, a workday time period tag, and/or a veto decision time period tag; the position tag includes: a plurality of location type tags, whether a location is resident tags, and/or a distance tag of a search location from a current location; the search intention label includes: entity intent tags, category intent tags, address intent tags, and/or content intent tags.
In an alternative way, the user behavior target entity history data includes: user browsing behavior data and user consumption behavior data of the target entity related to the search behavior; the behavior preference data includes: the user browses the behavior data and the data amount of the user consumption behavior data.
In an alternative, the program 710 may be further operable to cause the processor 702 to: generating category preference data under the user search scenes with different priorities according to the user search scene data, the category data and the behavior preference data; the user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
The program 710 may also be specifically operable to cause the processor 702 to: and after obtaining the user search scene data, carrying out aggregation processing on the user search scene data, and screening out the user search scene data with the data quantity smaller than a preset data quantity threshold value.
FIG. 8 illustrates a schematic diagram of a computing device, according to an embodiment of the invention, the particular embodiment of the invention not being limited to a particular implementation of the computing device.
As shown in fig. 8, the computing device may include: a processor (processor) 802, a communication interface (Communications Interface) 804, a memory (memory) 806, and a communication bus 808.
Wherein:
processor 802, communication interface 804, and memory 806 communicate with each other via a communication bus 808.
A communication interface 804 for communicating with network elements of other devices, such as clients or other servers.
The processor 802 is configured to execute the program 810, and may specifically perform relevant steps in the above-described embodiment of the scenario-based search recommendation method.
In particular, program 810 may include program code including computer operating instructions.
The processor 802 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included by the computing device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 806 for storing a program 810. The memory 806 may include high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 810 may be specifically operable to cause the processor 802 to:
receiving user behavior real-time data related to search behaviors, wherein the user behavior real-time data comprises user behavior scene real-time data;
inquiring user real-time searching scene data matched with the user behavior scene real-time data;
inquiring category preference data which is stored offline and corresponds to the user real-time searching scene data;
recommending search results according to category preference data;
and returning the recommended search results to the client so that the client can display the search results.
In an alternative way, the user behavior scene real-time data includes: time data, location data, and/or search terms; the program 810 may also be used to cause the processor 802 to: and obtaining a time period label, a position label and/or a search intention label of the user in a real-time search scene according to the time data, the position data and/or the search word.
In an alternative, the program 810 may also be used, in particular, to cause the processor 802 to: inquiring category preference data under the user search scene with highest priority corresponding to the user real-time search scene data in category preference data under the user search scenes with different priorities stored offline;
The user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
In an alternative, the program 810 may also be used, in particular, to cause the processor 802 to: and recommending the search results by taking the category preference data as a ranking factor.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, the present invention is not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components in a computing device according to embodiments of the invention may be implemented in practice using microprocessors or Digital Signal Processors (DSPs). The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.
Claims (18)
1. A scene-based category preference data generation method, comprising:
collecting user behavior historical data related to search behaviors, wherein the user behavior historical data comprises user behavior scene historical data and corresponding user behavior target entity historical data;
Performing scene recognition processing according to the user behavior scene history data to obtain user search scene data;
according to the historical data of the user behavior target entity, determining category data and behavior preference data corresponding to the user behavior target entity;
generating category preference data under a user search scene according to the user search scene data, the category data and the behavior preference data, and storing offline;
wherein, the user behavior scene history data comprises: time data, location data, and/or search terms;
the scene recognition processing is performed according to the user behavior scene history data, and obtaining the user search scene data further comprises:
obtaining a time period label, a position label and/or a search intention label in a user search scene according to the time data, the position data and/or the search word; wherein,
the time period tag includes: a plurality of time period grading tags, a workday time period tag, and/or a veto decision time period tag;
the location tag includes: a plurality of location type tags, whether a location is resident tags, and/or a distance tag of a search location from a current location;
the search intention tag includes: entity intent tags, category intent tags, address intent tags, and/or content intent tags.
2. The method of claim 1, wherein the user behavior target entity history data comprises: user browsing behavior data and user consumption behavior data of the target entity related to the search behavior;
the behavior preference data includes: and the user browses the behavior data and the data quantity of the user consumption behavior data.
