CN111127060B - Method and device for determining popularization users of service - Google Patents
Method and device for determining popularization users of service Download PDFInfo
- Publication number
- CN111127060B CN111127060B CN201811290502.7A CN201811290502A CN111127060B CN 111127060 B CN111127060 B CN 111127060B CN 201811290502 A CN201811290502 A CN 201811290502A CN 111127060 B CN111127060 B CN 111127060B
- Authority
- CN
- China
- Prior art keywords
- user
- determining
- target
- service
- users
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method and a device for determining popularization users of a service, wherein the method comprises the following steps: for a target service, acquiring each first user obtaining a product corresponding to the target service; acquiring a first user portrait of each first user and a second user portrait of all network users; the user portrait comprises at least one characteristic label of the user; determining N target feature labels according to each first user portrait and each second user portrait, wherein N is a positive integer; and determining popularization users of the target service according to the N target feature labels and the second user portraits. According to the method and the device, N target feature labels of users who obtain products corresponding to the service and have positive influences on popularization users of the determined service are selected, the popularization users of the service are selected from the whole network users based on the N target feature labels, the random determination users are not needed any more, and the determined popularization users of the service are accurate and comprehensive.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a method and a device for determining popularization users of a service.
Background
Along with the high popularization of the Internet, whether the development of a lot of Internet services is successful or not is closely related to the active participants, and how to find out suitable people to do accurate service popularization is an urgent problem to be solved.
Currently, the method for determining the popularization users of the service is that for the users who purchase the products corresponding to the service, the users can be used as the popularization users of the service, and for the products corresponding to the service which are never purchased before, a batch of users can only be selected from the users in a random mode to be used as the popularization users of the service. Therefore, the popularization users of the business determined by the current method are not accurate.
Disclosure of Invention
The embodiment of the application provides a method and a device for determining promotion users of a service, which can accurately and comprehensively determine promotion users of the service.
In a first aspect, an embodiment of the present application provides a method for determining a promoting user of a service, including:
for a target service, acquiring each first user of a product corresponding to the target service;
acquiring a first user portrait of each first user and a second user portrait of all network users; the user portrait comprises at least one characteristic label of a user;
determining N target feature labels according to the first user portraits and the second user portraits, wherein N is a positive integer;
and determining popularization users of the target service according to the N target feature labels and the second user portraits.
In one possible design, the determining N target feature labels from each of the first user representation and each of the second user representation includes:
for one feature tag, determining the information value and the evidence weight of the one feature tag according to the number of the first users, the number of all network users, the number of first user portraits comprising the one feature tag and the number of second user portraits comprising the one feature tag;
and determining the N target feature labels according to the information value and the evidence weight of each feature label.
In one possible design, the determining the target feature tag according to the information value and the evidence weight of each feature tag includes:
determining M feature labels with evidence weights of positive values;
and determining N characteristic labels with information values positioned in the first N of the M characteristic labels as the N target characteristic labels.
In one possible design, the determining the popularization user of the target service according to the N target feature labels and each of the second user portraits includes:
and determining a user corresponding to a second user portrait comprising at least one of the N target feature labels as a popularization user of the target service.
In one possible design, the method further comprises:
acquiring a first service related to the target service;
determining K item target retrieval contents according to first retrieval contents of the target service and the first service of a user, wherein K is a positive integer;
acquiring second retrieval contents corresponding to all network users respectively;
determining the popularization user of the target service according to the N target feature labels and the second user portrait, including:
and determining popularization users of the target service according to the N target feature labels, the second user portraits, the K item label search contents and the second search contents.
In one possible design, this includes:
acquiring an independent visitor UV value of the first retrieval content;
determining the first search content with the UV value at the front L as L pieces of preselected search content;
and de-duplicating the search contents with the same semantic meaning in the L pre-selected search contents to obtain K item mark search contents.
In one possible design, the determining the popularization user of the target service according to the N target feature labels, each of the second user portraits, the K item label search content and each of the second search content includes:
determining a first popularization user of the target service according to the N target feature labels and the second user portraits;
determining a second popularization user of the target service according to the K item mark retrieval content and each second retrieval content;
and determining the first popularization user and the second popularization user as popularization users of the target service.
In one possible design, the determining the second popularization user of the target service according to the K item index search content and each second search content includes:
and determining the user corresponding to the second search content with the same semantic meaning as any one of the K item target search contents as the second popularization user of the target service.
