CN111639266A - Recommendation information generation method and device, electronic equipment and readable storage medium - Google Patents

Recommendation information generation method and device, electronic equipment and readable storage medium Download PDF

Info

Publication number
CN111639266A
CN111639266A CN202010301661.3A CN202010301661A CN111639266A CN 111639266 A CN111639266 A CN 111639266A CN 202010301661 A CN202010301661 A CN 202010301661A CN 111639266 A CN111639266 A CN 111639266A
Authority
CN
China
Prior art keywords
paths
node
user
path
recommendation information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010301661.3A
Other languages
Chinese (zh)
Inventor
杨玉基
王倩舒
张梦迪
张富峥
王仲远
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sankuai Online Technology Co Ltd
Original Assignee
Beijing Sankuai Online Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Sankuai Online Technology Co Ltd filed Critical Beijing Sankuai Online Technology Co Ltd
Priority to CN202010301661.3A priority Critical patent/CN111639266A/en
Publication of CN111639266A publication Critical patent/CN111639266A/en
Priority to PCT/CN2021/076510 priority patent/WO2021208583A1/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/55—Push-based network services

Abstract

The embodiment of the application provides a recommendation information generation method and device, electronic equipment and a readable storage medium. The method comprises the following steps: according to the user identification, the object identification and the correlation relationship among the situation attribute parameters, a first node comprising the situation attribute parameters, a second node comprising the user identification and a plurality of paths comprising a third node comprising the object identification are determined, the paths are grouped according to various sub-parameter values and the third node of the first node on the paths to obtain a plurality of groups of paths, and the recommendation information of the object to be recommended is generated according to the respective path attribute values of the paths.

