CN113761327A - Scheduling method, device and storage medium of recommendation strategy - Google Patents
Scheduling method, device and storage medium of recommendation strategy Download PDFInfo
- Publication number
- CN113761327A CN113761327A CN202010559265.0A CN202010559265A CN113761327A CN 113761327 A CN113761327 A CN 113761327A CN 202010559265 A CN202010559265 A CN 202010559265A CN 113761327 A CN113761327 A CN 113761327A
- Authority
- CN
- China
- Prior art keywords
- recommendation
- policy
- strategy
- sub
- alias
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012545 processing Methods 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 20
- 238000013461 design Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000005055 memory storage Effects 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a scheduling method, equipment and storage medium of a recommendation strategy. The method includes the steps that according to a configuration set preset by a configuration center, a latest configuration strategy alias in the configuration set is obtained in real time, a recommendation strategy to be executed is determined according to the strategy alias, when a terminal device sends a recommendation request, recommendation information corresponding to a user identifier is generated by executing the recommendation strategy according to the user identifier in the recommendation request, and the recommendation information is displayed to the user through the terminal device. When the recommendation strategy needs to be changed, the quick switching of the recommendation strategy can be realized only by carrying out configuration operation on the set elements in the configuration set.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, a device, and a storage medium for scheduling a recommended policy.
Background
With the development of the internet and the increasing number of network users, it is becoming more and more common to recommend information, such as information, goods, services, etc., to users through the internet.
At present, a label of a user has multiple dimensions, a label of a commodity also has multiple dimensions, and in different dimensions, a matching degree between the commodity and the user is not fixed and constant, and the matching degree is influenced by various factors, such as a change of market economy, a change of season and season, a change of timeliness, and the like.
However, in the prior art, each time a recommendation policy is updated, a software version needs to be redeveloped and deployed online, and information can be recommended to a user according to a new recommendation policy after the user downloads the latest software version, which is time-consuming and not beneficial to fast switching and adjustment.
Disclosure of Invention
The application provides a scheduling method, equipment and a storage medium for recommending a strategy, which can realize the quick switching of strategy priorities.
In a first aspect, an embodiment of the present application provides a scheduling method for recommending a policy, where the method includes:
acquiring at least one policy alias of a recommended policy to be executed according to a configuration set preset by a configuration center; the configuration set is dynamically configured according to a configuration instruction of a user;
determining the recommendation strategy to be executed according to the at least one strategy alias and a preset corresponding relation; the recommendation strategy to be executed comprises at least two sub-strategies, the at least two sub-strategies have a priority relationship in the recommendation strategy, and the preset corresponding relationship is a preset corresponding relationship between the recommendation strategy and a strategy alias;
and responding to a recommendation request of the terminal equipment, generating recommendation information corresponding to the user identification according to the recommendation strategy and the priority relation so as to enable the terminal equipment to display the recommendation information to the user, wherein the recommendation request comprises the user identification.
In a specific implementation manner, each sub-policy in the recommended policy corresponds to a policy alias;
the obtaining of the policy alias of the recommended policy to be executed according to the configuration set preset by the configuration center includes:
and traversing the configuration set, and sequentially acquiring the policy alias of each sub-policy to be executed, wherein each set element in the configuration set corresponds to one policy alias.
Further, the determining the recommended policy to be executed according to the at least one policy alias and a preset corresponding relationship includes:
determining a sub-policy corresponding to each policy alias according to the policy alias and a preset corresponding relation;
combining the sub-strategies corresponding to the alias names of the strategies to obtain the recommendation strategy to be executed according to the priority relationship; the priority relationship is consistent with an order of the policy aliases in the configuration set.
Further, the generating recommendation information corresponding to the user identifier according to the recommendation policy and the priority relationship includes:
according to the user identification and the priority relationship, sequentially executing the sub-strategies corresponding to the alias of each strategy;
and combining the execution results of each sub-strategy according to the priority relationship to obtain recommendation information corresponding to the user identification.
Optionally, if the corresponding relationship is a hash table, the determining a recommended policy corresponding to the policy alias according to the at least one policy alias and a preset corresponding relationship includes:
taking the strategy alias as a keyword, and calculating to obtain a storage address of a corresponding sub-strategy by adopting a hash function;
reading at least two sub-policies in the storage address;
and combining the at least two sub-strategies according to the priority relationship to obtain the recommendation strategy.
In a specific implementation manner, the recommended policy corresponds to a policy alias;
the obtaining of the policy alias of the recommended policy to be executed according to the configuration set preset by the configuration center includes:
and taking the set elements in the configuration set as the strategy aliases of the recommendation strategies to be executed.
Further, the generating recommendation information corresponding to the user identifier according to the recommendation policy and the priority relationship includes:
according to the user identification and the priority relationship, sequentially executing each sub-strategy in the recommended strategy;
and combining the execution results of each sub-strategy according to the priority relationship to obtain recommendation information corresponding to the user identification.
Optionally, if the corresponding relationship is a hash table, the determining the recommended policy to be executed according to the at least one policy alias and a preset corresponding relationship includes:
calculating to obtain a storage address of a corresponding recommended strategy by taking the strategy alias as a keyword and adopting a hash function;
and reading the recommended strategy in the storage address.
In a specific implementation manner, before the obtaining, according to a configuration set preset by a configuration center, a policy alias of a recommended policy to be executed, the method further includes:
receiving the configuration operation of an information pushing party on the configuration set in the configuration center in real time; the configuration operation includes adding or deleting collection elements in the configuration collection, or modifying the order of collection elements in the configuration collection.
In a specific implementation manner, the generating, in response to a recommendation request of a terminal device, recommendation information corresponding to an identifier of a user according to the recommendation policy includes:
determining labels of multiple dimensions of the user according to the identification of the user in the recommendation request;
and generating recommendation information corresponding to the labels of the multiple dimensions of the user according to the recommendation strategy.
In a specific implementation manner, after the generating of the recommendation information according to the recommendation policy, the method further includes:
and sending the recommendation information to the terminal equipment.