In a second aspect, an embodiment of the present application provides an apparatus for determining a promoting user of a service, including:
the acquisition module is used for acquiring each first user of the product corresponding to the target service for the target service;
the acquisition module is also used for acquiring the first user portraits of the first users and the second user portraits of all network users; the user portrait comprises at least one characteristic label of a user;
the determining module is used for determining N target feature labels according to the first user portraits and the second user portraits, wherein N is a positive integer;
and the determining module is further used for determining popularization users of the target service according to the N target feature labels and the second user portraits.
In one possible design, the determining module is specifically configured to:
for one feature tag, determining the information value and the evidence weight of the one feature tag according to the number of the first users, the number of all network users, the number of first user portraits comprising the one feature tag and the number of second user portraits comprising the one feature tag;
and determining the N target feature labels according to the information value and the evidence weight of each feature label.
In one possible design, the determining module is specifically configured to: determining M feature labels with evidence weights of positive values; and determining N characteristic labels with information values positioned in the first N of the M characteristic labels as the N target characteristic labels.
In one possible design, the determining module is specifically configured to: determining a user corresponding to a second user portrait comprising at least one of N target feature labels as a popularization user of the target service
In one possible design, the acquiring module is further configured to acquire a first service related to the target service;
the determining module is further configured to determine, according to first search contents of the user for the target service and the first service, K target search contents, where K is a positive integer;
the acquisition module is further used for acquiring second retrieval contents corresponding to all network users respectively;
the determining module is specifically configured to: and determining popularization users of the target service according to the N target feature labels, the second user portraits, the K item label search contents and the second search contents.
In one possible design, the determining module is specifically configured to:
acquiring an independent visitor UV value of the first retrieval content;
determining the first search content with the UV value at the front L as L pieces of preselected search content;
and de-duplicating the search contents with the same semantic meaning in the L pre-selected search contents to obtain K item mark search contents.
In one possible design, the determining module is specifically configured to: determining a first popularization user of the target service according to the N target feature labels and the second user portraits; determining a second popularization user of the target service according to the K item mark retrieval content and each second retrieval content; and determining the first popularization user and the second popularization user as popularization users of the target service.
In one possible design, the determining module is specifically configured to: and determining the user corresponding to the second search content with the same semantic meaning as any one of the K item target search contents as the second popularization user of the target service.
In a third aspect, embodiments of the present application provide a readable storage medium comprising a program or instructions which, when run on a computer, perform the method of any of the first aspects.
In a fourth aspect, embodiments of the present application provide a server, including: a processor coupled to the memory;
the memory is used for storing a computer program;
the processor is configured to invoke a computer program stored in the memory to implement the method of any of the first aspects.
According to the method, N target feature labels which have positive influences on the popularization users of the determined service and have the information value of the front N are selected from all users of the product corresponding to the service, then the popularization users of the service are selected from the whole network users based on the N target feature labels, the random determination users are not needed, and the determined popularization users of the service are accurate.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief description will be given below of the drawings that are needed in the embodiments or the prior art descriptions, it being obvious that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a flowchart of a method for determining promotion users of a service provided in an embodiment of the present application;
fig. 2 is a flowchart two of a method for determining promotion users of a service according to an embodiment of the present application;
fig. 3 is a flowchart III of a method for determining promotion users of a service according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a device for determining promotion users of a service according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a server according to an embodiment of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of 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 apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The business in this embodiment may be sales products, transacted products, physical products such as watermelon and visa, or non-physical products such as travel.
The popularization user of the service is accurately and comprehensively determined, and the method plays an important role in smooth operation of the service. The method for determining the popularization users of the service is described below by adopting a specific embodiment.
First, a first implementation of a method of determining a promotion user of a service will be described.
Fig. 1 is a flowchart of a method for determining a promoting user of a service provided in an embodiment of the present application, where an execution body of the embodiment may be a device for determining a promoting user of a service, and the device for determining a promoting user of a service may be located in a server, and referring to fig. 1, the method of the embodiment includes:
step S101, for a target service, acquiring each first user of a product corresponding to the target service;
specifically, the target service in this embodiment may be any service, and the target service in this embodiment may be obtained by purchasing or transacting.