Description

Recommendation information generation method and device, electronic equipment and readable storage medium
Technical Field
The embodiment of the application relates to the technical field of data processing, in particular to a recommendation information generation method and device, an electronic device and a readable storage medium.
Background
With the development of internet technology, a user frequently selects an article on the internet, and under a common condition, a system recommends the article to the user for help selection. The existing recommendation information generation methods can be roughly divided into the following categories:
based on the user comment. High quality comment text is mined from a large number of comments made by the user on the item and then recommended to the user. For example, "Dongyinggong Tang is good for drinking.
Based on social relationships. And mining the preference degree of the social network of the current user for the item according to the social network and the behavior of the current user. For example, "6 your friends like the store".
Based on user similarity. And recommending according to the preference of other users similar to the current user. For example, "you may like this store because users similar to you like this store".
Based on item similarity. And recommending according to the similarity between the item set preferred by the current user and the current item. For example, "you may like this store because you have been going to a store similar to this store multiple times.
The recommendation information based on the user comments is relatively direct and common, the comments of other users have relatively high reference value for the current user decision, and the user tends to comprehensively compare the comments of a plurality of users. However, in the recommendation reason scene, the information amount of a single user comment is limited, and the surprise and the bright spot are not prominent enough. The problem with recommendation information based on social relationships, based on user similarity, and based on item similarity is that descriptions are too single and often appear to bring a sense of fatigue to the user.
Therefore, the recommendation information generation method in the prior art needs to be improved.
Disclosure of Invention
The embodiment of the application provides a recommendation information generation method and device, electronic equipment and a readable storage medium, and aims to provide recommendation information which is rich, strong in reference and strong in attraction for a user.
A first aspect of an embodiment of the present application provides a recommendation information generation method, where the method includes:
determining a plurality of paths including a first node of the situation attribute parameters, a second node of the user identifiers and a third node of the object identifiers according to the association relation among the user identifiers, the object identifiers and the situation attribute parameters;
grouping the multiple paths according to the sub-parameter values and the third nodes included in the first node on the multiple paths to obtain multiple groups of paths, wherein each sub-path included in one group of paths corresponds to the same sub-parameter value and the same object identifier;
and generating recommendation information of the object to be recommended according to the respective path attribute values of the multiple groups of paths.
Optionally, the path attribute value comprises a traffic parameter value; the flow parameter value of any one of the multiple groups of paths is determined according to the following steps:
determining the flow parameter value of each sub-path included in the group of paths, wherein the flow parameter value of one sub-path is determined according to the flow transfer value between every two nodes on the path, and the flow transfer value between the two nodes is determined according to the degree of departure of a first node in the two nodes;
and determining the flow parameter value of the group of paths according to the flow parameter value of each sub-path included in the group of paths.
Optionally, the path attribute value comprises a preference; the preference degree of any one group of paths in the multiple groups of paths is determined according to the following steps:
determining the preference degree of the group of paths according to the respective flow parameter values of the plurality of groups of paths corresponding to the same object identifier of the group of paths, the group number of the plurality of groups of paths corresponding to the same object identifier of the group of paths and the flow parameter values of the group of paths; or
And determining the preference degree of the group of paths according to the number of the user identifications on the group of paths and the total number of the user identifications on the plurality of groups of paths corresponding to the same object identification.
Optionally, generating recommendation information of the object to be recommended according to the respective path attribute values of the multiple groups of paths, where the generating recommendation information includes:
determining a target group path with a path attribute value larger than a preset threshold value from the multiple groups of paths corresponding to the same object identifier;
determining an object represented by the same object identifier corresponding to each sub-path in the target group path as an object to be recommended;
and generating recommendation information of the object to be recommended according to the same sub-parameter value corresponding to each sub-path in the target group of paths.
Optionally, a single path of the plurality of paths further includes intermediate nodes of other parameters; generating recommendation information of the object to be recommended according to the same sub-parameter value corresponding to each sub-path in the target group of paths, wherein the recommendation information comprises:
determining a target node label according to the node labels of at least one intermediate node on each sub-path in the target group path;
and generating recommendation information of the object to be recommended, wherein the label carried by the recommendation information is the target node label and/or the object label of the object to be recommended.
Optionally, determining, according to the user identifier, the object identifier, and the correlation relationship among the context attribute parameters, a plurality of paths including a first node including the context attribute parameter, a second node including the user identifier, and a third node including the object identifier, including:
determining a first node, a second node and a third node from a preset knowledge graph;
and traversing the preset knowledge graph according to the first node, the second node and the third node to obtain the plurality of paths.
Optionally, the association relationship between the user identifier, the object identifier, and the context attribute parameter is determined according to the following steps:
determining a preset operation relationship between a user identifier and an object identifier according to historical behavior data of the user, wherein the preset operation is at least one of ordering operation, browsing operation and clicking operation;
determining a first corresponding relation between the user identification and the situation attribute parameter according to the user attribute information, or determining a second corresponding relation between the object identification and the situation attribute parameter according to the object attribute information;
the preset operation relationship and the first corresponding relationship form the incidence relationship, or the preset operation relationship and the second corresponding relationship form the incidence relationship;
the context attribute parameters include at least one of: location parameters, time parameters, tag parameters.
Optionally, determining, according to the user identifier, the object identifier, and the correlation relationship among the context attribute parameters, a plurality of paths including a first node including the context attribute parameter, a second node including the user identifier, and a third node including the object identifier, including:
determining an identification set meeting a preset label according to the preset label, wherein the identification in the identification set is a user identification or an object identification;
determining a plurality of paths including a first node of the situation attribute parameters, a second node of the user identifications and a third node of the object identifications according to the incidence relation;
generating recommendation information of an object to be recommended according to the respective path attribute values of the multiple groups of paths, wherein the recommendation information comprises:
and generating recommendation information carrying the preset label of the object to be recommended according to the respective path attribute values of the multiple groups of paths.
Optionally, after generating recommendation information of an object to be recommended, the method further includes:
receiving an object recommendation request sent by a terminal;
and returning the object to be recommended and the recommendation information of the object to be recommended to the terminal.
A second aspect of the embodiments of the present application provides a recommendation information generation apparatus, where the apparatus includes:
the first determining module is used for determining a plurality of paths of a first node comprising the situation attribute parameters, a second node comprising the user identifiers and a third node comprising the object identifiers according to the user identifiers, the object identifiers and the correlation among the situation attribute parameters;
the grouping module is used for grouping the multiple paths according to the sub-parameter values and the third nodes included in the first node on the multiple paths to obtain multiple groups of paths, wherein each sub-path included in one group of paths corresponds to the same sub-parameter value and the same object identifier;
and the generation module is used for generating recommendation information of the object to be recommended according to the respective path attribute values of the plurality of groups of paths.
Optionally, the path attribute value comprises a traffic parameter value; the generation module comprises:
a first determining submodule, configured to determine a traffic parameter value of each sub-path included in the group of paths, where the traffic parameter value of one sub-path is determined according to a traffic transfer value between every two nodes on the path, and the traffic transfer value between two nodes is determined according to an out-degree of a first node in the two nodes;
and the second determining submodule is used for determining the flow parameter value of the group of paths according to the flow parameter value of each sub-path included in the group of paths.
Optionally, the path attribute value comprises a preference; the generation module comprises:
a third determining submodule, configured to determine a preference degree of the group of paths according to respective flow parameter values of the plurality of groups of paths corresponding to the same object identifier as the group of paths, the group number of the plurality of groups of paths corresponding to the same object identifier as the group of paths, and the flow parameter value of the group of paths;