3. The method of claim 1, wherein the generating category preference data in the user search context from the user search context data, the category data, and the behavior preference data further comprises:
generating category preference data under the user search scenes with different priorities according to the user search scene data, the category data and the behavior preference data;
the user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
4. The method of claim 1, wherein after the obtaining the user search context data, the method further comprises:
And carrying out aggregation processing on the user search scene data, and screening out the user search scene data of which the data quantity is smaller than a preset data quantity threshold value.
5. A scene-based search recommendation method, comprising:
receiving user behavior real-time data related to search behaviors, wherein the user behavior real-time data comprises user behavior scene real-time data;
inquiring user real-time searching scene data matched with the user behavior scene real-time data;
inquiring category preference data which is stored offline and corresponds to the user real-time searching scene data;
recommending search results according to the category preference data;
returning recommended search results to the client so that the client can display the search results;
wherein, the user behavior scene real-time data comprises: time data, location data, and/or search terms;
the querying the user real-time search scene data matched with the user behavior scene real-time data further comprises:
obtaining a time period label, a position label and/or a search intention label of a user in a real-time search scene according to the time data, the position data and/or the search word; wherein,
the time period tag includes: a plurality of time period grading tags, a workday time period tag, and/or a veto decision time period tag;
The location tag includes: a plurality of location type tags, whether a location is resident tags, and/or a distance tag of a search location from a current location;
the search intention tag includes: entity intent tags, category intent tags, address intent tags, and/or content intent tags.
6. The method of claim 5, wherein querying category preference data stored offline corresponding to user real-time search context data specifically comprises:
inquiring category preference data under the user search scene with highest priority corresponding to the user real-time search scene data in category preference data under the user search scenes with different priorities stored offline;
the user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
7. The method of claim 5, wherein the search result recommendation based on the category preference data specifically comprises:
and recommending the search results by taking the category preference data as a ranking factor.
8. A scene-based category preference data generating apparatus comprising:
the acquisition module is suitable for acquiring user behavior historical data related to search behaviors, wherein the user behavior historical data comprises user behavior scene historical data and corresponding user behavior target entity historical data;
the scene recognition module is suitable for performing scene recognition processing according to the user behavior scene history data to obtain user search scene data;
the data analysis module is suitable for determining category data and behavior preference data corresponding to the user behavior target entity according to the user behavior target entity history data;
the scene preference analysis module is suitable for generating category preference data in a user search scene according to the user search scene data, the category data and the behavior preference data and storing the category preference data offline;
wherein, the user behavior scene history data comprises: time data, location data, and/or search terms;
the scene recognition module is further adapted to: obtaining a time period label, a position label and/or a search intention label in a user search scene according to the time data, the position data and/or the search word; wherein,
the time period tag includes: a plurality of time period grading tags, a workday time period tag, and/or a veto decision time period tag;
The location tag includes: a plurality of location type tags, whether a location is resident tags, and/or a distance tag of a search location from a current location;
the search intention tag includes: entity intent tags, category intent tags, address intent tags, and/or content intent tags.
9. The apparatus of claim 8, wherein the user behavior target entity history data comprises: user browsing behavior data and user consumption behavior data of the target entity related to the search behavior;
the behavior preference data includes: and the user browses the behavior data and the data quantity of the user consumption behavior data.
10. The apparatus of claim 8, wherein the scene preference analysis module is further adapted to: generating category preference data under the user search scenes with different priorities according to the user search scene data, the category data and the behavior preference data;
the user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
11. The apparatus of claim 8, wherein the apparatus further comprises:
and the aggregation processing module is suitable for carrying out aggregation processing on the user search scene data and screening out the user search scene data of which the data quantity is smaller than a preset data quantity threshold value.
12. A scene-based search recommendation apparatus, comprising:
the receiving module is suitable for receiving user behavior real-time data related to search behaviors, and the user behavior real-time data comprises user behavior scene real-time data;
the matching module is suitable for inquiring the user real-time searching scene data matched with the user behavior scene real-time data;
the query module is suitable for querying category preference data which is stored offline and corresponds to the user real-time search scene data;
the search recommendation module is suitable for recommending search results according to the category preference data;
the return module is suitable for returning recommended search results to the client so that the client can display the search results;
wherein, the user behavior scene real-time data comprises: time data, location data, and/or search terms;
the matching module is further adapted to: obtaining a time period label, a position label and/or a search intention label of a user in a real-time search scene according to the time data, the position data and/or the search word; wherein,
The time period tag includes: a plurality of time period grading tags, a workday time period tag, and/or a veto decision time period tag;
the location tag includes: a plurality of location type tags, whether a location is resident tags, and/or a distance tag of a search location from a current location;
the search intention tag includes: entity intent tags, category intent tags, address intent tags, and/or content intent tags.