The obtaining of each first user obtaining the product corresponding to the target service may be obtaining each first user obtaining the product corresponding to the target service in a preset time period, or obtaining all first users obtaining the product corresponding to the target service in history. Wherein, obtaining each first user obtaining the product corresponding to the target service includes: and obtaining the user of the product corresponding to the target service on line (network) and/or obtaining the user of the product corresponding to the target service off line. Optionally, the obtaining each first user obtaining the product corresponding to the target service includes: and obtaining each first user of the product corresponding to the target service through a network in a preset time period.
For example, the target service is selling xx brand diaper, then each first user who has purchased xx brand diaper over the network in the current previous year may be obtained.
Step S102, acquiring a first user portrait of each first user and a second user portrait of each all network users; the user portrait comprises at least one characteristic label of the user;
specifically, each of the first user portrait and the second user portrait may be generated in advance by a server where a device for determining a promotion user of the service is located, where the generation of the user portrait is a method in the prior art, and will not be described herein.
The user representation includes at least one feature tag of the user, such as a user a's user representation including: men, 35 years old, doctor, like football, etc., then men, 35 years old, doctor, like football, etc. are feature tags for user a.
All network users in this embodiment are network users that can be acquired by a server where a device for determining a service promotion user is located, and the following embodiments are the same.
Step S103, determining N target feature labels according to the first user portrait and the second user portrait, wherein N is a positive integer.
Specifically, in one mode, determining N target feature tags from each first user representation and each second user representation includes:
a1, for one feature tag, determining the information value (information value, IV) and evidence weight (weight of evidence, WOE) of the one feature tag according to the number of first users, the number of all network users, the number of first user portraits comprising the one feature tag and the number of second user portraits comprising the one feature tag;
wherein IV i WOE for the information value corresponding to the ith feature tag i For the evidence weight corresponding to the ith feature label, A i Representing the number of first user portraits including the ith feature tag, B i The number of second user portraits including the ith feature tag in the representation, a represents the number of first users, B represents the number of all network users, i=1, 2, … … I.
The number of the first users is the number of the first user portraits, and the number of the second users is the number of the first user portraits.
And each feature tag obtains the information value and the evidence weight of each feature tag according to the calculation method, and I information values and I evidence weights are obtained in total.
It will be appreciated that I is the number of all non-duplicate feature labels included in each first user representation and each second user representation.
a2, determining N target feature labels according to the information value and the evidence weight of each feature label.
Specifically, determining the target feature tag according to the information value and the evidence weight of each feature tag includes:
a21, determining M feature labels with evidence weights of positive values;
specifically, the evidence weight WOE is a positive value, which indicates that the feature tag has a positive effect on the product corresponding to the target service. Correspondingly, the evidence weight WOE is a positive value, which indicates that the feature tag has negative influence on the product corresponding to the target service. Obviously, in order to determine the popularization users of the target service, feature tags with positive WOE values need to be used.
a22, determining N feature tags with information values at the front N in the M feature tags as the N target feature tags.
Specifically, the larger the information value IV value, the more relevant the feature label will be to the user who will get the product of the target service, i.e. the more useful it will be to distinguish between the product that will get the target service and the product that will not get the target service.
The N feature labels with the information value at the front N refer to: and if the information values are ordered in the order from big to small, N feature labels corresponding to the information values positioned in the front N are arranged.
And step S104, determining popularization users of the target service according to the N target feature labels and the second user portraits.
Specifically, according to the N target feature labels and each second user portrait, determining popularization users of the target service includes:
and determining the user corresponding to the second user portrait comprising at least one of the N target feature labels as the popularization user of the target service.
Such as: the N target tags for this business of selling xxx brand diapers include: like yy country's articles, baby clothes, milk powder. yy is the country to which xxx brand diaper belongs. The users in the second user portrayal of all network users who include the items like yy country are determined to be promoting users of the target service, the users in the user portrayal of all network users who include baby clothes are also determined to be promoting users of the target service, and the users in the user portrayal of all network users who include milk powder are also determined to be promoting users of the target service.
In another embodiment, the N target feature labels may be input by the user after the first user figures and the second user figures are acquired.
In this embodiment, N target feature labels of N, which have positive influence on the popularization user of the determined service and have information values of the first N, of each user of the product corresponding to the obtained service are selected, then the popularization user of the service is selected from the whole network users based on the N target feature labels, and is no longer a random determination user, and the popularization users of the determined service are more accurate and comprehensive.
It should be understood that the sequence numbers of the above processes do not mean the order of execution, and the execution order of the processes should be determined by the functions and internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Next, a second implementation of the method of determining a promotion user of a service will be described.