and the fourth determining submodule is used for determining the preference degree of the group of paths according to the number of the user identifications on the group of paths and the total number of the user identifications on the plurality of groups of paths corresponding to the same object identification with the group of paths.
Optionally, the generating module includes:
a fifth determining sub-module, configured to determine, from the multiple groups of paths corresponding to the same object identifier, a target group of paths whose path attribute values are greater than a preset threshold;
a sixth determining submodule, configured to determine, as an object to be recommended, an object represented by the same object identifier corresponding to each sub-path in the target group path;
and the first generation submodule is used for generating recommendation information of the object to be recommended according to the same sub-parameter value corresponding to each sub-path in the target group of paths.
Optionally, a single path of the plurality of paths further includes intermediate nodes of other parameters; the first generation submodule includes:
a determining subunit, configured to determine a target node label according to a node label of at least one intermediate node on each sub-path in the target group path;
and the generating subunit is configured to generate recommendation information of the object to be recommended, where the tag carried by the recommendation information is the target node tag and/or the object tag of the object to be recommended.
Optionally, the first determining module includes:
the seventh determining submodule is used for determining the first node, the second node and the third node from the preset knowledge graph;
and the obtaining submodule is used for traversing the preset knowledge graph according to the first node, the second node and the third node to obtain the multiple paths.
Optionally, the first determining module includes:
the eighth determining submodule is used for determining a preset operation relationship between the user identifier and the object identifier according to the historical behavior data of the user, wherein the preset operation is at least one of ordering operation, browsing operation and clicking operation;
a ninth determining sub-module, configured to determine, according to the user attribute information, a first corresponding relationship between the user identifier and the context attribute parameter, or determine, according to the object attribute information, a second corresponding relationship between the object identifier and the context attribute parameter;
the preset operation relationship and the first corresponding relationship form the incidence relationship, or the preset operation relationship and the second corresponding relationship form the incidence relationship;
the context attribute parameters include at least one of: location parameters, time parameters, tag parameters.
Optionally, the first determining module includes:
a tenth determining submodule, configured to determine, according to a preset tag, an identifier set that meets the preset tag, where an identifier in the identifier set is a user identifier or an object identifier;
an eleventh determining module, configured to determine, according to the association relationship, multiple paths including a first node including the context attribute parameter, a second node including the user identifier, and a third node including the object identifier;
the generation module comprises:
and the second generation submodule is used for generating recommendation information carrying the preset label of the object to be recommended according to the respective path attribute values of the multiple groups of paths.
Optionally, the apparatus further comprises:
the receiving module is used for receiving an object recommendation request sent by a terminal;
and the return module is used for returning the object to be recommended and the recommendation information of the object to be recommended to the terminal.
A third aspect of embodiments of the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, performs the steps in the method according to the first aspect of the present application.
A fourth aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect of the present application when executed.
By adopting the recommendation information generation method provided by the embodiment of the application, the process of generating the information to be recommended combines the situation attribute parameters and the path attribute values in the historical data in the field to which the recommendation information belongs, various characteristics of the object to be recommended are fully mined, and the recommendation information is generated by utilizing the various characteristics of the object to be recommended, so that the recommendation information of the object to be recommended is richer and has reference, and more surprise and attraction can be brought to users.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a flowchart of a recommendation information generation method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a path between "context attribute parameter-user identification-object identification";
fig. 3 is a flowchart of a recommendation information generation method according to an embodiment of the present application;
FIG. 4 is a diagram illustrating the effect of recommending information in an embodiment of the present application;
fig. 5 is a schematic diagram of a recommendation information generation apparatus according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a recommendation information generation method according to an embodiment of the present application. As shown in fig. 1, the method comprises the steps of:
step S11, determining multiple paths including a first node including the context attribute parameter, a second node including the user identifier, and a third node including the object identifier according to the association relationship among the user identifier, the object identifier, and the context attribute parameter.
In this embodiment, the user identifier is used to uniquely identify a user, where the user is a user existing in the history data of the field to which the recommendation information belongs, and the object identifier is used to uniquely identify an object, where the object is an object existing in the history data of the field to which the recommendation information belongs, the object may specifically be a merchant, a commodity, a store, and the like, the context attribute parameter may include a location parameter, a time parameter, and a tag parameter, where the location parameter may specifically be a parameter that can represent a location, such as province, Shanghai, Sichuan, a certain commercial street, or a certain subway entrance, and the like, the time parameter may specifically be a parameter that can represent a time node in the last month or the last week and the like, and the tag parameter may specifically be a parameter that can represent a feature tag in a 5 star class, a new store, an average price of 50-100.
For example, referring to fig. 2, fig. 2 is a schematic diagram of a path between a "context attribute parameter-a user identifier-an object identifier", where in fig. 2, the context attribute parameter is shanghai, sichuan, etc., the user identifiers are user134, user232, user479, user645, etc., and the object identifiers are shop113, shop200 (shop 200 is not shown in the figure), shop245, etc. The association relationship between the user134 and the user232 and shanghai may be a home address, that is, the home addresses of the user identified by the user134 and the user identified by the user232 are shanghai, the association relationship between the user479 and the user645 and the four-river may also be a home address, and similarly, the home addresses of the user identified by the user479 and the user identified by the user645 are four-river. The association of user134 with the shop113 and shop200 is an order, i.e., the user identified by user134 has made an order at the store identified by shop113 and the store identified by shop200, and similarly, the user identified by user479 and the user identified by user645 have made an order at the store identified by shop 245. At this time, referring to fig. 2, a plurality of paths, which are the shanghai-user 134-hop 113, the shanghai-user 134-hop 200 (the hop200 is not shown), the shanghai-user 232-hop 200, the sichuan-user 479-hop 245, and the sichuan-user 645-hop 245, may be determined.
It should be noted that the first node, the second node, and the third node in this embodiment do not represent a node arrangement order, that is, the first node including the context attribute parameter may be a start node, an intermediate node, or a termination node, similarly, the second node including the user identifier may be a start node, an intermediate node, or a termination node, and the third node including the object identifier may be a start node, an intermediate node, or a termination node.
The embodiment shown in fig. 2 is exemplified by a plurality of paths determined by using a context attribute parameter as a start node, using a user identifier as an intermediate node, and using an object identifier as a stop node, in an optional implementation manner, a plurality of paths determined by using an object identifier as a start node, using a user identifier as an intermediate node, and using a context attribute parameter as a stop node, or a plurality of paths determined by using a user identifier as a start node, using a user identifier as an intermediate node, and using a context attribute parameter as a stop node.
In one embodiment, the association relationship among the user identifier, the object identifier and the context attribute parameter can be determined by the following steps:
and determining a preset operation relation between the user identifier and the object identifier according to the historical behavior data of the user, wherein the preset operation is at least one of ordering operation, browsing operation and clicking operation.
And determining a first corresponding relation between the user identification and the situation attribute parameters according to the user attribute information, or determining a second corresponding relation between the object identification and the situation attribute parameters according to the object attribute information. The preset operation relationship and the first corresponding relationship form the incidence relationship, or the preset operation relationship and the second corresponding relationship form the incidence relationship. In this embodiment, after a certain user performs ordering, browsing, clicking and other operations under a certain object, historical behavior data of each user on each object is recorded, so that a preset operation relationship between the user identifier and the object identifier can be obtained, for example, a user identified by the user479 has made an order in a store identified by the object shop245, and an association relationship between the user479 and the shop245 is made an order.
In addition, each user usually performs identity registration first and fills in user attribute information; and for the users not filled with the attribute information, mining the attribute information of the users by using a user portrait technology. For example, the attribute information filled in by the user identified by the user479 is the home country, so that the first corresponding relationship between the user identification and the context attribute parameter can be obtained, that is, the association relationship between the user479 and the home country is the home country.