In a second aspect, an embodiment of the present application provides a method for scheduling a recommended policy, where the method includes:
sending a recommendation request to a server; the recommendation request comprises an identifier of a user and is used for requesting a server to generate recommendation information corresponding to the identifier of the user according to a recommendation strategy indicated by a configuration center, and the recommendation information comprises a plurality of recommendation contents with priority relations;
receiving the recommendation information sent by the server;
and displaying the recommendation information.
In a third aspect, an embodiment of the present application provides a server, including:
the acquisition module is used for acquiring at least one policy alias of a recommended policy to be executed according to a configuration set preset by the configuration center; the configuration set is dynamically configured according to a configuration instruction of a user;
the processing module is used for determining the recommendation strategy to be executed according to the at least one strategy alias and a preset corresponding relation; the recommendation strategy to be executed comprises at least two sub-strategies, the at least two sub-strategies have a priority relationship in the recommendation strategy, and the preset corresponding relationship is a preset corresponding relationship between the recommendation strategy and a strategy alias;
the processing module is further configured to respond to a recommendation request of the terminal device, generate recommendation information corresponding to the user identifier according to the recommendation policy and the priority relationship, so that the terminal device displays the recommendation information to the user, where the recommendation request includes the user identifier.
In a fourth aspect, an embodiment of the present application provides a terminal device, including:
the sending module is used for sending a recommendation request to the server; the recommendation request comprises an identifier of a user and is used for requesting a server to generate recommendation information corresponding to the identifier of the user according to a recommendation strategy indicated by a configuration center, and the recommendation information comprises a plurality of recommendation contents with priority relations;
the receiving module is used for receiving the recommendation information sent by the server;
and the display module is used for displaying the recommendation information.
In a fifth aspect, an embodiment of the present application provides a server, including: a memory and a processor;
the memory stores computer-executable instructions;
the processor executes the computer-executable instructions stored by the memory to cause the processor to perform the method of scheduling for a recommended policy of the first aspect.
In a sixth aspect, an embodiment of the present application provides a terminal device, including: a memory and a processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored by the memory, causing the processor to perform the policy scheduling method of the second aspect.
In a seventh aspect, an embodiment of the present application provides a storage medium, including: a readable storage medium and a computer program for implementing the method of scheduling a recommended policy according to the first aspect.
In an eighth aspect, an embodiment of the present application provides a storage medium, including: a readable storage medium and a computer program for implementing the scheduling method of the recommended policy according to the second aspect.
In a ninth aspect, embodiments of the present application provide a program product comprising instructions, which when run on a computer, cause the computer to perform the method of the first or second aspect.
In a tenth aspect, embodiments of the present application provide a computer program, which, when run on a computer, causes the computer to perform the method of the first or second aspect.
According to the scheduling method, the device and the storage medium for the recommendation strategy, the alias of the strategy configured latest in the configuration set is obtained in real time according to the configuration set preset by the configuration center, the recommendation strategy to be executed is determined according to the alias of the strategy, when the terminal device sends the recommendation request, each sub-strategy in the recommendation strategy is executed according to the user identification in the recommendation request and the priority relation of the sub-strategies, recommendation information corresponding to the user identification is generated, and the recommendation information is displayed to the user through the terminal device. When the recommendation strategy needs to be changed, the quick switching of the recommendation strategy can be realized only by carrying out configuration operation on the set elements in the configuration set.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present application;
fig. 2 is an interaction flow diagram of a scheduling method for recommending a policy according to an embodiment of the present application;
fig. 3 is a schematic diagram of a corresponding relationship between a configuration set and a recommended policy according to an embodiment of the present application;
fig. 4 is a schematic diagram of a hash table according to an embodiment of the present application;
fig. 5 and fig. 6 are schematic diagrams of a corresponding relationship between another configuration set and a recommended policy provided in an embodiment of the present application;
fig. 7 is a schematic diagram of another hash table provided in an embodiment of the present application;
fig. 8 is a schematic structural diagram of a server according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of another server provided in the embodiment of the present application;
fig. 10 is a schematic structural diagram of a terminal device according to an embodiment of the present application;
fig. 11 is a block diagram of a server according to an embodiment of the present disclosure;
fig. 12 is a block diagram of a terminal device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, 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 embodiments of the present application, but not all embodiments. 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.
Information is recommended to users through the internet, which is a common demand in various fields, such as information of recommending goods, consultation, service, and the like to users. Before information recommendation, a user needs to set tags in multiple dimensions, and set multi-dimensional tags for contents to be recommended. Taking recommending the goods to be purchased as an example, a multidimensional label can be set for each user according to whether the user is a member, the user's preference, the user's purchasing power, the user's logistics requirements, and the like, and a multidimensional label can be set for each goods according to the price of the goods, the logistics speed of the goods, the category of the goods, whether the goods have member preferential price, and the like. On the basis, a plurality of commodities to be pushed are obtained according to a preset recommendation strategy, the labels of the users and the labels of the commodities, and the commodities are recommended to the users. Generally, the recommendation strategy also has sub-strategies of multiple dimensions, a priority relationship exists between the sub-strategies corresponding to each dimension, and correspondingly, at least one recommended commodity obtained according to the recommendation strategy with high priority also has high recommendation priority.
However, due to various factors, such as changes in market economics, seasonal seasons, timeliness, and the like, the priority of the recommended goods that the user expects to receive changes, and thus the priority of the recommendation policy is often required to be adjusted so that the obtained priority of the recommended goods can meet the user's expectation. Still taking the recommended commodity as an example, assuming that the general purchasing power of the user is reduced according to the market economy data analysis, the price dimension of the commodity is taken as the dimension with the highest priority, that is, the priority of the sub-strategy corresponding to the price dimension of the commodity in the recommendation strategy is the highest.
At present, the adjustment of the priority of the recommendation strategy is usually realized by updating the software version, but the user downloads the latest software version and realizes the adjustment of the priority of the recommendation strategy by updating the software version and deploying the new version online each time, so that the time consumption of the process of updating the priority of the recommendation strategy is long, and the quick switching of the recommendation strategy is not facilitated.