Fig. 2 is a second flowchart of a method for determining a promoting user of a service provided in an embodiment of the present application, where an execution body of the embodiment may be a device for determining a promoting user of a service, and referring to fig. 2, the method of the embodiment includes:
step S201, for a target service, acquiring a first service related to the target service.
Specifically, the number of first services related to the target service is at least one.
For example, if the target service is a sales japanese and korean tour, the service related to sales xx tour (a kind of country tour) includes: sales of travel products, sales of tax free store items, handling visas, and the like.
Step S202, determining K item target retrieval contents according to first retrieval contents of a target service and a first service of a user.
Specifically, first, a plurality of pieces of first retrieval information for a target service and for a first service by a user are acquired. The first search information includes first search content, for example, the first search content may be how much xx has been in, or how xx has been playing this year, or xx brand skin care product price, or visa, etc. The first search information further includes: the identification of the user and the information of the corresponding webpage are retrieved; wherein retrieving information for the corresponding web page may include retrieving a link for the corresponding web page.
The first search information of the user for the target service and the first service is search information including information for searching the corresponding web page, and only information for searching the corresponding web page is included, which indicates that the search actually occurs, that is, the user inputs not only a search word but also a search instruction (for example, clicks a "search" button to input the search instruction, or clicks a page tag in a page to input the search instruction). And determining K item target retrieval contents by using first retrieval information corresponding to the actually transmitted retrieval, wherein the determined K item target retrieval contents have large relevance to the target service, so that popularization users of the determined target service are more accurate.
Then, according to the first search content of the user aiming at the target service and the first service, determining K item target search content, wherein K is a positive integer, and the method comprises the following steps:
b1, obtaining the independent visitor UV value of the first search content.
For each piece of first search content, the number of non-repeated users corresponding to the piece of first search content is the UV value of the first search content. The user corresponding to the first search content is the user included in the first search information including the first search content.
b2, determining the first search content with the UV value at the front L as L pieces of preselected search content.
The first search content with the UV value at the front L refers to: and if the UV values are ordered in the order from big to small, L first retrieval contents corresponding to the UV values positioned in the front L are obtained.
And b3, de-duplicating the search contents with the same semantic meaning in the L pre-selected search contents to obtain K item target search contents.
Specifically, the search content with the same semantic meaning in the L preselected search contents is de-duplicated to obtain K item target search content. Optionally, corresponding to each group of search contents with the same semantic meaning of the L pre-selected search contents, reserving one search content with the shortest characters in the group to obtain K item mark search contents. For example, a set of semantically identical search content includes: "how to play in Japan this year" and "how to play in Japanese this day", the "how to play in Japan this year" can be removed, and "how to play in Japanese this day" can be retained.
Step S203, obtaining second retrieval contents corresponding to all network users respectively;
specifically, second search information corresponding to all network users is obtained, the second search information comprises second search content, and the second search information further comprises the identification of the user. The second search information may not include information for searching the corresponding web page.
The obtaining of the second search content corresponding to each of all the network users may be obtaining the second search content corresponding to all the network users in a preset time period, or may be obtaining the second search content corresponding to all the network users in all the historical time periods. Obviously, the second search content has a plurality of pieces.
And step S204, determining popularization users of the target service according to the K item mark retrieval contents and the second retrieval contents.
Specifically, a user corresponding to a second search content having the same semantic meaning as any one of the K index search contents is determined as a popularization user of the target service.
For example, the K item mark includes how much money to go to japan in the search content, and if a certain piece of second search content is "how much money to go to japan" or "how much money to go to japan now" or "price of going to the daily travel", the user in the second search information corresponding to the piece of second search content is determined as a popularization user of the target service.
In this embodiment, according to the search content of the user for the target service and the service related to the target service, the multi-item target search content with a high UV value is determined, then the search content corresponding to the whole network user is semantically matched with the target search content, and the user corresponding to the search content with the same semantic as the target search content is the popularization user of the target service. Because the correlation between the search content of the high UV value and the target service is larger, and the popularization user of the target service is determined from the whole network users, the determined popularization user of the target service is more accurate and comprehensive.
It should be understood that the sequence numbers of the above processes do not mean the order of execution, and the execution order of the processes should be determined by the functions and internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Next, a third implementation of the method of determining a promotion user of a service will be described.