13. The apparatus of claim 12, wherein the query module is further adapted to:
inquiring category preference data under the user search scene with highest priority corresponding to the user real-time search scene data in category preference data under the user search scenes with different priorities stored offline;
the user searching scene is as follows according to the order of priority from high to low: a user search scenario comprising a search intent tag, a period tag, a location tag, a user search scenario comprising a period tag and a location tag, a user search scenario comprising a period tag.
14. The apparatus of claim 12, wherein the search recommendation module is further adapted to:
and recommending the search results by taking the category preference data as a ranking factor.
15. A computing device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to the scenario-based category preference data generation method of any one of claims 1-4.
16. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the scene-based category preference data generating method of any one of claims 1-4.
17. A computing device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to the scenario-based search recommendation method according to any one of claims 5-7.
18. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the scene-based search recommendation method of any one of claims 5-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911128690.8A CN111080339B (en) | 2019-11-18 | 2019-11-18 | Scene-based category preference data generation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911128690.8A CN111080339B (en) | 2019-11-18 | 2019-11-18 | Scene-based category preference data generation method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111080339A CN111080339A (en) | 2020-04-28 |
CN111080339B true CN111080339B (en) | 2024-01-30 |
Family
ID=70311215
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911128690.8A Active CN111080339B (en) | 2019-11-18 | 2019-11-18 | Scene-based category preference data generation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111080339B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111737574B (en) * | 2020-06-19 | 2024-01-26 | 口口相传(北京)网络技术有限公司 | Search information acquisition method, apparatus, computer device and readable storage medium |
CN111914133A (en) * | 2020-07-02 | 2020-11-10 | 海信视像科技股份有限公司 | Electronic equipment and query statement processing method |
CN112541123A (en) * | 2020-12-24 | 2021-03-23 | 北京百度网讯科技有限公司 | Map region recommendation method, device, equipment and storage medium |
CN113034319A (en) * | 2020-12-24 | 2021-06-25 | 广东国粒教育技术有限公司 | User behavior data processing method and device in teaching management, electronic equipment and storage medium |
CN113609375A (en) * | 2021-06-21 | 2021-11-05 | 青岛海尔科技有限公司 | Content recommendation method and device, storage medium and electronic device |
Citations (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013025813A2 (en) * | 2011-08-16 | 2013-02-21 | Alibaba Group Holding Limited | Recommending content information based on user behavior |
CN102982066A (en) * | 2011-10-12 | 2013-03-20 | 微软公司 | Search result presenting gathering place endorsement |
JP2014203442A (en) * | 2013-04-10 | 2014-10-27 | 株式会社Nttドコモ | Recommendation information generation device and recommendation information generation method |
CN105320706A (en) * | 2014-08-05 | 2016-02-10 | 阿里巴巴集团控股有限公司 | Processing method and device of search result |
CN106095842A (en) * | 2016-06-01 | 2016-11-09 | 腾讯科技(深圳)有限公司 | Online course searching method and device |
CN106447371A (en) * | 2015-08-10 | 2017-02-22 | 北京奇虎科技有限公司 | Webpage advertisement recommendation method and device |
CN106528812A (en) * | 2016-08-05 | 2017-03-22 | 浙江工业大学 | USDR model based cloud recommendation method |
CN106776860A (en) * | 2016-11-28 | 2017-05-31 | 北京三快在线科技有限公司 | One kind search abstraction generating method and device |
WO2017193323A1 (en) * | 2016-05-12 | 2017-11-16 | 深圳大学 | User preference-based personalized recommendation method and system utilizing same |
CN107423308A (en) * | 2016-05-24 | 2017-12-01 | 华为技术有限公司 | subject recommending method and device |