Similarly, each object is usually registered first, and object attribute information is filled in; or dig out attribute information of the object. For example, the attribute information filled in by the shop identified by the shop113 is that the menu is shanghai menu, and the business circle is tangjing, so that the second corresponding relationship between the object identifier and the context attribute parameter can be obtained, that is, the association relationship between the shop113 and the shanghai menu is the menu, and the association relationship between the shop113 and the tangjing is the business circle. In addition, each object may also be marked with attribute information by a user, for example, after other users place orders in a store identified by the shop113, attribute information may be marked for the shop113 according to characteristics of the shop113, for example, a price interval is 50-100 yuan, and thus, a second corresponding relationship between the object identification and the context attribute parameter may also be obtained, that is, an association relationship between the shop113 and the 50-100 yuan is the price interval.
In practical application, a domain knowledge graph containing types (class), entities (entity), relations (relation) and the like can be constructed through the domain historical data to which the recommendation information belongs, and the user identification, the object identification, the situation attribute parameters and the association relation among the user identification, the object identification, the situation attribute parameters can be quickly, intuitively and accurately obtained through the knowledge graph. At this time, when determining a plurality of paths including a first node including the context attribute parameter, a second node including the user identifier, and a third node including the object identifier according to the user identifier, the object identifier, and the association relationship among the context attribute parameters, the method may include the following steps:
step S111, determining a first node, a second node and a third node from a preset knowledge graph;
and step S112, traversing the preset knowledge graph according to the first node, the second node and the third node to obtain the plurality of paths.
In this embodiment, in a preset knowledge graph, that is, in a domain knowledge graph including a type (class), an entity (entity), a relationship (relationship), and the like, which is constructed by domain history data to which recommendation information belongs, a meta path may be formed by a first node including a context attribute parameter, a second node including a user identifier, and a third node including an object identifier, and in the meta path, a path formed by the type as a node and the relationship as an edge, for example, province — [ hometown ] - [ user ] - [ next order ] -business entity, is a meta path. After determining the meta-path, multiple paths may be obtained by traversing the knowledge-graph.
It should be noted that the association relationship among the user identifier, the object identifier, and the context attribute parameter is not limited to the preset operation relationship between the user identifier and the object identifier, the first correspondence relationship between the user identifier and the context attribute parameter, and the second correspondence relationship between the object identifier and the context attribute parameter, but includes all relationships and attributes in the knowledge graph.
In one embodiment, for some fields of recommendation information, an existing knowledge graph is available, so that the existing knowledge graph can be directly used, and the user identification, the object identification, the context attribute parameters and the association relationship among the user identification, the object identification, the context attribute parameters are more convenient to obtain.
And step S12, grouping the multiple paths according to the sub-parameter values and the third node included in the first node on the multiple paths to obtain multiple groups of paths.
Each sub-path included in the group of paths corresponds to the same sub-parameter value and corresponds to the same object identifier.
In this embodiment, the sub-parameter values refer to next-level parameters included in the context attribute parameters, for example, when the context attribute parameters are location parameters, the sub-parameters may be parameters such as shanghai and sikawa, when the context attribute parameters are time parameters, the sub-parameters may be parameters such as the last month or the last week, and when the context attribute parameters are tag parameters, the sub-parameters may be parameters such as 5 star, new store, and average price store of 50-100 yuan.
Illustratively, with continued reference to FIG. 2, the subparameters of the Sichuan-user 479-shop245 and the Sichuan-user 645-shop245 are the same and have the same object identification, so the Sichuan-user 479-shop245 and the Sichuan-user 645-shop245 are the same set of paths.
It should be understood that the path diagram shown in fig. 2 only shows a small part of the path data, and in the rest of the path data, not shown, there may be paths such as the shanghai-user 134-hop 200 (the hop200 is not shown), the shanghai-user 232-hop 200, and similarly, multiple paths are grouped according to the above grouping method, and if there are paths of the shanghai-user 134-hop 200, the shanghai-user 232-hop 200, the shanghai-user 134-hop 200 and the shanghai-user 232-hop 200 are also the same group of paths.
And step S13, generating recommendation information of the object to be recommended according to the respective path attribute values of the plurality of groups of paths.
In this embodiment, the path attribute value may include two types, namely, a flow parameter value and a preference degree.
When the path attribute values are flow parameter values, the flow parameter values corresponding to the multiple groups of paths can be determined specifically through the following steps:
step S131, determining a traffic parameter value of each sub-path included in the group of paths, where the traffic parameter value of a sub-path is determined according to a traffic transfer value between every two nodes on the path, and the traffic transfer value between two nodes is determined according to an out-degree of a first node in the two nodes.
Step S132, determining the flow parameter value of the group of paths according to the flow parameter value of each sub-path included in the group of paths.
In this embodiment, the out degree refers to the number of edges pointing to the next node, and referring to fig. 2, the out degree of the node sichuan is 2, the out degree of the node user479 is 2, and the out degree of the node user645 is 1.
Each sub-path in the group of paths takes the situation attribute parameter as an initial node, the user identifier as an intermediate node and the object identifier as a termination node, so that when a flow transfer value between the initial node and the intermediate node is calculated, the initial node is the first node of the intermediate node, calculation is performed according to the degree of departure of the initial node, and when the flow transfer value between the intermediate node and the termination node is calculated, the intermediate node is the first node of the termination node, and calculation is performed according to the degree of departure of the intermediate node. Illustratively, the traffic parameter value of each sub-path in the set of paths is equal to the product of the traffic transfer values between two nodes in the sub-path, and the traffic transfer value between two nodes is equal to the reciprocal of the degree of departure of the head node in the two nodes, i.e. 1/degree of departure of the head node.
Therefore, the flow parameter values of the sub-paths included in the group of paths may be calculated first, and then the flow parameter values of the sub-paths may be added to determine the flow parameter values of the group of paths. Continuing with fig. 2, taking the calculation of the flow parameter values of the set of the sichuan-user 479-shop245 and the sichuan-user 645-shop245 as an example, the flow parameter values of the sub-paths of the sichuan-user 479-shop245 and the sub-paths of the sichuan-user 645-shop245 included in the set of paths are first calculated. The flow parameter value 1/2 × 1/2 of the sub-path sikawa-user 479-shop245 is 1/4, the flow parameter value 1/2 × 1 of the sub-path sikawa-user 645-shop245 is 1/2, and the flow parameter value 1/4+1/2 of the set of paths is 3/4.
When the path attribute value is a preference, the preference corresponding to each of the plurality of groups of paths can be determined specifically by the following steps:
step S133, determining a preference of the group of paths according to the respective flow parameter values of the plurality of groups of paths corresponding to the same object identifier as the group of paths, the group number of the plurality of groups of paths corresponding to the same object identifier as the group of paths, and the flow parameter values of the group of paths; or determining the preference degree of the group of paths according to the number of the user identifications on the group of paths and the total number of the user identifications on the plurality of groups of paths corresponding to the same object identification.
In this embodiment, the preference degree calculation specifically includes two calculation methods, one is a calculation method that is adopted based on the calculated flow parameter values of the group of paths and the flow parameter values of the respective multiple groups of paths corresponding to the same object identifier as the group of paths, and specifically may calculate the preference degree for the object identifier to be recommended according to the following formula:
pk＝(Dk-avg(D1+D2+…+Dn))/avg(D1+D2+…+Dn)
wherein p iskRepresenting the preference degree D of the Kth group of paths after the flow parameter values of the group of paths and the flow parameter values of the multiple groups of paths corresponding to the same object identifier of the group of paths are arranged in reverse orderkAnd n represents the sum of the group number of the group of paths and the plurality of groups of paths corresponding to the same object identifier of the group of paths. The preference is a positive number, indicating a positive preference, the preference is a negative number, indicating a negative preference.
The idea of the method is a relative calculation method, namely, the calculation is carried out in proportion, namely, each position parameter is provided with a ticket, the ticket of each position parameter is divided into a plurality of tickets, if the position parameter corresponds to two users, each user obtains 1/2 tickets of the position parameter, namely, the reciprocal of the position parameter, similarly, each user is provided with a ticket, the ticket of each user is divided into a plurality of tickets, and if the user goes to three stores, each store obtains 1/3 tickets of the user, namely, the reciprocal of the user's degree.
For example, assume that there are 3 sets of paths from the start node, the user node, the middle node, and the end node, the hop113, the shanghai-user-hop 113, the flow parameter value 0.3, the kawa-user-hop 113, the flow parameter value 0.1, and the Guizhou-user-hop 113, the flow parameter value 0.08.
Then the preference of the shop113 to shanghai is:
(0.3-avg(0.3+0.1+0.08))/avg(0.3+0.1+0.08)＝0.875。
then the preference of shop113 for Sichuan is:
(0.1-avg(0.3+0.1+0.08))/avg(0.3+0.1+0.08)＝-0.375。
then the preference of shop113 to Guizhou is:
(0.08-avg(0.3+0.1+0.08))/avg(0.3+0.1+0.08)＝-0.5。
the other is to determine the preference degree of the group of paths directly according to the number of the user identifiers on the group of paths and the total number of the user identifiers on the plurality of groups of paths corresponding to the same object identifier as the group of paths, and specifically, the preference degree for the object identifier to be recommended may be calculated according to the following formula:
pk＝(Dk-avg(D1+D2+…+Dn))/avg(D1+D2+…+Dn)
wherein p iskIndicates the preference of the k-th group of paths, DkThe number of user identities, avg (D), representing the kth group path1+D2+…+Dn) Representing the average of the number of user identities for all group paths.
The idea of the method is an absolute calculation method, that is, the calculation is performed according to the actual number, which is equivalent to that each location parameter corresponds to several users, the location parameter is used for respectively casting a ticket for the several users, if the location parameter corresponds to 70 users, the 70 users respectively obtain 1 ticket of the location parameter, similarly, each user corresponds to several stores, the user is used for respectively casting a ticket for the several stores, and if the user corresponds to 10 stores, each store respectively obtains 1 ticket of the user.
By way of example, assume that there are 3 sets of paths from the start node, which is the sub-parameter of the location parameter, to the end node, the hop113, which is the shanghai-user-hop, including 70 user identifiers, along the sichuan-user-hop 113, including 40 user identifiers (i.e., the intermediate node, user), along the guizhou-user-hop 113, including 10 user identifiers.
Then the preference of the shop113 to shanghai is: (70-avg (70+40+10))/avg (70+40+10) ═ 0.75.
Then the preference of shop113 for Sichuan is: (40-avg (70+40+10))/-avg (70+40+10) ═ 0.
Then the preference of shop113 to Guizhou is: (10-avg (70+40+10))/-avg (70+40+10) — 0.75.
In this embodiment, each group of paths corresponds to a path attribute value, and after a plurality of groups of paths are grouped to obtain a plurality of groups of paths, the embodiment of the present invention may further generate recommendation information of an object to be recommended according to the respective path attribute values of the plurality of groups of paths.
In a preferred embodiment of the present invention, the step S13 may further include the steps of:
step S134, determining a target group path having a path attribute value greater than a preset threshold value from the multiple groups of paths corresponding to the same object identifier.
Step S135, determining the object represented by the same object identifier corresponding to each sub-path in the target group of paths as the object to be recommended.
Step S136, generating recommendation information of the object to be recommended according to the same sub-parameter value corresponding to each sub-path in the target group of paths.
In this embodiment, in order to conveniently and accurately determine the object to be recommended and the recommendation information of the object to be recommended, a target group path may be determined from the multiple groups of paths corresponding to the same object identifier, after the target group path is determined, an object represented by the same object identifier corresponding to each sub-path in the target group path may be determined as the object to be recommended, and the recommendation information of the object to be recommended is generated according to the same sub-parameter value corresponding to each sub-path in the target group path.
For example, three groups of paths including a shanghai-user-shop 113, a guizhou-user-shop 113 and a sichuan-user-shop 113 are shared, and the selected target group path is the shanghai-user-shop 113, and each sub-path included in one group of paths corresponds to the same sub-parameter value and corresponds to the same object identifier, so that each sub-path included in the target group path shanghai-user-shop 113 corresponds to the same sub-parameter value and corresponds to the same object identifier shop113, at this time, the object to be recommended may be a shop113, and the recommendation information for the shop113 may be a shop that is most likely to be consumed by shanghai people.
In this embodiment, specifically, the target group paths may be selected by setting a preset threshold, so that the number of the selected target group paths may be controlled, for example, in some cases, the multiple groups of paths corresponding to the same object identifier may be arranged in reverse order according to the path attribute values, and the fourth path attribute value is selected as the preset threshold, so that when generating recommendation information of an object to be recommended, three groups of target group paths, which are respectively the shanghai-user-shop 113, the guizhou-user-shop 113, and the sichuan-user-shop 113, may be obtained, because sub-paths of the three target group paths are directed at the same object identifier, so that three pieces of recommendation information may be generated for the same object to be recommended, for example, for the shop113, recommendation information may be generated, one of the shanghai favorite consumption shops, and one of the favorite consumption shops of the sichuan, one of the favorite consumption stores of the Guizhou people.
In an implementation manner, for example, the multiple groups of paths corresponding to the same object identifier may be arranged in reverse order according to the path attribute values, and the second path attribute value is selected as a preset threshold, so that when generating recommendation information of an object to be recommended, a group of target group paths, that is, a path with the largest path attribute value, such as a shanghai-user-shop 113, may be obtained, at this time, the object to be recommended may be the shop113, and the recommendation information for the shop113 may be a shop that is most likely to be consumed by shanghai people.
It should be noted that, in this embodiment, the path attribute value may be a flow parameter value alone, or a preference degree, or a flow parameter value and a preference degree may be selected at the same time, and a flow parameter value alone is selected, or a preference degree may reduce the processing steps, so as to improve the generation efficiency of the recommendation information, but the accuracy is relatively low, and although the generation efficiency of the recommendation information is reduced by selecting a flow parameter value and a preference degree at the same time, the accuracy of the recommendation information may be improved, so that a person skilled in the art may select a parameter included in the path attribute value according to actual needs.
In the embodiment of the invention, the process of generating the information to be recommended combines the situation attribute parameters and the path attribute values in the historical data in the field to which the recommendation information belongs, so that the recommendation information of the object to be recommended is richer and has referential property, and more surprise and attraction can be brought to a user.
In order to further enrich the content of the recommendation information, as an optional implementation manner, a single path in the multiple paths further includes intermediate nodes of other parameters, and at this time, when generating the recommendation information of the object to be recommended according to the same sub-parameter value corresponding to each sub-path in the target group of paths, the following steps may be included:
step S136-1, according to the node label of at least one intermediate node on each sub-path in the target group path, determining a target node label.
Step S136-2, generating recommendation information of the object to be recommended, wherein the label carried by the recommendation information is the target node label and/or the object label of the object to be recommended.
In this embodiment, on one hand, the content of the recommendation information may be enriched by adding other intermediate nodes, for example, the intermediate nodes may include not only the user identifier but also the taste node, and the recommendation information generated in this way may include a taste, for example, a shanghai may prefer to consume a spicy dish in this store.
On the other hand, the content of the recommendation information can be enriched by directly adding the target node label and/or the object label of the object to be recommended to the recommendation information. If the user identifier has a node label in the intermediate node, the node label of the user identifier can be directly used, and if other intermediate nodes, for example, the taste node has a node label, the node label of the taste intermediate node can also be directly used. Still taking the recommendation information as: the Shanghai prefers to consume the spicy and sour dish in the store as an example, the corresponding target group path is Shanghai-user-spicy-shop 113, at the moment, the middle node is user and spicy and sour, wherein the middle node user has a node label white collar crowd, the middle node has a node label hot dish with spicy and sour, the object to be recommended shop113 has an object label new store, at the moment, the target node label and/or the object label of the object to be recommended can be directly added to the recommendation information, and the generated recommendation information is as follows: new stores in Shanghai white-collar people prefer to consume hot, sour and spicy vegetables. Therefore, the method of the embodiment further enriches the content of the recommendation information, can bring more surprise and attraction to the user, and simultaneously, the embodiment directly uses the node label of the intermediate node and the object label of the object to be recommended, and is simple to operate.
In order to further enrich the content of the recommendation information, as another alternative implementation, when determining a plurality of paths including a first node including the context attribute parameter, a second node including the user identifier, and a third node including the object identifier according to the user identifier, the object identifier, and the association relationship among the context attribute parameters, the following steps may be included:
step S113, according to a preset label, determining an identification set meeting the preset label, wherein an identification in the identification set is a user identification or an object identification.
Step S114, according to the incidence relation, a plurality of paths of a first node comprising the situation attribute parameter, a second node comprising the user identifier and a third node comprising the object identifier are determined.
At this time, when generating recommendation information of an object to be recommended according to the respective path attribute values of the plurality of sets of paths, the method may include:
and step S137, generating recommendation information carrying the preset label of the object to be recommended according to the respective path attribute values of the multiple groups of paths.
In this embodiment, the preset tag is a tag predetermined according to the attribute and the type of the user or the object. For example, for the user identifiers, after the user134, the user135, the user136, and the user137 have the attribute 90, after the user140 and the user141 have the attribute 80, and after the user150 and the user151 have the attribute 70, the preset tag may be 90, so that an identifier set meeting the tag 90, that is, the user134, the user135, the user136, and the user137, may be obtained. The user identities in the identity set are a subset of the total user identities.
Similarly, for the object identifiers, the shop113, the shop114, the shop115, and the shop116 have an attribute of a restaurant, the shop121 and the shop122 have an attribute of 5-star goodness, the shop131 and the shop132 have an attribute of 10 years old, and the preset tag may be the restaurant, so that the identifier set meeting the tag of the restaurant, that is, the shop113, the shop114, the shop115, and the shop116, can be obtained. The object identifications in the set of identifications are a subset of the total object identifications.
At this time, multiple paths including a first node of the context attribute parameter, a second node of the user identifier, and a third node of the object identifier may be determined according to the association relationship, for example, if shanghai, user134, and shop113 have an association relationship, a path shanghai-user 134-shop113 may be obtained, and if shanghai, user135, and shop113 have an association relationship, a path shanghai-user 135-shop113 may be obtained. After obtaining the multiple paths, the multiple paths may be grouped with reference to the grouping method in step S12 to obtain multiple groups of paths, and then with reference to the methods in steps S131 to S136, the object to be recommended and recommendation information of the object to be recommended are generated according to respective path attribute values of the multiple groups of paths, where the difference is that the recommendation information in this embodiment carries a preset tag. For example, when the identification set includes the user identification, the recommendation information generated in this embodiment is a store that the user likes most to consume after shanghai 90, and when the identification set includes the object identification, the recommendation information generated in this embodiment is a 10-year old store that the user likes most to consume in shanghai.
In this embodiment, the user identifier or the object identifier is limited by determining the preset tag, so that richer recommendation information can be obtained, and further more surprise and attraction are brought to the user.
Referring to fig. 3, fig. 3 is a flowchart of a recommendation information generation method according to an embodiment of the present application. As shown in fig. 3, the method further comprises the steps of:
in step S14, the object recommendation request sent by the terminal is received.
And step S15, returning the object to be recommended and the recommendation information of the object to be recommended to the terminal.
In this embodiment, the terminal may be a terminal used by a user, for example, after the user logs in to an e-commerce platform page using the terminal, the user may send an object recommendation request to the server, and after receiving the object recommendation request, the server may return an object to be recommended and recommendation information of the object to be recommended to the terminal.
Referring to fig. 4, fig. 4 is a schematic diagram illustrating the effect of recommending information in an embodiment of the present application. In fig. 4, after logging in the e-commerce page, the user clicks the food column, the request of clicking the food column can be regarded as an object recommendation request, then the server returns various stores under the food column to the terminal according to preset rules, wherein, the returned 'wide stool old kitchen fire pan' in the shop carries the recommendation information 'near the palm spring living square, (small fund) user especial grass-pulling shop' generated by the embodiment of the application, the returned 'iron pan' in the shop carries the recommendation information 'sunward park/reunion lake (staff) interested flour noodle shop' generated by the embodiment of the application, and the returned recommendation information of 'Ji Ye' in the shop, namely 'one cup of cola, one bowl of rice and one slice of beef with reasonable collocation of … …', obviously, the recommendation information of 'the wide stool old stove fire pot' and 'the iron pot one house' can bring surprise and attraction to the user.
Based on the same inventive concept, an embodiment of the present application provides a recommendation information generation apparatus. Referring to fig. 5, fig. 5 is a schematic diagram of a recommendation information generating apparatus 50 according to an embodiment of the present application. As shown in fig. 5, the apparatus includes:
a first determining module 51, configured to determine, according to the user identifier, the object identifier, and the association relationship among the context attribute parameters, multiple paths including a first node including the context attribute parameter, a second node including the user identifier, and a third node including the object identifier;
a grouping module 52, configured to group the multiple paths according to the sub-parameter values and the third nodes included in the first node in the multiple paths, so as to obtain multiple groups of paths, where each sub-path included in a group of paths corresponds to the same sub-parameter value and corresponds to the same object identifier;
and the generating module 53 is configured to generate recommendation information of the object to be recommended according to the respective path attribute values of the multiple groups of paths.
Optionally, the path attribute value comprises a traffic parameter value; the generation module comprises:
a first determining submodule, configured to determine a traffic parameter value of each sub-path included in the group of paths, where the traffic parameter value of one sub-path is determined according to a traffic transfer value between every two nodes on the path, and the traffic transfer value between two nodes is determined according to an out-degree of a first node in the two nodes;
and the second determining submodule is used for determining the flow parameter value of the group of paths according to the flow parameter value of each sub-path included in the group of paths.
Optionally, the path attribute value comprises a preference; the generation module comprises:
a third determining submodule, configured to determine a preference degree of the group of paths according to respective flow parameter values of the plurality of groups of paths corresponding to the same object identifier as the group of paths, the group number of the plurality of groups of paths corresponding to the same object identifier as the group of paths, and the flow parameter value of the group of paths;
and the fourth determining submodule is used for determining the preference degree of the group of paths according to the number of the user identifications on the group of paths and the total number of the user identifications on the plurality of groups of paths corresponding to the same object identification with the group of paths.
Optionally, the generating module includes:
a fifth determining sub-module, configured to determine, from the multiple groups of paths corresponding to the same object identifier, a target group of paths whose path attribute values are greater than a preset threshold;
a sixth determining submodule, configured to determine, as an object to be recommended, an object represented by the same object identifier corresponding to each sub-path in the target group path;
and the first generation submodule is used for generating recommendation information of the object to be recommended according to the same sub-parameter value corresponding to each sub-path in the target group of paths.
Optionally, a single path of the plurality of paths further includes intermediate nodes of other parameters; the first generation submodule includes:
a determining subunit, configured to determine a target node label according to a node label of at least one intermediate node on each sub-path in the target group path;
and the generating subunit is configured to generate recommendation information of the object to be recommended, where the tag carried by the recommendation information is the target node tag and/or the object tag of the object to be recommended.
Optionally, the first determining module includes:
the seventh determining submodule is used for determining the first node, the second node and the third node from the preset knowledge graph;
and the obtaining submodule is used for traversing the preset knowledge graph according to the first node, the second node and the third node to obtain the multiple paths.
Optionally, the first determining module includes:
the eighth determining submodule is used for determining a preset operation relationship between the user identifier and the object identifier according to the historical behavior data of the user, wherein the preset operation is at least one of ordering operation, browsing operation and clicking operation;
a ninth determining sub-module, configured to determine, according to the user attribute information, a first corresponding relationship between the user identifier and the context attribute parameter, or determine, according to the object attribute information, a second corresponding relationship between the object identifier and the context attribute parameter;
the preset operation relationship and the first corresponding relationship form the incidence relationship, or the preset operation relationship and the second corresponding relationship form the incidence relationship;
the context attribute parameters include at least one of: location parameters, time parameters, tag parameters.
Optionally, the first determining module includes:
a tenth determining submodule, configured to determine, according to a preset tag, an identifier set that meets the preset tag, where an identifier in the identifier set is a user identifier or an object identifier;
an eleventh determining module, configured to determine, according to the association relationship, multiple paths including a first node including the context attribute parameter, a second node including the user identifier, and a third node including the object identifier;
the generation module comprises:
and the second generation submodule is used for generating recommendation information carrying the preset label of the object to be recommended according to the respective path attribute values of the multiple groups of paths.
Optionally, the apparatus further comprises:
the receiving module is used for receiving an object recommendation request sent by a terminal;
and the return module is used for returning the object to be recommended and the recommendation information of the object to be recommended to the terminal.
Based on the same inventive concept, another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the method according to any of the above-mentioned embodiments of the present application.
Based on the same inventive concept, another embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the electronic device implements the steps of the method according to any of the above embodiments of the present application.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one of skill in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The recommendation information generation method, the recommendation information generation device, the electronic device and the readable storage medium provided by the application are introduced in detail, and a specific example is applied in the description to explain the principle and the implementation of the application, and the description of the embodiment is only used for helping to understand the method and the core idea of the application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (12)

1. A recommendation information generation method, comprising:
determining a plurality of paths including a first node of the situation attribute parameters, a second node of the user identifiers and a third node of the object identifiers according to the association relation among the user identifiers, the object identifiers and the situation attribute parameters;
grouping the multiple paths according to the sub-parameter values and the third nodes included in the first node on the multiple paths to obtain multiple groups of paths, wherein each sub-path included in one group of paths corresponds to the same sub-parameter value and the same object identifier;
and generating recommendation information of the object to be recommended according to the respective path attribute values of the multiple groups of paths.
2. The method of claim 1, wherein the path attribute values comprise flow parameter values; the flow parameter value of any one of the multiple groups of paths is determined according to the following steps:
determining the flow parameter value of each sub-path included in the group of paths, wherein the flow parameter value of one sub-path is determined according to the flow transfer value between every two nodes on the path, and the flow transfer value between the two nodes is determined according to the degree of departure of a first node in the two nodes;
and determining the flow parameter value of the group of paths according to the flow parameter value of each sub-path included in the group of paths.
3. The method according to claim 1 or 2, wherein the path attribute value comprises a preference degree; the preference degree of any one group of paths in the multiple groups of paths is determined according to the following steps:
determining the preference degree of the group of paths according to the respective flow parameter values of the plurality of groups of paths corresponding to the same object identifier of the group of paths, the group number of the plurality of groups of paths corresponding to the same object identifier of the group of paths and the flow parameter values of the group of paths; or
And determining the preference degree of the group of paths according to the number of the user identifications on the group of paths and the total number of the user identifications on the plurality of groups of paths corresponding to the same object identification.
4. The method according to claim 1, wherein generating recommendation information of an object to be recommended according to respective path attribute values of the plurality of sets of paths comprises:
determining a target group path with a path attribute value larger than a preset threshold value from the multiple groups of paths corresponding to the same object identifier;
determining an object represented by the same object identifier corresponding to each sub-path in the target group path as an object to be recommended;
and generating recommendation information of the object to be recommended according to the same sub-parameter value corresponding to each sub-path in the target group of paths.
5. The method of claim 4, wherein a single path of the plurality of paths further comprises intermediate nodes for other parameters; generating recommendation information of the object to be recommended according to the same sub-parameter value corresponding to each sub-path in the target group of paths, wherein the recommendation information comprises:
determining a target node label according to the node labels of at least one intermediate node on each sub-path in the target group path;
and generating recommendation information of the object to be recommended, wherein the label carried by the recommendation information is the target node label and/or the object label of the object to be recommended.
6. The method according to claim 1, wherein determining a plurality of paths including a first node including the context attribute parameter, a second node including the user identifier, and a third node including the object identifier according to the association relationship among the user identifier, the object identifier, and the context attribute parameter comprises:
determining a first node, a second node and a third node from a preset knowledge graph;
and traversing the preset knowledge graph according to the first node, the second node and the third node to obtain the plurality of paths.
7. The method of claim 1, wherein the association relationship among the user identifier, the object identifier and the context attribute parameter is determined according to the following steps:
determining a preset operation relationship between a user identifier and an object identifier according to historical behavior data of the user, wherein the preset operation is at least one of ordering operation, browsing operation and clicking operation;
determining a first corresponding relation between the user identification and the situation attribute parameter according to the user attribute information, or determining a second corresponding relation between the object identification and the situation attribute parameter according to the object attribute information;
the preset operation relationship and the first corresponding relationship form the incidence relationship, or the preset operation relationship and the second corresponding relationship form the incidence relationship;
the context attribute parameters include at least one of: location parameters, time parameters, tag parameters.
8. The method according to claim 1, wherein determining a plurality of paths including a first node including the context attribute parameter, a second node including the user identifier, and a third node including the object identifier according to the association relationship among the user identifier, the object identifier, and the context attribute parameter comprises:
determining an identification set meeting a preset label according to the preset label, wherein the identification in the identification set is a user identification or an object identification;
determining a plurality of paths including a first node of the situation attribute parameters, a second node of the user identifications and a third node of the object identifications according to the incidence relation;
generating recommendation information of an object to be recommended according to the respective path attribute values of the multiple groups of paths, wherein the recommendation information comprises:
and generating recommendation information carrying the preset label of the object to be recommended according to the respective path attribute values of the multiple groups of paths.
9. The method according to any one of claims 1 to 8, wherein after generating recommendation information for an object to be recommended, the method further comprises:
receiving an object recommendation request sent by a terminal;
and returning the object to be recommended and the recommendation information of the object to be recommended to the terminal.
10. An apparatus for generating recommendation information, the apparatus comprising:
the first determining module is used for determining a plurality of paths of a first node comprising the situation attribute parameters, a second node comprising the user identifiers and a third node comprising the object identifiers according to the user identifiers, the object identifiers and the correlation among the situation attribute parameters;
the grouping module is used for grouping the multiple paths according to the sub-parameter values and the third nodes included in the first node on the multiple paths to obtain multiple groups of paths, wherein each sub-path included in one group of paths corresponds to the same sub-parameter value and the same object identifier;
and the generation module is used for generating recommendation information of the object to be recommended according to the respective path attribute values of the plurality of groups of paths.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 9.
12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executed implements the steps of the method according to any of claims 1-9.
CN202010301661.3A 2020-04-16 2020-04-16 Recommendation information generation method and device, electronic equipment and readable storage medium Pending CN111639266A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202010301661.3A CN111639266A (en) 2020-04-16 2020-04-16 Recommendation information generation method and device, electronic equipment and readable storage medium
PCT/CN2021/076510 WO2021208583A1 (en) 2020-04-16 2021-02-10 Recommendation information generation method and apparatus, electronic device and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010301661.3A CN111639266A (en) 2020-04-16 2020-04-16 Recommendation information generation method and device, electronic equipment and readable storage medium

Publications (1)

Publication Number Publication Date
CN111639266A true CN111639266A (en) 2020-09-08

Family

ID=72328901

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010301661.3A Pending CN111639266A (en) 2020-04-16 2020-04-16 Recommendation information generation method and device, electronic equipment and readable storage medium

Country Status (2)

Country Link
CN (1) CN111639266A (en)
WO (1) WO2021208583A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112380359A (en) * 2021-01-18 2021-02-19 平安科技（深圳）有限公司 Knowledge graph-based training resource allocation method, device, equipment and medium
WO2021208583A1 (en) * 2020-04-16 2021-10-21 北京三快在线科技有限公司 Recommendation information generation method and apparatus, electronic device and readable storage medium
CN113704493A (en) * 2021-08-27 2021-11-26 北京有竹居网络技术有限公司 Display information determining method, device, equipment and computer readable storage medium

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116308687B (en) * 2023-05-22 2023-07-18 北京青麦科技有限公司 Commodity information recommendation method based on knowledge graph, electronic equipment and storage medium

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103106259B (en) * 2013-01-25 2016-01-20 西北工业大学 A kind of mobile webpage content recommendation method based on situation
CN103955535A (en) * 2014-05-14 2014-07-30 南京大学镇江高新技术研究院 Individualized recommending method and system based on element path
US10565229B2 (en) * 2018-05-24 2020-02-18 People.ai, Inc. Systems and methods for matching electronic activities directly to record objects of systems of record
CN111639266A (en) * 2020-04-16 2020-09-08 北京三快在线科技有限公司 Recommendation information generation method and device, electronic equipment and readable storage medium

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021208583A1 (en) * 2020-04-16 2021-10-21 北京三快在线科技有限公司 Recommendation information generation method and apparatus, electronic device and readable storage medium
CN112380359A (en) * 2021-01-18 2021-02-19 平安科技（深圳）有限公司 Knowledge graph-based training resource allocation method, device, equipment and medium
CN113704493A (en) * 2021-08-27 2021-11-26 北京有竹居网络技术有限公司 Display information determining method, device, equipment and computer readable storage medium
WO2023024976A1 (en) * 2021-08-27 2023-03-02 北京有竹居网络技术有限公司 Display information determination method and apparatus, device, and computer-readable storage medium

Also Published As

Publication number Publication date
WO2021208583A1 (en) 2021-10-21

Similar Documents

Publication Publication Date Title
CN111639266A (en) Recommendation information generation method and device, electronic equipment and readable storage medium
CN106303955B (en) For carrying out matched method and apparatus to hotspot and POI
US20170206204A1 (en) System, method, and device for generating a geographic area heat map
CN107291888B (en) Machine learning statistical model-based living recommendation system method near living hotel
US10275530B2 (en) System and method for communal search
US20160171531A1 (en) Systems and Methods for Generating Advertising Targeting Data Using Customer Profiles Generated from Customer Data Aggregated from Multiple Information Sources
CN107424043A (en) A kind of Products Show method and device, electronic equipment
US20140032676A1 (en) System, apparatus and method for discovery of music within a social network
CN105701108B (en) A kind of information recommendation method, device and server
WO2014015079A2 (en) Method and apparatus of recommending clothing products
TW201740295A (en) Method for determining user behaviour preference, and method and device for presenting recommendation information
WO2018126740A1 (en) Method and device for pushing information
CN110110244B (en) Interest point recommendation method integrating multi-source information
CN110473040B (en) Product recommendation method and device and electronic equipment
CN107092616B (en) Object sorting method and device
US20140095307A1 (en) Spotting trends by identifying influential consumers
CN102184224A (en) System and method for screening search results
CN111080339B (en) Scene-based category preference data generation method and device
CN105447045A (en) Information ordering method and device and information providing method and system
CN102693223A (en) Search method
CN112559879B (en) Interest model training method, interest point recommending method, device and equipment
CN109741125A (en) Recommend method and device, the storage medium, electronic device of vegetable
CN111597254A (en) Resource data sharing method, device and equipment
US10452701B2 (en) Predicting a level of knowledge that a user of an online system has about a topic associated with a set of content items maintained in the online system
CN112989169A (en) Target object identification method, information recommendation method, device, equipment and medium

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