Fig. 3 is a flowchart III of a method for determining a promoting user of a service provided in an embodiment of the present application, where an execution body of the embodiment may be a device for determining a promoting user of a service, and referring to fig. 3, the method of the embodiment includes:
step S301, for a target service, acquiring each first user obtaining a product corresponding to the target service;
specifically, step S301 is described with reference to step S101 in the embodiment shown in fig. 1, which is not described herein.
Step S302, acquiring a first user portrait of each first user and a second user portrait of each all network users; the user representation includes at least one feature tag of the user.
Specifically, step S302 is described with reference to step S102 in the embodiment shown in fig. 1, and is not described herein.
Step S303, determining N target feature labels according to each first user portrait and each second user portrait, wherein N is a positive integer.
Specifically, step S303 is described with reference to step S103 in the embodiment shown in fig. 1, which is not described herein.
And step S304, determining a first popularization user of the target service according to the N target feature labels and the second user portraits.
Specifically, step S304 is described with reference to step S104 in the embodiment shown in fig. 1, which is not described herein.
Step S305, a first service related to the target service is acquired.
Specifically, step S305 is described with reference to step S201 in the embodiment shown in fig. 2, and will not be described herein.
Step S306, determining K item target retrieval contents according to the first retrieval contents of the target service and the first service of the user.
Specifically, step S306 is described with reference to step S202 in the embodiment shown in fig. 2, and will not be described herein.
Step S307, obtaining second retrieval contents corresponding to all network users respectively;
specifically, step S307 is described with reference to step S203 in the embodiment shown in fig. 2, and will not be described herein.
Step S308, determining a second popularization user of the target service according to the K item mark retrieval contents and each second retrieval content;
specifically, step S308 is described with reference to step S204 in the embodiment shown in fig. 2, and will not be described herein.
Step S309, determining the first popularization user and the second popularization user as popularization users of the target service.
Specifically, the number of the first popularization users is multiple, the number of the second popularization users is also multiple, repeated users in the plurality of the first popularization users and the plurality of the second popularization users are removed, and the rest users are all popularization users of the target service.
In the embodiment, the promotion user of the target service based on the portrait of the user and the promotion user of the target service based on the retrieval behavior of the user are combined, so that the determined promotion user of the target service is accurate and comprehensive.
It should be understood that the sequence numbers of the above processes do not mean the order of execution, and the execution order of the processes should be determined by the functions and internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present application.
The method for determining the popularization user of the service of the present application is described above with reference to fig. 1 to 3, and the apparatus for determining the popularization user of the service of the present application is described below with reference to fig. 4.
Fig. 4 is a schematic structural diagram of a device for determining a promoting user of a service according to an embodiment of the present application, as shown in fig. 4, where the device in this embodiment may include: an acquisition module 41 and a determination module 42;
the obtaining module 41 is configured to obtain, for a target service, each first user that has obtained a product corresponding to the target service;
the acquiring module 41 is further configured to acquire a first user portrait of each first user and a second user portrait of each all network users; the user portrait comprises at least one characteristic label of a user;
a determining module 42, configured to determine N target feature tags according to each of the first user representation and each of the second user representation, where N is a positive integer;
the determining module 42 is further configured to determine a promoting user of the target service according to the N target feature labels and each of the second user portraits.
In one possible design, the determining module 42 is specifically configured to:
for one feature tag, determining the information value and the evidence weight of the one feature tag according to the number of the first users, the number of all network users, the number of first user portraits comprising the one feature tag and the number of second user portraits comprising the one feature tag;
and determining the N target feature labels according to the information value and the evidence weight of each feature label.
In one possible design, the determining module 42 is specifically configured to: determining M feature labels with evidence weights of positive values; and determining N characteristic labels with information values positioned in the first N of the M characteristic labels as the N target characteristic labels.
In one possible design, the determining module 42 is specifically configured to: determining a user corresponding to a second user portrait comprising at least one of N target feature labels as a popularization user of the target service
In one possible design, the obtaining module 41 is further configured to obtain a first service related to the target service;
the determining module 42 is further configured to determine, according to first search contents of the user for the target service and the first service, K target search contents, where K is a positive integer;
the acquiring module 41 is further configured to acquire second search contents corresponding to all network users;
the determining module 42 is specifically configured to: and determining popularization users of the target service according to the N target feature labels, the second user portraits, the K item label search contents and the second search contents.
In one possible design, the determining module 42 is specifically configured to:
acquiring an independent visitor UV value of the first retrieval content;
determining the first search content with the UV value at the front L as L pieces of preselected search content;
and de-duplicating the search contents with the same semantic meaning in the L pre-selected search contents to obtain K item mark search contents.
In one possible design, the determining module 42 is specifically configured to: determining a first popularization user of the target service according to the N target feature labels and the second user portraits; determining a second popularization user of the target service according to the K item mark retrieval content and each second retrieval content; and determining the first popularization user and the second popularization user as popularization users of the target service.
In one possible design, the determining module 42 is specifically configured to: and determining the user corresponding to the second search content with the same semantic meaning as any one of the K item target search contents as the second popularization user of the target service.
The device of the present embodiment may be used to execute the technical solution of the foregoing method embodiment, and its implementation principle and technical effects are similar, and are not described herein again.
Fig. 5 is a schematic structural diagram of a terminal provided in an embodiment of the present application, referring to fig. 5, a terminal in this embodiment includes: a processor 51, a memory 52 and a communication bus 53, the communication bus 53 being for connecting the processor 51 and the memory 52, the processor 51 being coupled to the memory 52;
the memory 51 is used for storing a computer program;
the processor 52 is configured to invoke the computer program stored in the memory 51 to implement the method in the above-described method embodiment.
Wherein the computer program may also be stored in a memory external to the server.
It should be appreciated that in embodiments of the present application, the processor 52 may be a CPU, and the processor 52 may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or any conventional processor or the like.
The memory 51 may include read only memory and random access memory and provides instructions and data to the processor 52. The memory 51 may also include a nonvolatile random access memory. For example, the memory 51 may also store information of the device type.
The memory 51 may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DR RAM).
The bus 53 may include a power bus, a control bus, a status signal bus, and the like in addition to a data bus. But for clarity of illustration the various buses are labeled as bus 53 in the figures.
The embodiments of the present application provide a readable storage medium comprising a program or instructions which, when run on a computer, performs a method as described in any of the method embodiments described above.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the method embodiments described above may be performed by hardware associated with program instructions. The foregoing program may be stored in a computer readable storage medium. The program, when executed, performs steps including the method embodiments described above; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the embodiments of the present application, and are not limited thereto; although embodiments of the present application have been described in detail with reference to the foregoing embodiments, it will be appreciated by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions.
Claims (11)
1. A method for determining a promotional user of a service, comprising:
for a target service, acquiring each first user of a product corresponding to the target service;
acquiring a first user portrait of each first user and a second user portrait of all network users; the user portrait comprises at least one characteristic label of the user;
determining N target feature labels according to the first user portraits and the second user portraits, wherein N is a positive integer;
determining popularization users of the target service according to the N target feature labels and the second user portraits;
the method further comprises the steps of: acquiring a first service related to the target service;
determining K item target retrieval contents according to first retrieval contents of the target service and the first service of a user, wherein K is a positive integer;
acquiring second retrieval contents corresponding to all network users respectively;
determining the popularization user of the target service according to the N target feature labels and the second user portrait, including:
and determining popularization users of the target service according to the N target feature labels, the second user portraits, the K item label search contents and the second search contents.
2. The method of claim 1, wherein said determining N target feature tags from each of said first user representation and each of said second user representations comprises:
for one feature tag, determining the information value and the evidence weight of the one feature tag according to the number of the first users, the number of all network users, the number of first user portraits comprising the one feature tag and the number of second user portraits comprising the one feature tag;
and determining the N target feature labels according to the information value and the evidence weight of each feature label.
3. The method of claim 2, wherein determining the target feature label based on the information value and the evidence weight of each feature label comprises:
determining M feature labels with evidence weights of positive values;
and determining N characteristic labels with information values positioned in the first N of the M characteristic labels as the N target characteristic labels.
4. A method according to any of claims 1-3, wherein said determining K index search content from the first search content of the user for the target service and the first service comprises:
acquiring an independent visitor UV value of the first retrieval content;
determining the first search content with the UV value at the front L as L pieces of preselected search content;
and de-duplicating the search contents with the same semantic meaning in the L pre-selected search contents to obtain K item mark search contents.
5. A method according to any one of claims 1-3, wherein said determining a promotion user for said target service based on said N target feature labels, each of said second user portraits, said K target search content, and each of said second search content comprises:
determining a first popularization user of the target service according to the N target feature labels and the second user portraits;
determining a second popularization user of the target service according to the K item mark retrieval content and each second retrieval content;
and determining the first popularization user and the second popularization user as popularization users of the target service.
6. The method of claim 5, wherein the determining the second promoting user of the target service according to the K-entry index search content and each second search content comprises:
and determining the user corresponding to the second search content with the same semantic meaning as any one of the K item target search contents as the second popularization user of the target service.
7. An apparatus for determining a promotional user of a service, comprising:
the acquisition module is used for acquiring each first user of the product corresponding to the target service for the target service;
the acquisition module is also used for acquiring the first user portraits of the first users and the second user portraits of all network users; the user portrait comprises at least one characteristic label of a user;
the determining module is used for determining N target feature labels according to the first user portraits and the second user portraits, wherein N is a positive integer;
the determining module is further configured to determine a popularization user of the target service according to the N target feature tags and each of the second user portraits;
the acquisition module is further used for acquiring a first service related to the target service;
the determining module is further configured to determine, according to first search contents of the user for the target service and the first service, K target search contents, where K is a positive integer;
the acquisition module is further used for acquiring second retrieval contents corresponding to all network users respectively;
the determining module is specifically configured to: and determining popularization users of the target service according to the N target feature labels, the second user portraits, the K item label search contents and the second search contents.
8. The apparatus of claim 7, wherein the determining module is specifically configured to:
for one feature tag, determining the information value and the evidence weight of the one feature tag according to the number of the first users, the number of all network users, the number of first user portraits comprising the one feature tag and the number of second user portraits comprising the one feature tag;
and determining the N target feature labels according to the information value and the evidence weight of each feature label.
9. The apparatus according to claim 7 or 8, wherein the determining module is specifically configured to:
acquiring an independent visitor UV value of the first retrieval content;
determining the first search content with the UV value at the front L as L pieces of preselected search content;
and de-duplicating the search contents with the same semantic meaning in the L pre-selected search contents to obtain K item mark search contents.
10. A readable storage medium comprising a program or instructions which, when run on a computer, performs the method of any of claims 1 to 6.
11. A server, comprising: a processor coupled to the memory;
the memory is used for storing a computer program;
the processor is configured to invoke a computer program stored in the memory to implement the method of any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811290502.7A CN111127060B (en) | 2018-10-31 | 2018-10-31 | Method and device for determining popularization users of service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811290502.7A CN111127060B (en) | 2018-10-31 | 2018-10-31 | Method and device for determining popularization users of service |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111127060A CN111127060A (en) | 2020-05-08 |
| CN111127060B true CN111127060B (en) | 2023-08-08 |
Family
ID=70494376
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811290502.7A Active CN111127060B (en) | 2018-10-31 | 2018-10-31 | Method and device for determining popularization users of service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111127060B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102456058A (en) * | 2010-11-02 | 2012-05-16 | 阿里巴巴集团控股有限公司 | Method and device for providing category information |
| CN104239450A (en) * | 2014-09-01 | 2014-12-24 | 百度在线网络技术（北京）有限公司 | Search recommending method and device |
| CN106874922A (en) * | 2015-12-11 | 2017-06-20 | 腾讯科技（深圳）有限公司 | A kind of method and device for determining service parameter |
| CN107092629A (en) * | 2017-01-18 | 2017-08-25 | 北京小度信息科技有限公司 | Recommend method and device |
| CN107220852A (en) * | 2017-05-26 | 2017-09-29 | 北京小度信息科技有限公司 | Method, device and server for determining target recommended user |
| CN107464141A (en) * | 2017-08-07 | 2017-12-12 | 北京京东尚科信息技术有限公司 | For the method, apparatus of information popularization, electronic equipment and computer-readable medium |
| CN107516237A (en) * | 2017-07-22 | 2017-12-26 | 长沙兔子代跑网络科技有限公司 | A kind of drawn a portrait according to user excavates the method and device of generation race client |
| CN107633416A (en) * | 2016-07-18 | 2018-01-26 | 阿里巴巴集团控股有限公司 | A kind of recommendation methods, devices and systems of business object |
| CN107729469A (en) * | 2017-10-12 | 2018-02-23 | 北京小度信息科技有限公司 | Usage mining method, apparatus, electronic equipment and computer-readable recording medium |
| CN107730311A (en) * | 2017-09-29 | 2018-02-23 | 北京小度信息科技有限公司 | A kind of method for pushing of recommendation information, device and server |
| CN108470023A (en) * | 2018-01-18 | 2018-08-31 | 阿里巴巴集团控股有限公司 | The recommendation method and device of business function |
| CN108520058A (en) * | 2018-03-30 | 2018-09-11 | 维沃移动通信有限公司 | A kind of Business Information recommends method and mobile terminal |
-
2018
- 2018-10-31 CN CN201811290502.7A patent/CN111127060B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102456058A (en) * | 2010-11-02 | 2012-05-16 | 阿里巴巴集团控股有限公司 | Method and device for providing category information |
| CN104239450A (en) * | 2014-09-01 | 2014-12-24 | 百度在线网络技术（北京）有限公司 | Search recommending method and device |
| CN106874922A (en) * | 2015-12-11 | 2017-06-20 | 腾讯科技（深圳）有限公司 | A kind of method and device for determining service parameter |
| CN107633416A (en) * | 2016-07-18 | 2018-01-26 | 阿里巴巴集团控股有限公司 | A kind of recommendation methods, devices and systems of business object |
| CN107092629A (en) * | 2017-01-18 | 2017-08-25 | 北京小度信息科技有限公司 | Recommend method and device |
| CN107220852A (en) * | 2017-05-26 | 2017-09-29 | 北京小度信息科技有限公司 | Method, device and server for determining target recommended user |
| CN107516237A (en) * | 2017-07-22 | 2017-12-26 | 长沙兔子代跑网络科技有限公司 | A kind of drawn a portrait according to user excavates the method and device of generation race client |
| CN107464141A (en) * | 2017-08-07 | 2017-12-12 | 北京京东尚科信息技术有限公司 | For the method, apparatus of information popularization, electronic equipment and computer-readable medium |
| CN107730311A (en) * | 2017-09-29 | 2018-02-23 | 北京小度信息科技有限公司 | A kind of method for pushing of recommendation information, device and server |
| CN107729469A (en) * | 2017-10-12 | 2018-02-23 | 北京小度信息科技有限公司 | Usage mining method, apparatus, electronic equipment and computer-readable recording medium |
| CN108470023A (en) * | 2018-01-18 | 2018-08-31 | 阿里巴巴集团控股有限公司 | The recommendation method and device of business function |
| CN108520058A (en) * | 2018-03-30 | 2018-09-11 | 维沃移动通信有限公司 | A kind of Business Information recommends method and mobile terminal |
Non-Patent Citations (1)
| Title |
|---|
| 鲁墨.基于用户画像的推荐系统的设计与实现.《万方中国学位论文数据库》.2017,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111127060A (en) | 2020-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107729937B (en) | Method and device for determining user interest tag | |
| CN111523976A (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| CN106295832A (en) | Product information method for pushing and device | |
| EP2791832A1 (en) | Personalized information pushing method and device | |
| CN107003987A (en) | Enhanced search query suggestion | |
| CN107633416B (en) | Method, device and system for recommending service object | |
| CN107341173A (en) | A kind of information processing method and device | |
| US11609919B2 (en) | Methods and apparatus for automatically providing personalized search results | |
| CN112579941A (en) | Information processing method, device, equipment and storage medium | |
| US9460163B1 (en) | Configurable extractions in social media | |
| CN109597934B (en) | Method and device for determining click recommendation words, storage medium and electronic equipment | |
| US11216519B2 (en) | Methods and apparatus for automatically providing personalized search results | |
| CN111353836B (en) | Commodity recommendation method, device and equipment | |
| CN111127060B (en) | Method and device for determining popularization users of service | |
| EP3731108A1 (en) | Search system, search method, and program | |
| CN111767457A (en) | Recommendation method and device | |
| CN110113410A (en) | A kind of management method, device, electronic equipment and the storage medium of information push | |
| CN113254623B (en) | Data processing method, device, server, medium and product | |
| CN112115258B (en) | Credit evaluation method and device for user, server and storage medium | |
| CN113781171A (en) | Information pushing method, device, equipment and storage medium | |
| CN113111259A (en) | Subscription number content pushing method, device, equipment and storage medium | |
| CN112256943A (en) | Portal portrait extraction method based on combination of natural language processing and knowledge graph | |
| CN111695922A (en) | Potential user determination method and device, storage medium and electronic equipment | |
| CN111507366B (en) | Training method of recommendation probability model, intelligent completion method and related device | |
| CN113254622B (en) | Knowledge point query method, knowledge point query device and knowledge point query server |
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 |