CN107870984A (en) * | 2017-10-11 | 2018-04-03 | 北京京东尚科信息技术有限公司 | The method and apparatus for identifying the intention of search term |
CN108198019A (en) * | 2017-12-27 | 2018-06-22 | 网易无尾熊(杭州)科技有限公司 | Item recommendation method and device, storage medium, electronic equipment |
WO2018113468A1 (en) * | 2016-12-23 | 2018-06-28 | 北京奇虎科技有限公司 | Search term recommendation method, device, program and medium |
CN108416649A (en) * | 2018-02-05 | 2018-08-17 | 北京三快在线科技有限公司 | Search result ordering method, device, electronic equipment and storage medium |
CN109064278A (en) * | 2018-07-26 | 2018-12-21 | 北京三快在线科技有限公司 | Target object recommended method and device, electronic equipment, storage medium |
CN109214418A (en) * | 2018-07-25 | 2019-01-15 | 百度在线网络技术(北京)有限公司 | The method for digging and device, computer equipment and readable medium that user is intended to |
WO2019015262A1 (en) * | 2017-07-20 | 2019-01-24 | 北京三快在线科技有限公司 | Information search method, apparatus and system |
CN109299994A (en) * | 2018-07-27 | 2019-02-01 | 北京三快在线科技有限公司 | Recommended method, device, equipment and readable storage medium storing program for executing |
CN110020148A (en) * | 2017-11-29 | 2019-07-16 | 北京搜狗科技发展有限公司 | A kind of information recommendation method, device and the device for information recommendation |
CN110020128A (en) * | 2017-10-26 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of search result ordering method and device |
CN110175895A (en) * | 2019-05-31 | 2019-08-27 | 京东方科技集团股份有限公司 | A kind of item recommendation method and device |
CN110363570A (en) * | 2019-06-19 | 2019-10-22 | 北京三快在线科技有限公司 | Classification methods of exhibiting, device, electronic equipment and storage medium in |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6895406B2 (en) * | 2000-08-25 | 2005-05-17 | Seaseer R&D, Llc | Dynamic personalization method of creating personalized user profiles for searching a database of information |
US20080005069A1 (en) * | 2006-06-28 | 2008-01-03 | Microsoft Corporation | Entity-specific search model |
US9152726B2 (en) * | 2010-12-01 | 2015-10-06 | Microsoft Technology Licensing, Llc | Real-time personalized recommendation of location-related entities |
US20130080423A1 (en) * | 2011-09-23 | 2013-03-28 | Ebay Inc. | Recommendations for search queries |
JP5785869B2 (en) * | 2011-12-22 | 2015-09-30 | 株式会社日立製作所 | Behavior attribute analysis program and apparatus |
CN104112009B (en) * | 2014-07-17 | 2017-11-17 | 华为技术有限公司 | The method and apparatus of data processing |
US10698966B2 (en) * | 2017-05-18 | 2020-06-30 | International Business Machines Corporation | Search result prioritization based on device location |
-
2019
- 2019-11-18 CN CN201911128690.8A patent/CN111080339B/en active Active
Patent Citations (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013025813A2 (en) * | 2011-08-16 | 2013-02-21 | Alibaba Group Holding Limited | Recommending content information based on user behavior |
CN102982066A (en) * | 2011-10-12 | 2013-03-20 | 微软公司 | Search result presenting gathering place endorsement |
JP2014203442A (en) * | 2013-04-10 | 2014-10-27 | 株式会社Nttドコモ | Recommendation information generation device and recommendation information generation method |
CN105320706A (en) * | 2014-08-05 | 2016-02-10 | 阿里巴巴集团控股有限公司 | Processing method and device of search result |
CN106447371A (en) * | 2015-08-10 | 2017-02-22 | 北京奇虎科技有限公司 | Webpage advertisement recommendation method and device |
WO2017193323A1 (en) * | 2016-05-12 | 2017-11-16 | 深圳大学 | User preference-based personalized recommendation method and system utilizing same |
CN107423308A (en) * | 2016-05-24 | 2017-12-01 | 华为技术有限公司 | subject recommending method and device |
CN106095842A (en) * | 2016-06-01 | 2016-11-09 | 腾讯科技(深圳)有限公司 | Online course searching method and device |
CN106528812A (en) * | 2016-08-05 | 2017-03-22 | 浙江工业大学 | USDR model based cloud recommendation method |
CN106776860A (en) * | 2016-11-28 | 2017-05-31 | 北京三快在线科技有限公司 | One kind search abstraction generating method and device |
WO2018113468A1 (en) * | 2016-12-23 | 2018-06-28 | 北京奇虎科技有限公司 | Search term recommendation method, device, program and medium |
WO2019015262A1 (en) * | 2017-07-20 | 2019-01-24 | 北京三快在线科技有限公司 | Information search method, apparatus and system |