The method and the device are applied to the scheduling scene of the recommendation strategies, the priority of the recommendation strategies is adjusted by adjusting the sequence of the set elements in the configuration set in the configuration center, or the set elements in the configuration set are set in the configuration center to correspond to the recommendation strategies with the priority sequence of the sub-strategies, and the recommendation strategies are selected to determine the priority sequence of the sub-strategies; and then, obtaining recommendation information with priority by executing the recommendation strategy, and displaying the recommendation information to the user according to the priority of each piece of recommendation content in the recommendation information, namely displaying each piece of recommendation content in the recommendation information from high to low according to the priority, so that the recommendation strategy is quickly adjusted, and the effect of adjusting the recommendation information in real time is achieved.
Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present application. As shown in fig. 1, the main body of the embodiment of the present application includes a configuration center 10, a server 20, and a terminal device 30.
Illustratively, the configuration center is configured to receive configuration operations of the information presenter on the configuration set, so that set elements in the configuration set are added or deleted according to requirements of the information presenter, or a sequence between the set elements is modified. The information pushing party is a demanding party, such as a business, a merchant, media and the like, providing recommendation information to the user.
The server 20 determines the recommended strategy to be executed according to the configuration set in the configuration center 10. Alternatively, the configuration center 10 may be deployed in a separate server, or may be deployed in the server 20.
The terminal device 30 may be a mobile phone, a computer, a tablet computer, a smart wearable device, and the like, and when the user opens the recommendation information interface 001 through the terminal device 30, the terminal device 30 sends a recommendation request to the server 20, where the recommendation request includes an identifier of the user, for example, a user account number logged in by the user in an application of the terminal device 30, and the server 20 generates recommendation information corresponding to the user identifier according to the determined recommendation policy to be executed.
The server 20 transmits the recommendation information to the terminal device 30, and the terminal device 30 displays the received recommendation information on a recommendation information interface 001 shown in fig. 1 through a display screen.
Optionally, a plurality of selectable recommendation strategies are preset in the server 20, where the recommendation strategy may include a plurality of sub-strategies, each sub-strategy corresponds to recommendation information of one dimension, and a priority relationship exists between each sub-strategy, and different recommendation strategies may include the same sub-strategy, but the priority relationships between the sub-strategies are different; or a plurality of selectable recommendation strategies are preset in the server 20, each recommendation strategy corresponds to recommendation information of one dimension, and the priority relationship among the plurality of recommendation strategies is determined according to the priority relationship of the set elements (i.e., the strategy aliases) in the configuration set.
The present application is specifically illustrated by the following examples.
Fig. 2 is an interaction flow diagram of a scheduling method for recommending a policy according to an embodiment of the present application. In order to improve scheduling efficiency of a recommendation policy and achieve that real-time adjustment of recommendation information meets a current recommendation expectation of a user, in the embodiment of the present application, real-time adjustment of the recommendation policy is performed according to a configuration set preset in a configuration center, so as to adjust a priority of content of the recommendation information obtained by executing the recommendation policy, for example, the method includes:
s101: and acquiring at least one policy alias of the recommended policy to be executed according to the configuration set of the configuration center.
It should be understood that the configuration set can be dynamically configured according to the configuration operation of the information push side. Illustratively, the configuration set is an ordered ArrayList set, which is a dynamic array that can dynamically add or subtract set elements from a set. For example, at least one set element corresponding to at least one policy alias of the recommended policy to be executed is configured in the configuration set, and for example, at least one policy alias may be configured in the configuration set as a set element of the configuration set.
Optionally, the configuration set is stored in an open source distributed application coordination service, such as zookeeper pr.
In this step, a set element in a preset configuration set is obtained, that is, at least one policy alias of a recommended policy to be executed is obtained.
In a specific implementation manner, before step S101, the embodiment of the present application further includes: and receiving the configuration operation of the information pushing party on the configuration set in the configuration center, wherein the configuration operation comprises adding or deleting the set elements in the configuration set or modifying the sequence of the set elements in the configuration set. Better convenience is provided for the recommendation information sender to change the recommendation information.
S102: and determining a recommendation strategy to be executed according to at least one strategy alias and a preset corresponding relation.
The preset corresponding relation is the preset corresponding relation between the recommended strategy and the strategy alias.
Illustratively, each recommended policy includes at least two sub-policies, each sub-policy being implemented in an asynchronous message processing handler object.
The recommendation policy to be executed includes at least two sub-policies, and the at least two sub-policies have a priority relationship in the recommendation policy, and the priority relationship may be preset or may be determined according to an order of set elements in a configuration set. If a preset priority relation exists between each sub-strategy of the recommendation strategy, setting a strategy alias for each recommendation strategy; if each sub-policy of the recommended policy is in a parallel relationship, a policy alias is set for each sub-policy, and the priority relationship between the sub-policies is determined by configuring the sequence of the set elements in the set.
In this step, a preset corresponding relationship exists between the policy alias and the recommendation policy, and the corresponding recommendation policy can be obtained according to the policy alias, or at least two sub-policies constituting the recommendation policy can be obtained according to the policy alias. For example, the correspondence may be a correspondence list, or a correspondence data, or a hash table.
As an example, the recommendation policy includes a plurality of sub-policies having a priority relationship, each recommendation policy corresponds to a policy alias, and the recommendation policy to be executed may be determined according to the policy alias and a preset corresponding relationship. For example, the number of the recommendation policies may be one to multiple, each recommendation policy includes at least two sub-policies having a priority relationship, the sub-policies included in different recommendation policies may be the same or different, and if the same sub-policy is included in different recommendation policies, the priority relationships between the sub-policies should be different. The priority relation between the recommendation strategies may be consistent with the order of the strategy aliases in the configuration set, or there may be no priority relation between the recommendation strategies, which is not required by the present solution.
As another example, the recommendation policy includes a plurality of sub-policies in parallel relationship, each sub-policy corresponds to one policy alias, the sub-policy corresponding to each policy alias can be determined according to the policy alias and the preset corresponding relationship, and the sub-policies form the recommendation policy to be executed. It should be understood that when the recommended policy includes a plurality of sub-policies in parallel relationship, the priority of each sub-policy needs to be determined according to the configuration set, and the priority relationship between the sub-policies is consistent with the priority relationship of the policy aliases in the configuration set.
S103: and sending a recommendation request.
In this step, the terminal device sends a recommendation request to the server, where the recommendation request includes an identifier of the user, for example, a user account number that the user logs in the terminal device, and the recommendation request is used to request the server to generate recommendation information corresponding to the identifier of the user according to a recommendation policy indicated by the configuration center.
For example, after the user opens the interface containing the recommendation information in the terminal device, the terminal device sends a recommendation request to the server in response to the user's interface opening operation.
S104: and generating recommendation information corresponding to the user identification according to the recommendation strategy and the priority relation.
In this step, recommendation information corresponding to the user identifier is generated by executing the recommendation policy determined in step S102 and the priority relationship between the sub-policies in the recommendation policy, and it should be understood that in the process of executing the recommendation policy, processing needs to be performed in combination with the user identifier.
The user's identification corresponds to the user's labels in multiple dimensions. In a specific implementation manner, according to the identification of the user in the recommendation request, the multi-dimensional tags of the user are determined, and recommendation information corresponding to the multi-dimensional tags of the user is generated according to a recommendation policy.
Still taking the recommended commodities as an example, the recommendation strategy is assumed to be that recommendation information is sequentially obtained according to three dimensions of whether the commodities have member discount prices, logistics speeds of the commodities and categories of the commodities, the priority of the recommended commodities obtained by taking whether the commodities have the member discount prices as the recommendation dimensions in the recommendation information is the highest and is displayed at the forefront, the priority of the recommended commodities obtained by taking the logistics speeds of the commodities as the recommendation dimensions is the lowest, and the priority of the recommended commodities obtained by taking the categories of the commodities as the recommendation dimensions is displayed at the last. However, in practical applications, recommendation information needs to be generated in combination with a tag of a user, for example, if the user is a non-member, even if the product has a recommendation dimension with a member preference of the highest priority, but the product does not match the current user, the recommendation dimension is skipped to obtain a recommended product for a recommendation dimension of a next priority.
Illustratively, generating recommendation information corresponding to the user identifier according to the recommendation policy specifically includes: according to the user identification, each sub-strategy in the recommendation strategies is executed to obtain an execution result of each sub-strategy, the execution result is at least one recommendation content of any dimension, corresponding to the priority of each sub-strategy, the priority of the sub-strategy executed first is the highest, correspondingly, the recommendation content obtained by executing the sub-strategy is recommended in priority, for example, the recommendation content is displayed at the top of all recommendation contents in an interface, then a plurality of recommendation contents with recommendation priority relations are obtained in sequence according to the priorities of the sub-strategies, and the recommendation information is formed by the recommendation contents with the recommendation priority relations.
S105: and sending recommendation information.
S106: and displaying the recommendation information.
And the server sends the generated recommendation information to the terminal equipment of the recommendation requester, and the terminal equipment displays the recommendation information on a recommendation information interface.
According to the method and the device, the latest configured strategy alias in the configuration set is obtained in real time according to the configuration set preset by the configuration center, the recommendation strategy to be executed is determined according to the strategy alias, when the terminal device sends the recommendation request, each sub-strategy in the recommendation strategy is executed according to the user identification in the recommendation request and the priority relation of the sub-strategies, recommendation information corresponding to the user identification is generated, and the recommendation information is displayed to the user through the terminal device. When the recommendation strategy needs to be changed, the quick switching of the recommendation strategy can be realized only by carrying out configuration operation on the set elements in the configuration set, so as to realize the updating of the priority of the recommendation information.
On the basis of the above embodiments, the embodiments of the present application implement and adjust the recommendation policy according to the configuration set, and have at least the following two specific implementation manners:
the first method is as follows: the method comprises the steps that a plurality of sub-strategies are preset in a server, each sub-strategy corresponds to a recommendation dimension, the priority relation between the corresponding at least two sub-strategies is determined according to at least two ordered set elements in a configuration set, the execution of the recommendation strategies is realized by sequentially executing the at least two sub-strategies, a plurality of recommendation contents with the recommendation priority relation are obtained, and the plurality of recommendation contents are used as recommendation information.
The recommendation strategy comprises at least two sub-strategies, the sub-strategies are in parallel relation, and each sub-strategy corresponds to a strategy alias.
Fig. 3 is a schematic diagram of a corresponding relationship between a configuration set and a recommended policy according to an embodiment of the present application. For example, as shown in fig. 3, the configuration set includes a set element (KeyB KeyC KeyA), the set element may be a policy alias, and the recommended policy includes a sub-policy 1, a sub-policy 2, and a sub-policy 3. The policy alias KeyB corresponds to the sub-policy 2, the policy alias KeyC corresponds to the sub-policy 3, and the policy alias KeyA corresponds to the sub-policy 1.
In the embodiment of the application, policy aliases, namely KeyB, KeyC and KeyA, of each sub-policy to be executed are sequentially acquired through traversing a configuration set, further, the sub-policies corresponding to the policy aliases, namely sub-policy 2, sub-policy 3 and sub-policy 1, are determined according to the policy aliases and a preset corresponding relation, then the sub-policies corresponding to the policy aliases are sequentially executed according to the user identifiers, namely sub-policy 2, sub-policy 3 and sub-policy 1 are sequentially executed, a plurality of pieces of recommended content corresponding to the user identifiers are generated according to the execution result of each sub-policy, and the generated plurality of pieces of recommended content form recommended information according to the order of the recommended content generated by executing the sub-policies.
Still taking the recommended commodity as an example, assuming that the commodity is required to be recommended sequentially according to the price dimension of the commodity (corresponding to the sub-policy 2), the logistics speed dimension of the commodity (corresponding to the sub-policy 3), and whether the commodity has the priority order of the member preferential price dimension (corresponding to the sub-policy 1), namely, the configuration set is required to be adjusted so that the sub-policy 2, the sub-policy 3, and the sub-policy 1 are sequentially executed, and then the recommended content corresponding to the sub-policy 2, the recommended content corresponding to the sub-policy 3, and the recommended content corresponding to the sub-policy 1 are sequentially obtained by executing each sub-policy, the number of the recommended contents is not limited in the present application, and the recommended contents corresponding to each sub-policy form final recommendation information according to the obtained order. Before the above process, the order of the policy alias corresponding to each sub-policy in the configuration set needs to be adjusted, for example, by setting the configuration set to (KeyB KeyC KeyA) and traversing the configuration set, KeyB corresponding to sub-policy 2, KeyC corresponding to sub-policy 3, and KeyA corresponding to sub-policy 1 can be obtained in sequence. By dynamically configuring the set elements in the configuration set, the priority relationship among the sub-strategies is changed, and the quick change of the recommendation strategy is realized.
In this embodiment, a corresponding sub-policy is set for each recommendation dimension, and an execution sequence of the sub-policies is changed by dynamically configuring a configuration set, where the execution sequence of the sub-policies determines a push sequence of generated recommendation contents, that is, a sub-policy to be executed first, the generated recommendation contents are pushed first, that is, a recommendation priority of the recommendation contents obtained by executing each sub-policy is changed, and all recommendation contents form recommendation information according to the priority, so that a convenient implementation manner is provided for switching recommendation information of different recommendation dimensions.
Fig. 4 is a schematic diagram of a hash table according to an embodiment of the present application. In a specific implementation manner, the preset correspondence may be implemented by a hash table, as shown in fig. 4, each sub-policy is used as a value, for example, sub-policy 1 to sub-policy 5 and other more sub-policies, a policy alias corresponding to a sub-policy is used as a key, for example, KeyA, KeyB, KeyC, etc., for example, KeyA corresponds to sub-policy 1, KeyB corresponds to sub-policy 4, and KeyC corresponds to sub-policy 5, and the sub-policy and the corresponding policy alias are combined into a key-value pair and stored in the hash table. And determining a recommended strategy to be executed according to at least one strategy alias and a preset corresponding relation based on the hash table, for example, if a sub-strategy corresponding to KeyA needs to be determined, performing hash function operation according to KeyA to obtain a storage address 1 of the sub-strategy 1, and reading the sub-strategy 1 from the storage address 1.
The second method comprises the following steps: the method comprises the steps that a plurality of recommendation strategies are preset in a server, each recommendation strategy comprises at least two sub-strategies, a preset priority relation exists between the sub-strategies, an information pushing party determines the recommendation strategy to be selected according to the priority of recommendation information to be realized, and at least one set element (namely a strategy alias) corresponding to at least one selected recommendation strategy is configured in a recommendation strategy configuration set.
If the number of the set elements in the configuration set is 1, taking the set elements in the configuration set as policy aliases of the recommendation policy to be executed; if the number of the set elements in the configuration set is greater than or equal to 2, the at least one set element may have a priority relationship or may not have a priority relationship, and the present solution does not require this, and accordingly, a plurality of policy aliases may be directly obtained from the configuration set, or policy aliases of each recommended policy to be executed may be sequentially obtained by traversing the configuration set.
Fig. 5 and fig. 6 are schematic diagrams of correspondence between another configuration set and a recommended policy provided in an embodiment of the present application. For example, as shown in fig. 5, a set element KeyB is set in the configuration set, the set element may specifically be a policy alias, and a plurality of selectable recommendation policies, such as recommendation policy 1, recommendation policy 2, and recommendation policy 3, are preset in the server. Further, each recommendation policy includes at least two sub-policies, and at least two sub-policies have a preset priority relationship therebetween, for example, the sub-policy of the recommendation policy 2 is sequentially sub-policy 1, sub-policy 2, and sub-policy 3, as shown in fig. 6, the sub-policy of the recommendation policy 3 is sequentially sub-policy 2, sub-policy 3, and sub-policy 1, and the recommendation policy 3 and the recommendation policy 2 include the same sub-policy, but the priority relationships between the sub-policies are different, and the sub-policy of the recommendation policy 1 is sequentially sub-policy 4 and sub-policy 5, for example, the recommendation policy 1, the recommendation policy 2, and the recommendation policy 3 may have the same sub-policy, or have partially same sub-policies, or have completely different sub-policies, and the present scheme does not make a request for this.
Referring to fig. 5, if the set element in the configuration set is KeyB, the recommendation policy determined according to KeyB is recommendation policy 2, that is, sub-policy 1, sub-policy 2, and sub-policy 3 in recommendation policy 2 are sequentially executed.
If the number of the set elements in the configuration set is at least two, and the set elements in the configuration set are KeyB and KeyA as shown in fig. 6, then the recommendation policy 2 corresponding to KeyB and the recommendation policy 1 corresponding to KeyA are executed respectively, or the recommendation policy 2 and the recommendation policy 1 are executed in sequence according to the order from KeyB to KeyA, which is not required in the present solution.
Still taking the recommended commodities as an example, assuming that the commodity recommendation needs to be performed in sequence according to the priority order of the price dimension of the commodities (corresponding to the sub-policy 1), the logistics speed dimension of the commodities (corresponding to the sub-policy 2), and whether the commodities have the member preferential price dimension (corresponding to the sub-policy 3), a policy alias corresponding to the recommendation policy 2 needs to be set in the configuration set, namely KeyB, and further determines the recommendation strategy to be executed to be recommendation strategy 2 through the KeyB acquired from the configuration set, and executes the sub-strategies in sequence according to the priority relation of the sub-strategies in the recommendation strategy 2, that is, the recommendation information meeting the priority requirement is obtained, for example, when the priority order of the sub-policies needs to be adjusted to sub-policy 2, sub-policy 3, and sub-policy 1, and deleting the set element KeyB in the configuration set, and adding the set element KeyC corresponding to the recommendation policy 3, so that the recommendation policy can be quickly switched.
In this embodiment, sub-policies corresponding to different dimensions are set in multiple recommendation policies, and each sub-policy has a preset priority relationship, and by performing configuration operation on set elements in a configuration set, a recommendation policy can be selected or adjusted, so that switching of the recommendation policies is realized, and further, execution sequences of the sub-policies corresponding to different recommendation dimensions and the sub-policies are changed.
Fig. 7 is a schematic diagram of another hash table according to an embodiment of the present application. In a specific implementation manner, the preset correspondence may be implemented by a hash table, as shown in fig. 4, each recommendation policy is used as a value, for example, recommendation policy 1 to recommendation policy 5 and other more recommendation policies, policy aliases corresponding to the recommendation policies are used as keys, for example, KeyA, KeyB, KeyC, and the like, for example, KeyA corresponds to recommendation policy 1, KeyB corresponds to recommendation policy 4, and KeyC corresponds to recommendation policy 5, and the recommendation policy and the corresponding policy aliases are combined into a key-value pair and stored in the hash table. Based on the hash table, determining a recommendation policy to be executed according to at least one policy alias and a preset corresponding relationship, for example, if a recommendation policy corresponding to KeyA needs to be determined, performing hash function operation according to KeyA to obtain a storage address 1 of the recommendation policy 1, and reading the recommendation policy 1 in the storage address 1.
On the basis of the above embodiment, the hash table and the handler object of each recommended policy are deployed in the common domain service.
Fig. 8 is a schematic structural diagram of a server according to an embodiment of the present application, and as shown in fig. 8, the server 10 includes:
the obtaining module 11 is configured to obtain at least one policy alias of a recommended policy to be executed according to a configuration set preset by a configuration center; the configuration set is dynamically configured according to a configuration instruction of a user;
the processing module 12 is configured to determine the recommended policy to be executed according to the at least one policy alias and a preset corresponding relationship; the recommendation strategy to be executed comprises at least two sub-strategies, the at least two sub-strategies have a priority relationship in the recommendation strategy, and the preset corresponding relationship is a preset corresponding relationship between the recommendation strategy and a strategy alias;
the processing module 12 is further configured to respond to a recommendation request of a terminal device, and generate recommendation information corresponding to an identifier of a user according to the recommendation policy and the priority relationship, so that the terminal device displays the recommendation information to the user, where the recommendation request includes the identifier of the user.
The server 10 provided in the embodiment of the present application includes an obtaining module 11 and a processing module 12, which obtain, in real time, an alias of a newly configured policy in a configuration set according to a configuration set preset by a configuration center, determine a recommendation policy to be executed according to the alias of the policy, generate, when a terminal device sends a recommendation request, recommendation information corresponding to an identifier of a user by executing the recommendation policy according to the identifier of the user in the recommendation request, and display, by the terminal device, the recommendation information to the user. When the recommendation strategy needs to be changed, the quick switching of the recommendation strategy can be realized only by carrying out configuration operation on the set elements in the configuration set.
In a possible design, the obtaining module 11 is specifically configured to traverse the configuration set, and sequentially obtain a policy alias of each sub-policy to be executed, where each set element in the configuration set corresponds to one policy alias.
In one possible design, the processing module 12 is specifically configured to:
determining a sub-policy corresponding to each policy alias according to the policy alias and a preset corresponding relation;
combining the sub-strategies corresponding to the alias names of the strategies to obtain the recommendation strategy to be executed according to the priority relationship; the priority relationship is consistent with an order of the policy aliases in the configuration set.
In one possible design, the processing module 12 is specifically configured to:
according to the user identification and the priority relationship, sequentially executing the sub-strategies corresponding to the alias of each strategy;
and obtaining recommendation information corresponding to the user identification according to the execution result of each sub-strategy and the priority relation.
In one possible design, the processing module 12 is specifically configured to:
taking the strategy alias as a keyword, and calculating to obtain a storage address of a corresponding sub-strategy by adopting a hash function;
reading at least two sub-policies in the storage address;
and combining the at least two sub-strategies according to the priority relationship to obtain the recommendation strategy.
In one possible design, the obtaining module 11 is specifically configured to: and taking the set elements in the configuration set as the strategy aliases of the recommendation strategies to be executed.
In one possible design, the processing module 12 is specifically configured to: according to the user identification and the priority relationship, sequentially executing each sub-strategy in the recommended strategy;
and combining the execution results of each sub-strategy according to the priority relationship to obtain recommendation information corresponding to the user identification.
In one possible design, the processing module 12 is specifically configured to:
calculating to obtain a storage address of a corresponding recommended strategy by taking the strategy alias as a keyword and adopting a hash function;
and reading the recommended strategy in the storage address.
In one possible design, the processing module 12 is specifically configured to:
determining labels of multiple dimensions of the user according to the identification of the user in the recommendation request;
and generating recommendation information corresponding to the labels of the multiple dimensions of the user according to the recommendation strategy.
Fig. 9 is a schematic structural diagram of another server provided in the embodiment of the present application, and as shown in fig. 9, the server 10 further includes: a receiving module 13 and a transmitting module 14;
the receiving module 13 is configured to receive, in real time, a configuration operation of an information push party on the configuration set in the configuration center; the configuration operation includes adding or deleting collection elements in the configuration collection, or modifying the order of collection elements in the configuration collection.
The sending module 14 is configured to send the recommendation information to the terminal device.
The server provided in the foregoing embodiment may execute the technical solution of the foregoing method embodiment, and the implementation principle and the technical effect are similar, which are not described herein again.
Fig. 10 is a schematic structural diagram of a terminal device according to an embodiment of the present application, and as shown in fig. 10, the terminal device 20 includes:
a sending module 21, configured to send a recommendation request to a server; the recommendation request comprises an identifier of a user and is used for requesting a server to generate recommendation information corresponding to the identifier of the user according to a recommendation strategy indicated by a configuration center, and the recommendation information comprises a plurality of recommendation contents with priority relations;
a receiving module 22, configured to receive the recommendation information sent by the server;
and the display module 23 is configured to display the recommendation information.
The terminal device provided in the foregoing embodiment may execute the technical solution of the foregoing method embodiment, and the implementation principle and technical effect are similar, which is not described herein again.
Referring to fig. 11, the embodiment of the present application only uses fig. 11 as an example to describe, and does not mean that the present application is limited thereto.
Fig. 11 is a block diagram of a server according to an embodiment of the present application. In general, the server 600 includes: a processor 601 and a memory 602; optionally, a bus 603 may also be included. The bus 603 is used to realize the connection between the elements.
The processor 601 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor 601 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 601 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 601 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, processor 601 may also include an AI (Artificial Intelligence) processor for processing computational operations related to machine learning.
The memory 602 may include one or more computer-readable storage media, which may be non-transitory. The memory 602 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 602 is used to store at least one instruction for execution by processor 601 to implement the scheduling method applied to the recommended policies on the server side provided by the method embodiments herein.
Those skilled in the art will appreciate that the architecture shown in FIG. 11 does not constitute a limitation on the server 600, and may include more or fewer components than those shown, or combine certain components, or employ a different arrangement of components.
Referring to fig. 12, in the embodiment of the present application, only fig. 12 is taken as an example to illustrate the terminal device, which does not mean that the present application is limited thereto.
Fig. 12 is a block diagram of a terminal device according to an embodiment of the present application. In general, the terminal device 500 includes: a processor 501 and a memory 502; optionally, a bus 503 may also be included. The bus 503 is used to realize connection between the elements.
The processor 501 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor 501 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 501 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 501 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, processor 501 may also include an AI (Artificial Intelligence) processor for processing computational operations related to machine learning.
The embodiment of the present application further provides a non-transitory computer-readable storage medium, and when instructions in the storage medium are executed by a processor of a mobile terminal, the terminal is enabled to execute the scheduling method of the recommendation policy provided in the foregoing embodiment.
The embodiment of the present application further provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the scheduling method of the recommendation policy provided in the above embodiment.
The embodiment of the present application further provides a computer program, and when the computer program runs on a computer, the computer is enabled to execute the scheduling method of the recommendation policy.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (18)
1. A method for scheduling a recommended policy, the method comprising:
acquiring at least one policy alias of a recommended policy to be executed according to a configuration set of a configuration center; the configuration set is dynamically configured according to a configuration instruction of a user;
determining the recommendation strategy to be executed according to the at least one strategy alias and a preset corresponding relation; the recommendation strategy to be executed comprises at least two sub-strategies, the at least two sub-strategies have a priority relationship in the recommendation strategy, and the preset corresponding relationship is a preset corresponding relationship between the recommendation strategy and a strategy alias;
and responding to a recommendation request of the terminal equipment, and generating recommendation information corresponding to the user identification according to the recommendation strategy and the priority relation so as to enable the terminal equipment to display the recommendation information to the user, wherein the recommendation request comprises the user identification.
2. The method of claim 1, wherein each sub-policy in the recommended policy corresponds to a policy alias;
the obtaining of the policy alias of the recommended policy to be executed according to the configuration set preset by the configuration center includes:
and traversing the configuration set, and sequentially acquiring the policy alias of each sub-policy to be executed, wherein each set element in the configuration set corresponds to one policy alias.
3. The method according to claim 2, wherein the determining the recommended policy to be executed according to the at least one policy alias and a preset correspondence comprises:
determining a sub-policy corresponding to each policy alias according to the policy alias and a preset corresponding relation;
combining the sub-strategies corresponding to the alias names of the strategies to obtain the recommendation strategy to be executed according to the priority relationship; the priority relationship is consistent with an order of the policy aliases in the configuration set.
4. The method according to claim 3, wherein the generating recommendation information corresponding to the user's identifier according to the recommendation policy and the priority relationship comprises:
according to the user identification and the priority relationship, sequentially executing the sub-strategies corresponding to the alias of each strategy;
and combining the execution results of each sub-strategy according to the priority relationship to obtain recommendation information corresponding to the user identification.
5. The method according to any one of claims 1 to 4, wherein if the correspondence is a hash table, the determining the recommended policy corresponding to the policy alias according to the at least one policy alias and a preset correspondence includes:
taking the strategy alias as a keyword, and calculating to obtain a storage address of a corresponding sub-strategy by adopting a hash function;
reading at least two sub-policies in the storage address;
and combining the at least two sub-strategies according to the priority relationship to obtain the recommendation strategy.
6. The method of claim 1, wherein the recommended policy corresponds to a policy alias;
the obtaining of the policy alias of the recommended policy to be executed according to the configuration set preset by the configuration center includes:
and taking the set elements in the configuration set as the strategy aliases of the recommendation strategies to be executed.
7. The method according to claim 6, wherein the generating recommendation information corresponding to the user's identifier according to the recommendation policy and the priority relationship comprises:
according to the user identification and the priority relationship, sequentially executing each sub-strategy in the recommended strategy;
and combining the execution results of each sub-strategy according to the priority relationship to obtain recommendation information corresponding to the user identification.
8. The method according to claim 6 or 7, wherein if the correspondence is a hash table, the determining the recommended policy to be executed according to the at least one policy alias and a preset correspondence includes:
calculating to obtain a storage address of a corresponding recommended strategy by taking the strategy alias as a keyword and adopting a hash function;
and reading the recommended strategy in the storage address.
9. The method according to any one of claims 1 to 4, wherein before the obtaining of the policy alias of the recommended policy to be executed according to the configuration set preset by the configuration center, the method further comprises:
receiving the configuration operation of an information pushing party on the configuration set in the configuration center in real time; the configuration operation includes adding or deleting collection elements in the configuration collection, or modifying the order of collection elements in the configuration collection.
10. The method according to any one of claims 1 to 4, wherein the generating recommendation information corresponding to the user identifier according to the recommendation policy in response to the recommendation request of the terminal device comprises:
determining labels of multiple dimensions of the user according to the identification of the user in the recommendation request;
and generating recommendation information corresponding to the labels of the multiple dimensions of the user according to the recommendation strategy.
11. The method of any of claims 1 to 4, wherein after the generating recommendation information according to the recommendation policy, the method further comprises:
and sending the recommendation information to the terminal equipment.
12. A method for scheduling a recommended policy, the method comprising:
sending a recommendation request to a server; the recommendation request comprises an identifier of a user and is used for requesting a server to generate recommendation information corresponding to the identifier of the user according to a recommendation strategy indicated by a configuration center, and the recommendation information comprises a plurality of recommendation contents with priority relations;
receiving the recommendation information sent by the server;
and displaying the recommendation information.
13. A server, comprising:
the acquisition module is used for acquiring at least one policy alias of a recommended policy to be executed according to a configuration set preset by the configuration center; the configuration set is dynamically configured according to a configuration instruction of a user;
the processing module is used for determining the recommendation strategy to be executed according to the at least one strategy alias and a preset corresponding relation; the recommendation strategy to be executed comprises at least two sub-strategies, the at least two sub-strategies have a priority relationship in the recommendation strategy, and the preset corresponding relationship is a preset corresponding relationship between the recommendation strategy and a strategy alias;
the processing module is further configured to respond to a recommendation request of the terminal device, generate recommendation information corresponding to the user identifier according to the recommendation policy and the priority relationship, so that the terminal device displays the recommendation information to the user, where the recommendation request includes the user identifier.
14. A terminal device, comprising:
the sending module is used for sending a recommendation request to the server; the recommendation request comprises an identifier of a user and is used for requesting a server to generate recommendation information corresponding to the identifier of the user according to a recommendation strategy indicated by a configuration center, and the recommendation information comprises a plurality of recommendation contents with priority relations;
the receiving module is used for receiving the recommendation information sent by the server;
and the display module is used for displaying the recommendation information.
15. A server, comprising: a memory and a processor;
the memory stores computer-executable instructions;
the processor executing the computer-executable instructions stored by the memory causes the processor to perform the method of scheduling of recommended policies of any of claims 1 to 11.
16. A terminal device, comprising: a memory and a processor;
the memory stores computer-executable instructions;
the processor executing the memory-stored computer-executable instructions cause the processor to perform the policy scheduling method of claim 12.
17. A storage medium, comprising: a readable storage medium and a computer program for implementing the method of scheduling of a recommended strategy according to any one of claims 1 to 11.
18. A storage medium, comprising: a readable storage medium and a computer program for implementing the scheduling method of a recommendation policy of claim 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010559265.0A CN113761327B (en) | 2020-06-18 | 2020-06-18 | Scheduling method, equipment and storage medium of recommendation strategy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010559265.0A CN113761327B (en) | 2020-06-18 | 2020-06-18 | Scheduling method, equipment and storage medium of recommendation strategy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113761327A true CN113761327A (en) | 2021-12-07 |
| CN113761327B CN113761327B (en) | 2024-06-18 |
Family
ID=78785476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010559265.0A Active CN113761327B (en) | 2020-06-18 | 2020-06-18 | Scheduling method, equipment and storage medium of recommendation strategy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113761327B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090144635A1 (en) * | 2007-12-04 | 2009-06-04 | Mitsuhiro Miyazaki | Information processing apparatus, information processing method, and information processing program |
| CN109062994A (en) * | 2018-07-04 | 2018-12-21 | 平安科技（深圳）有限公司 | Recommended method, device, computer equipment and storage medium |
| CN109389451A (en) * | 2017-08-08 | 2019-02-26 | 阿里巴巴集团控股有限公司 | A kind of method and system of determining recommendation information |
| CN109428871A (en) * | 2017-08-31 | 2019-03-05 | 腾讯科技（深圳）有限公司 | Defence policies determine method and device |
| CN110688579A (en) * | 2019-10-08 | 2020-01-14 | 北京星选科技有限公司 | Object pushing method and device, electronic equipment and storage medium |
| CN110769034A (en) * | 2019-09-20 | 2020-02-07 | 中国平安人寿保险股份有限公司 | Recommendation system strategy iteration method and device, storage medium and server |
| CN110910201A (en) * | 2019-10-18 | 2020-03-24 | 中国平安人寿保险股份有限公司 | Information recommendation control method and device, computer equipment and storage medium |
-
2020
- 2020-06-18 CN CN202010559265.0A patent/CN113761327B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090144635A1 (en) * | 2007-12-04 | 2009-06-04 | Mitsuhiro Miyazaki | Information processing apparatus, information processing method, and information processing program |
| CN109389451A (en) * | 2017-08-08 | 2019-02-26 | 阿里巴巴集团控股有限公司 | A kind of method and system of determining recommendation information |
| CN109428871A (en) * | 2017-08-31 | 2019-03-05 | 腾讯科技（深圳）有限公司 | Defence policies determine method and device |
| CN109062994A (en) * | 2018-07-04 | 2018-12-21 | 平安科技（深圳）有限公司 | Recommended method, device, computer equipment and storage medium |
| CN110769034A (en) * | 2019-09-20 | 2020-02-07 | 中国平安人寿保险股份有限公司 | Recommendation system strategy iteration method and device, storage medium and server |
| CN110688579A (en) * | 2019-10-08 | 2020-01-14 | 北京星选科技有限公司 | Object pushing method and device, electronic equipment and storage medium |
| CN110910201A (en) * | 2019-10-18 | 2020-03-24 | 中国平安人寿保险股份有限公司 | Information recommendation control method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王志松;段历历;: "基于用户访问路径分析的页面推荐模型", 燕山大学学报, no. 01, 15 January 2007 (2007-01-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113761327B (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10534635B2 (en) | Personal digital assistant | |
| WO2016101811A1 (en) | Information arrangement method and apparatus | |
| US10554613B2 (en) | Dynamic hashtag ordering based on projected interest | |
| CN109901987B (en) | Method and device for generating test data | |
| CN110706093A (en) | Accounting processing method and device | |
| CN112686519A (en) | Gray scale adjusting method and device, electronic equipment and storage medium | |
| CN109726295A (en) | Brand knowledge map display methods, device, figure server and storage medium | |
| CN106104617B (en) | Performing market actions based on social networking tags | |
| CN112748969A (en) | Information processing method, information display method and device | |
| CN112749323A (en) | Method and device for constructing user portrait | |
| CN111782850A (en) | Object searching method and device based on hand drawing | |
| CN109561048B (en) | Communication management method and device | |
| RU2714583C1 (en) | Method and system for selecting multidimensional data blocks in electronic information system | |
| US9076172B1 (en) | Generating item suggestions from a profile-based group | |
| CN115222338B (en) | Material purchasing system, purchasing list generation method and component | |
| CN113761327B (en) | Scheduling method, equipment and storage medium of recommendation strategy | |
| CN111062682A (en) | Work order processing method and device | |
| CN113051476B (en) | Method and device for sending message | |
| CN112819619A (en) | Transaction processing method and device | |
| CN113741888A (en) | Service processing method and device | |
| CN111597784A (en) | Information sending method, device, terminal equipment and medium | |
| CN111488537A (en) | Page display method and device | |
| CN111782776A (en) | Method and device for realizing intention identification through slot filling | |
| US10269046B1 (en) | Networked environment that enables interaction between content requestors and content creators | |
| US10896193B2 (en) | Cache fetching of OLAP based data using client to client relationships and data encoding |
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 |