CN107870984A (en) * | 2017-10-11 | 2018-04-03 | 北京京东尚科信息技术有限公司 | The method and apparatus for identifying the intention of search term |
CN110020128A (en) * | 2017-10-26 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of search result ordering method and device |
CN110020148A (en) * | 2017-11-29 | 2019-07-16 | 北京搜狗科技发展有限公司 | A kind of information recommendation method, device and the device for information recommendation |
CN108198019A (en) * | 2017-12-27 | 2018-06-22 | 网易无尾熊(杭州)科技有限公司 | Item recommendation method and device, storage medium, electronic equipment |
CN108416649A (en) * | 2018-02-05 | 2018-08-17 | 北京三快在线科技有限公司 | Search result ordering method, device, electronic equipment and storage medium |
CN109214418A (en) * | 2018-07-25 | 2019-01-15 | 百度在线网络技术(北京)有限公司 | The method for digging and device, computer equipment and readable medium that user is intended to |
CN109064278A (en) * | 2018-07-26 | 2018-12-21 | 北京三快在线科技有限公司 | Target object recommended method and device, electronic equipment, storage medium |
CN109299994A (en) * | 2018-07-27 | 2019-02-01 | 北京三快在线科技有限公司 | Recommended method, device, equipment and readable storage medium storing program for executing |
CN110175895A (en) * | 2019-05-31 | 2019-08-27 | 京东方科技集团股份有限公司 | A kind of item recommendation method and device |
CN110363570A (en) * | 2019-06-19 | 2019-10-22 | 北京三快在线科技有限公司 | Classification methods of exhibiting, device, electronic equipment and storage medium in |
Non-Patent Citations (4)
Title |
---|
元搜索引擎的个性化;李晓红;冯志勇;张亮;;天津大学学报;第41卷(第05期);第616-620页 * |
基于标签的商品推荐模型研究;涂海丽;唐晓波;;数据分析与知识发现(第09期);第28-37页 * |
基于浏览偏好挖掘的实时商品推荐方法;谢意;陈德人;干红华;;计算机应用;第31卷(第01期);第89-92页 * |
基于用户查询意图的搜索排序算法;张美珍;王治莹;;天津理工大学学报;第28卷(第03期);第46-51页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111080339A (en) | 2020-04-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111080339B (en) | Scene-based category preference data generation method and device | |
CN105989004B (en) | Information delivery preprocessing method and device | |
CN108596695B (en) | Entity pushing method and system | |
JP5596152B2 (en) | Information matching method and system on electronic commerce website | |
JP5405665B2 (en) | System and method for adding advertisements to a location-based advertising system | |
CN110413877A (en) | A kind of resource recommendation method, device and electronic equipment | |
CN102142003B (en) | Method and device for providing point of interest information | |
US20160171587A1 (en) | Methods and systems for selecting an optimized scoring function for use in ranking item listings presented in search results | |
US8412591B2 (en) | Systems and methods for online matching of consumers and retailers | |
US20080243797A1 (en) | Method and system of selecting landing page for keyword advertisement | |
CN108280749B (en) | Method and device for displaying service function entry | |
CN110322277A (en) | Product information methods of exhibiting and device, electronic equipment | |
CN102314654B (en) | A kind of information-pushing method and Information Push Server | |
CN102024041A (en) | Searching method and system used for electronic commerce | |
CN107679103B (en) | Attribute analysis method and system for entity | |
CN108429776B (en) | Network object pushing method, device, client, interaction equipment and system | |
KR20180052489A (en) | method of providing goods recommendation for cross-border E-commerce based on user experience analysis and environmental factors | |
CN109388756A (en) | Information recommendation method and device | |
US20230237511A1 (en) | Alcohol information management system and management method | |
CN110969512A (en) | Commodity recommendation method and device based on user purchasing behavior | |
CN109241455B (en) | Recommended object display method and device | |
CN106547365A (en) | The method and apparatus of commercial product recommending | |
US20130132431A1 (en) | Proximity Alert System | |
CN103136250B (en) | Change dump recognition methods, device and information search method, system | |
CN104063437B (en) | A kind of information on services issue and searcher and method based on electronic map |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |