CN111080401A - Age estimation method and device - Google Patents
Age estimation method and device Download PDFInfo
- Publication number
- CN111080401A CN111080401A CN201911166552.9A CN201911166552A CN111080401A CN 111080401 A CN111080401 A CN 111080401A CN 201911166552 A CN201911166552 A CN 201911166552A CN 111080401 A CN111080401 A CN 111080401A
- Authority
- CN
- China
- Prior art keywords
- age group
- age
- preset
- behavior
- intersection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 description 172
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 9
- 238000003860 storage Methods 0.000 description 7
- 239000008267 milk Substances 0.000 description 6
- 210000004080 milk Anatomy 0.000 description 6
- 235000013336 milk Nutrition 0.000 description 6
- 239000000843 powder Substances 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
-
- 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
- G06Q30/0203—Market surveys; Market polls
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an age estimation method and device, and belongs to the technical field of internet. The method comprises the following steps: acquiring a plurality of behavior records associated with user identification, wherein each behavior record comprises an applicable age range and a corresponding behavior category of a commodity; dividing each behavior record into corresponding preset age groups according to the respective applicable age groups; taking intersection from all behavior records in each preset age group according to behavior categories, and obtaining a target age group corresponding to each preset age group according to the intersection taking result; and estimating a final age group corresponding to the user identifier according to the target age group corresponding to each preset age group. According to the embodiment of the invention, the age groups of children and children of the user can be estimated, so that the accuracy of recommending children commodities to the user can be improved.
Description
Technical Field
The invention relates to the technical field of internet, in particular to an age estimation method and device.
Background
In recent years, electronic commerce is continuously developed, online shopping is more and more common for users by browsing electronic commerce websites, meanwhile, the electronic commerce websites can provide accurate recommendation for the users by constructing user tags, however, for users with children, due to the fact that children are different in age group, the applicability of children commodities is also different, the age of the children of the users is obtained, and the accuracy of recommending the children commodities to the users can be improved.
At present, the internet e-commerce acquires the age of children of a user, which is mainly based on the personal information of the user and mainly based on the child information filled by the user, and although the confidence coefficient of the method is higher, the method is limited by the requirement of the user to actively fill in the information; in addition, although the user information integrity can also be improved by some incentive marketing means, the effect is often limited.
Disclosure of Invention
In order to solve the technical problems mentioned in the background art, the invention provides an age estimation method and an age estimation device, which can estimate the age bracket of a child of a user, so that the accuracy of recommending children commodities to the user can be improved. The embodiment of the invention provides the following specific technical scheme:
in a first aspect, there is provided an age estimation method, the method comprising:
acquiring a plurality of behavior records associated with user identification, wherein each behavior record comprises an applicable age range of a commodity and a corresponding behavior category;
dividing each behavior record into corresponding preset age groups according to respective applicable age groups;
performing intersection taking on all the behavior records in each preset age group according to behavior categories, and acquiring a target age group corresponding to each preset age group according to intersection taking results;
and estimating a final age group corresponding to the user identifier according to the target age group corresponding to each preset age group.
Further, the dividing the behavior records into corresponding preset age groups according to the respective applicable age groups comprises:
calculating a midpoint value corresponding to the applicable age group in each behavior record according to the left endpoint value and the right endpoint value corresponding to the applicable age group in each behavior record;
and in a plurality of preset age groups, dividing each behavior record into preset age groups in which the corresponding midpoint values fall.
Further, the intersecting set of all the behavior records in each preset age group is taken according to behavior categories, and a target age group corresponding to each preset age group is obtained according to the intersecting set taking result, including:
performing intersection taking on applicable age groups in all the behavior records in all the preset age groups according to behavior categories to obtain intersection results of all non-empty sets in all the preset age groups;
and taking intersection of intersection results of all the non-empty sets in each preset age group to obtain a target age group corresponding to each preset age group.
Further, the acquiring an intersection result of the non-empty sets in each preset age group by taking an intersection of applicable age groups in each behavior record in each preset age group according to behavior categories includes:
and respectively executing the following operations aiming at each behavior category in each preset age group:
judging whether the largest left endpoint value is less than or equal to the smallest right endpoint value in the left endpoint values and the right endpoint values of all applicable age groups corresponding to the behavior categories;
if so, taking the age range from the maximum left endpoint value to the minimum right endpoint value as the intersection result of the non-empty sets corresponding to the behavior categories;
and if not, filtering all applicable age groups corresponding to the behavior types as invalid data.
Further, the intersecting the intersection results of all the non-empty sets in each preset age group to obtain a target age group corresponding to each preset age group includes:
and aiming at each preset age group, respectively executing the following operations:
judging whether the largest left endpoint value is smaller than or equal to the smallest right endpoint value in the left endpoint value and the right endpoint value corresponding to the intersection result of all the non-empty sets in the preset age group;
if so, taking the age group between the maximum left endpoint value and the minimum right endpoint value as a target age group corresponding to the preset age group;
and if not, determining the intersection result of the non-empty sets corresponding to the behavior categories with high priority as the target age group corresponding to the preset age group according to the priority order of each behavior category.
Further, the estimating a final age group corresponding to the user identifier according to a target age group corresponding to each of the preset age groups includes:
taking intersection of the target age groups corresponding to all the preset age groups, and judging whether an intersection age group of a non-empty set corresponding to the user identifier exists or not;
if so, taking the intersection age group of the non-empty set corresponding to the user identifier as a final age group corresponding to the user identifier;
if not, judging whether the number of all the target age groups is two or not;
if so, taking the two target age groups as two final age groups corresponding to the user identification;
and if not, determining all the target age groups as invalid data.
Further, the method further comprises:
and scoring the final age group according to a preset scoring rule and the occurrence frequency of each behavior category in each preset age group.
Further, the scoring the final age group according to a preset scoring rule and the occurrence number of each behavior category in each preset age group includes:
obtaining the rating values corresponding to the behavior categories in the preset age groups according to the corresponding relation between the behavior times and the rating values in the preset rating rules;
calculating the score value of a target age group in each preset age group according to the score value corresponding to each behavior category in each preset age group;
and calculating the score value of the final age group according to the calculated score value of the target age group in each preset age group.
Further, the method further comprises:
and outputting the final age group corresponding to the user identification and the reliability grade obtained based on the scoring value of the final age group.
In a second aspect, there is provided an age estimation apparatus, the apparatus comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a plurality of behavior records associated with user identifications, and each behavior record comprises an applicable age group and a corresponding behavior category of a commodity;
the age dividing module is used for dividing each behavior record into corresponding preset age groups according to the respective applicable age groups;
the intersection taking module is used for taking an intersection of all the behavior records in the preset age groups according to behavior categories;
the second acquisition module is used for acquiring a target age group corresponding to each preset age group according to the intersection acquisition result;
and the age estimation module is used for estimating a final age group corresponding to the user identifier according to the target age group corresponding to each preset age group.
Further, the age grouping module is specifically configured to:
calculating a midpoint value corresponding to the applicable age group in each behavior record according to the left endpoint value and the right endpoint value corresponding to the applicable age group in each behavior record;
and in a plurality of preset age groups, dividing each behavior record into preset age groups in which the corresponding midpoint values fall.
Further, the intersection fetching module comprises:
the first intersection taking submodule is used for taking an intersection of applicable age groups in all the behavior records in each preset age group according to behavior categories to obtain an intersection result of all non-empty sets in each preset age group;
and the second intersection fetching submodule is used for fetching the intersection of the intersection results of all the non-empty sets in each preset age group to obtain a target age group corresponding to each preset age group.
Further, the first intersection fetching submodule is specifically configured to:
and respectively executing the following operations aiming at each behavior category in each preset age group:
judging whether the largest left endpoint value is less than or equal to the smallest right endpoint value in the left endpoint values and the right endpoint values of all applicable age groups corresponding to the behavior categories;
if so, taking the age range from the maximum left endpoint value to the minimum right endpoint value as the intersection result of the non-empty sets corresponding to the behavior categories;
and if not, filtering all applicable age groups corresponding to the behavior types as invalid data.
Further, the second intersection fetching submodule is specifically configured to:
and aiming at each preset age group, respectively executing the following operations:
judging whether the largest left endpoint value is smaller than or equal to the smallest right endpoint value in the left endpoint value and the right endpoint value corresponding to the intersection result of all the non-empty sets in the preset age group;
if so, taking the age group between the maximum left endpoint value and the minimum right endpoint value as a target age group corresponding to the preset age group;
and if not, determining the intersection result of the non-empty sets corresponding to the behavior categories with high priority as the target age group corresponding to the preset age group according to the priority order of each behavior category.
Further, the age estimation module is specifically configured to:
taking intersection of the target age groups corresponding to all the preset age groups, and judging whether an intersection age group of a non-empty set corresponding to the user identifier exists or not;
if so, taking the intersection age group of the non-empty set corresponding to the user identifier as a final age group corresponding to the user identifier;
if not, judging whether the number of all the target age groups is two or not;
if so, taking the two target age groups as two final age groups corresponding to the user identification;
and if not, determining all the target age groups as invalid data.
Further, the apparatus further comprises:
the score acquisition module is used for acquiring the score corresponding to each behavior category in each preset age group according to a preset scoring rule and the occurrence frequency of each behavior category in each preset age group;
the first calculation module is used for calculating the score value of a target age group in each preset age group according to the score value corresponding to each behavior category in each preset age group;
and the second calculation module is used for calculating the score value of the final age group according to the calculated score value of the target age group in each preset age group.
Further, the apparatus further comprises:
and the result output module is used for outputting the final age group corresponding to the user identification and the reliability grade obtained based on the scoring value of the final age group.
In a third aspect, a computer device is provided, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the age estimation method according to any one of the first aspect.
In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the age estimation method according to any one of the first aspect.
The embodiment of the invention provides an age estimation method and device, wherein a plurality of behavior records associated with a user identifier are obtained, each behavior record is divided into corresponding preset age groups according to the respective applicable age group based on the applicable age group of a commodity contained in each behavior record, then intersection is taken according to behavior types for all the behavior records in each preset age group, a target age group corresponding to each preset age group is obtained according to the result of the intersection taking, and finally, a final age group corresponding to the user identifier is estimated according to the target age group corresponding to each preset age group. Therefore, according to the technical scheme of the embodiment of the invention, the suitable age groups and the behavior types of the commodities in the user behavior record and the preset age groups are combined for carrying out the hierarchical processing, so that the age groups of the children of the user can be accurately estimated, the commodities can be recommended to the user according to the age groups of the children of the user, and the purpose of accurately recommending the commodities is realized.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of an age estimation method according to an embodiment of the present invention;
FIG. 2 is a detailed flowchart of step S12 of the method shown in FIG. 1;
FIG. 3 is a detailed flowchart of step S13 of the method shown in FIG. 1;
FIG. 4 is a detailed flowchart of step S14 of the method shown in FIG. 1;
FIG. 5 is a flow chart of another age estimation method according to an embodiment of the present invention;
fig. 6 is a block diagram of an age estimation apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
It is to be understood that, unless the context clearly requires otherwise, throughout the description and the claims, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including, but not limited to".
Furthermore, in the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified.
Fig. 1 is a flowchart of an age estimation method according to an embodiment of the present invention, where the method may be applied to a computer device, such as a server, and as shown in fig. 1, the method may include steps S11 to S14:
step S11, acquiring a plurality of behavior records associated with the user identifier, where each behavior record includes an applicable age group of the commodity and a corresponding behavior category.
Specifically, the process may include:
acquiring a user historical behavior log, wherein the user historical behavior log comprises various behavior data generated by various operation behaviors of a common user on a commodity, and the common user is a user different from a purchasing user and a large client;
respectively extracting a user identifier, a commodity ID (identity) and a behavior category of an operation behavior generated by a user from each behavior data, and acquiring an applicable age group of the commodity according to the commodity ID, wherein the user identifier can be a user registration account or other unique identifiers of the user;
and respectively forming a behavior record by extracting the user identification, the commodity ID, the behavior category and the applicable age bracket of the commodity from each behavior data to obtain a plurality of behavior records associated with the user identification.
Wherein the operation behavior comprises at least one of: the behavior that a user browses commodities, collects the commodities, adds the commodities into a virtual shopping cart, submits orders and pays the commodities on online platforms such as websites and APPs, and correspondingly, the behavior categories comprise at least one of the following behaviors: browsing, collecting, purchasing and purchasing.
In this embodiment, the commodities are children commodities, and the commodities in the user history behavior log can be identified as the children commodities according to the preset commodity category, for example, the commodities belong to children, such as milk powder, children toys, and diapers. Different children class commodity, the applicable age bracket that corresponds is also different, and if the model is different for the commodity that belongs to same kind of children class commodity, the applicable age bracket that corresponds is also different, for example, 0 ~ 6 months children are suitable for 1 section milk powder, 6 ~ 12 months children are suitable for 2 sections milk powder, 1 ~ 3 years children are suitable for 3 sections milk powder, 3 years children are suitable for 4 sections milk powder. Of course, the classification of other products of children, not just milk powder, is similar.
Wherein, the above-mentioned obtaining the applicable age bracket of the goods according to the goods ID may include:
inquiring the applicable age bracket of the commodity from a preset database for the commodity ID, wherein the preset database stores the corresponding relation between the commodity ID and the applicable age bracket of the commodity in advance, and the corresponding relation can be set in advance according to the actual applicable range of the commodity; if the applicable age bracket of the commodity cannot be inquired, resolving a key field from the name of the commodity and/or the commodity description data according to a preset business rule, and determining the applicable age bracket of the commodity according to the key field. In this embodiment, the applicable age group of the commodity may be recorded as the corresponding left and right endpoint values, and if there is no left endpoint value, it is recorded as 0; if there is no right endpoint value, it is recorded as 168 (in "month").
For example, if "baby" is included in the key field, the applicable age groups for the product are: 0-12, if the key fields include "1 paragraph" and "infant", then the applicable age group of the product is: 0 to 6.
And step S12, dividing each behavior record into corresponding preset age groups according to the respective applicable age groups.
Wherein, according to the characteristics of child in different stages, divide into a plurality of preset age brackets with child age bracket in advance, for example, in an example, can divide child age into 6 preset age brackets, do in proper order: 0 to 6, 6 to 12, 12 to 24, 24 to 36, 36 to 72 and 72+ of which the age units in the present embodiment are "months".
It should be noted that, the embodiment of the present invention does not limit the specific preset age group.
In a preferred example, as shown in fig. 2, the implementation process of the step S12 may include:
and S121, calculating a midpoint value corresponding to the applicable age group in each behavior record according to the left endpoint value and the right endpoint value corresponding to the applicable age group in each behavior record.
And S122, dividing each behavior record into preset age groups in which corresponding midpoint values fall in a plurality of preset age groups.
For example, taking the above 6 preset age groups as an example, assume that the applicable age groups of the goods in one behavior record of the user a are: 0-18, with a corresponding midpoint value of 9, the behavior record will be divided into a second predetermined age group, namely: 6-12; assume that the applicable age bracket of the product in the other behavior record of user a is: 12-24, with a midpoint value of 18, the behavior record will be divided into a third predetermined age group, namely: 12 to 24.
In this embodiment, the midpoint value corresponding to the applicable age group of the commodity in the behavior record is calculated for each behavior record, and the preset age group in which the corresponding midpoint value falls is determined, so that the behavior record can be divided into the preset age groups in which the corresponding midpoint values fall.
And step S13, performing intersection extraction on all behavior records in each preset age group according to behavior categories, and acquiring a target age group corresponding to each preset age group according to the intersection extraction result.
In a preferred example, as shown in fig. 3, the implementation process of the step S13 may include:
s131, intersection is taken for applicable age groups in all behavior records in all the preset age groups according to behavior categories, and intersection results of all non-empty sets in all the preset age groups are obtained.
Specifically, for each behavior category in each preset age group, the following operations are respectively performed:
judging whether the largest left endpoint value is less than or equal to the smallest right endpoint value in the left endpoint value and the right endpoint value of all applicable age groups corresponding to the behavior category; if so, taking the age range from the maximum left endpoint value to the minimum right endpoint value as the intersection result of the non-empty sets corresponding to the behavior category; and if not, filtering all applicable age groups corresponding to the behavior type as invalid data.
In this embodiment, for all behavior records falling within the same preset age group, the maximum value of the left end point values and the minimum value of the right end point values of all corresponding applicable age groups may be taken out according to the behavior category, and whether a contradiction exists between the data is compared, and if the maximum value of the left end point values is less than or equal to the minimum value of the right end point values, it may be determined that an intersection of non-empty sets exists between the same user ID and all applicable age groups corresponding to the same behavior category in the preset age group, and the age group from the maximum value of the left end point values to the minimum value of the right end point values is regarded as a new record. If the maximum value in the left end point value is greater than the minimum value in the right end point value, it can be determined that all applicable age groups corresponding to the same user ID and the same behavior category in the preset age group are invalid records, and filtering is performed. Therefore, the user identification, the behavior category of the user and the intersection age bracket corresponding to the behavior category can be obtained in each corresponding preset age bracket.
For example, suppose that the applicable age groups of different commodities in all the behavior records of the purchasing behavior classified by the user a into the third preset age group (i.e. 12-24) are respectively: 6-30, 18-24 and 0-36, wherein the largest left endpoint value and the smallest right endpoint value in the left endpoint value and the right endpoint value of the age groups are 18 and 24 respectively, and the intersection result corresponding to the purchasing behavior in the third preset age group is 18-24.
And S132, taking intersection of intersection results of all the non-empty sets in each preset age group to obtain a target age group corresponding to each preset age group.
Specifically, for each preset age group, the following operations are respectively performed:
judging whether the largest left endpoint value is less than or equal to the smallest right endpoint value in the left endpoint value and the right endpoint value corresponding to the intersection result of all the non-empty sets in the preset age group; if so, taking the age group between the maximum left endpoint value and the minimum right endpoint value as a target age group corresponding to a preset age group; and if not, determining the intersection result of the non-empty sets corresponding to the behavior categories with high priority as the target age group corresponding to the preset age group according to the priority order of each behavior category.
In this embodiment, the intersection is taken again for the intersection result of all the non-empty sets in each preset age group obtained in step S131, and the purpose is to remove the behavior category. Under the same preset age range, acquiring the maximum value of the left end point value and the minimum value of the right end point value corresponding to the intersection result of all the non-empty sets, judging whether the maximum value of the left end point value is smaller than or equal to the minimum value of the right end point value, if the maximum value of the left end point value is larger than the minimum value of the right end point value in the intersection process, keeping the intersection result corresponding to the behavior class with high priority according to the priority sequence of the behavior class, and removing the intersection result corresponding to the behavior class with low priority. In a preferred example, the priority order of the behavior categories may be set as: buy > collect > browse. And if the maximum value of the left endpoint value is less than or equal to the minimum value in the right endpoint value, taking the age group between the maximum value of the left endpoint and the minimum value of the right endpoint as the target age group corresponding to the preset age group. Thus, it is possible to obtain (one or more) qualified target age groups corresponding to the user identifiers, wherein at most one corresponding preset age group can only correspond to one target age group.
And step S14, estimating the final age bracket corresponding to the user identification according to the target age bracket corresponding to each preset age bracket.
Specifically, as shown in fig. 4, the implementation process of step S14 may include:
and S141, taking intersection of target age groups corresponding to all preset age groups, judging whether an intersection age group of a non-empty set corresponding to the user identifier exists, if so, executing the step S142, and otherwise, executing the step S143.
Specifically, in the left end point value and the right end point value corresponding to all the target age groups, whether the largest left end point value is smaller than or equal to the smallest right end point value is judged, if the largest value in the left end point values is smaller than or equal to the smallest value in the right end point values, the intersection age group corresponding to the user identifier can be determined to be a non-empty set, and if the largest value in the left end point values is larger than the smallest value in the right end point values, the intersection age group corresponding to the user identifier can be determined to be an empty set.
And S142, taking the intersection age group of the non-empty set corresponding to the user identification as the final age group corresponding to the user identification.
And S143, judging whether the number of all the target age groups is two, if so, taking the two target age groups as two final age groups corresponding to the user identification, and if not, determining all the target age groups as invalid data.
In this embodiment, an intersection is taken through all corresponding target age groups corresponding to the preset age groups of the user, and if the intersection result indicates that there is an intersection age group of a non-empty set, the intersection age group is determined as the age group of a child of the user. If the intersection result indicates that there are only two target age groups (i.e., there are only two preset age groups into which the user behavior record is divided), it may be assumed that the user has two children, and the two target age groups are used as the age groups of the two children, and if there are more than two target age groups, all the target age groups are regarded as invalid data.
The age estimation method provided by the embodiment of the present invention is further described below by using a specific example.
If the applicable age groups and behavior classes of the commodities in each behavior record of the user a are respectively shown in the 1 st column and the 2 nd column in the following table 1, the behavior records are classified into corresponding preset age groups according to the respective applicable age groups, the classified preset age groups can be referred to the 3 rd column in the table 1 (only two preset age groups), the intersection age groups under the behavior classes shown in the 4 th column in the following table 1 can be obtained by intersecting the applicable age groups in all the behavior records in each classified preset age group according to the behavior classes, the target age groups under the preset age groups shown in the 5 th column in the following table 1 can be obtained by intersecting the intersection age groups under all the behavior classes in each preset age group, wherein, in the preset age groups 12-24, because the intersection age group corresponding to the purchasing behavior is 18-24, the intersection age group corresponding to the collecting behavior is 9-16, and the intersection age group of the purchasing behavior and the collecting behavior is an empty set, the priority of the combined purchasing behavior is higher than that of the collecting behavior, and then the intersection age group 18-24 corresponding to the purchasing behavior is used as a target age group corresponding to the preset age group 12-24. By taking the intersection of the target age groups corresponding to the preset age groups of 0-6 and the target age groups corresponding to the preset age groups of 12-24, the intersection age groups of the two are empty sets, and the number of the target age groups is only two, so that the two target age groups can be regarded as the age groups of two children of the user a, namely, the age group of one child is 0-6, the age group of the other child is 18-24, and the age units are all 'months'.
Table 1:
the embodiment of the invention provides an age estimation method, which comprises the steps of obtaining a plurality of behavior records associated with a user identifier, dividing each behavior record into corresponding preset age groups according to the respective applicable age groups based on the applicable age groups of commodities contained in each behavior record, then taking intersection of all behavior records in each preset age group according to behavior types, obtaining target age groups corresponding to the preset age groups according to the result of taking intersection, and finally estimating the final age group corresponding to the user identifier according to the target age groups corresponding to the preset age groups. Therefore, according to the technical scheme of the embodiment of the invention, the suitable age groups and the behavior types of the commodities in the user behavior record and the preset age groups are combined for carrying out the hierarchical processing, so that the age groups of the children of the user can be accurately estimated, the commodities can be recommended to the user according to the age groups of the children of the user, and the purpose of accurately recommending the commodities is realized.
Fig. 5 is a flowchart of another age estimation method according to an embodiment of the present invention, which may be applied to a computer device, such as a server, and as shown in fig. 5, the method may include the steps of:
and S51, acquiring a plurality of behavior records associated with the user identifier, wherein each behavior record comprises an applicable age group and a corresponding behavior category of the commodity.
Specifically, the implementation process of step S51 can refer to step S11, which is not described herein again.
And S52, dividing the behavior records into corresponding preset age groups according to the applicable age groups.
Specifically, the implementation process of step S52 can refer to step S12, which is not described herein again.
And S53, performing intersection extraction on all behavior records in each preset age group according to the behavior types.
Specifically, the implementation process of step S53 can refer to step S13, which is not described herein again.
And S54, obtaining the corresponding rating value of each behavior category in each preset age group according to the preset rating rule and the occurrence frequency of each behavior category in each preset age group.
The preset scoring rule records the corresponding relationship between the occurrence frequency of different behavior categories and different scoring values in advance.
Specifically, according to the real ages of children of a plurality of sample users, the corresponding relation between the occurrence times and the accuracy of the behavior categories is counted, and under the condition that the score is 100 points, the score distribution condition of different occurrence times of each behavior category is established. For example, the preset scoring rules may be as shown in table 2 below:
table 2:
table 2 is for illustration only, and the embodiment of the present invention is not limited thereto.
In this embodiment, the score values corresponding to the behavior categories in each preset age group can be quickly obtained through the preset score rules, and the score values corresponding to the occurrence times of each behavior category can be recorded as: score _ wtijWhere j is 1, 2, 6 indicates the above six preset age stages, and i is 1, 2, 3, 4 indicates the above four behavior categories.
And S55, acquiring the target age groups corresponding to the preset age groups according to the intersection acquisition result.
Specifically, the implementation process of step S55 can refer to step S13, which is not described herein again.
And S56, calculating the score value of the target age group in each preset age group according to the score value corresponding to each behavior class in each preset age group.
Specifically, the score value score _ wt of the target age group within the jth preset age group is calculated according to the following calculation formulaj：
Wherein n isijRepresents the number of occurrences of the i-th behavior class at the j-th preset age stage, score _ wtijAnd (4) a scoring value corresponding to the occurrence frequency of the ith behavior category in the jth preset age stage.
And S57, estimating the final age bracket corresponding to the user identifier according to the target age bracket corresponding to each preset age bracket.
Specifically, the implementation process of step S57 can refer to step S14, which is not described herein again.
S58, calculating the score of the final age group according to the calculated score of the target age group in each preset age group.
Specifically, by performing the intersection operation on the target age groups corresponding to all the corresponding preset age groups of the user in the step S57, the intersection operation results include the following three cases:
a. if the intersection result indicates that there is an intersection age group of non-empty sets, the user is marked to have a child, and the intersection age group is determined as the age group of a child of the user, and the score value score of the age group can be calculated by using the following formula:
wherein n isijRepresents the number of occurrences of the i-th behavior class at the j-th preset age stage, score _ wtjIndicating the score value of the target age group at the jth preset age group.
b. Taking the intersection result indicates that there are empty sets of intersection age groups, but there are just two target age groups (that is, there are only two preset age groups into which all behavior records of the user are divided), it can be inferred that the user has two children, and the two target age groups are taken as the age groups of the two children, and the score value of the age group of each child is equal to the score value of the target age group in the respective preset age group.
c. Taking the intersection result indicates that there are the intersection age groups of the empty sets, but taking more than two target age groups before the intersection (that is, the preset age groups divided by all the behavior records of the user are more than two), at this time, regarding all the target age groups as invalid data of the user identifier, which indicates that the age groups of the children of the user cannot be estimated.
It is understood that the higher the score value of the final age group, the greater the accuracy of the final age group estimation.
And S59, outputting the final age group corresponding to the user identification and the reliability grade obtained based on the scoring value of the final age group.
The reliability grade corresponding to the score value can be determined according to the corresponding relation between the preset score value and the reliability grade, and the reliability grade is used for indicating the accuracy of the final age group corresponding to the user identifier.
In one example, child real age data for a plurality of sample users is tested to establish a correspondence between score values and reliability ratings, as shown in Table 3 below:
table 3:
| SCORE | DEPEND_LVL |
| >＝80 | good |
| >＝60&&<80 | medium |
| <60 | bad |
table 3 is for illustration only, and the embodiment of the present invention is not limited thereto.
Further, the method may further comprise:
and inquiring whether the real age information corresponding to the user identification exists or not, if so, preferentially outputting the real age data corresponding to the user identification, and otherwise, outputting the final age group corresponding to the user identification and the reliability grade obtained based on the score value of the final age group.
In this embodiment, the real age information sources include two types: front-end registration and collection, if the real age information corresponding to the user identifier is collected, the output result is finally output by taking the collected real age information as final output, if the real age information corresponding to the user identifier is not collected, but the age registration information corresponding to the user identifier is inquired, the age registration information is finally output, label scores under the two results are marked as 100, and if the real age information corresponding to the user identifier is not collected and the age registration information corresponding to the user identifier is not inquired, the final age group corresponding to the user identifier obtained in the step S59 and the reliability grade obtained based on the score value of the final age group are taken as final output results.
The embodiment of the invention provides an age estimation method, which comprises the steps of obtaining the rating values corresponding to all behavior categories in all preset age groups by using a preset rating rule in the process of estimating the final age group corresponding to a user identifier, and calculating the rating values of target age groups in all the preset age groups based on the rating values corresponding to all the behavior categories in all the preset age groups; and calculating the score value of the final age group according to the calculated score values of the target age groups in the preset age groups, so that the accuracy of the estimation of the final age group can be evaluated by using the score value of the final age group.
It should be understood that, although the steps in the flowcharts of fig. 1 to 5 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
Fig. 6 is a block diagram of an age estimation apparatus according to an embodiment of the present invention, and as shown in fig. 6, the apparatus may include:
the first obtaining module 61 is configured to obtain a plurality of behavior records associated with the user identifier, where each behavior record includes an applicable age group of the commodity and a corresponding behavior category;
an age dividing module 62, configured to divide each behavior record into corresponding preset age groups according to the respective applicable age groups;
the intersection taking module 63 is used for taking an intersection of all the behavior records in each preset age group according to the behavior category;
a second obtaining module 64, configured to obtain target age groups corresponding to the preset age groups according to the intersection obtaining result;
and the age estimation module 65 is configured to estimate a final age group corresponding to the user identifier according to a target age group corresponding to each preset age group.
Further, the age grouping module 62 is specifically configured to:
calculating a midpoint value corresponding to the applicable age group in each behavior record according to the left endpoint value and the right endpoint value corresponding to the applicable age group in each behavior record;
and dividing each behavior record into preset age groups in which the corresponding midpoint values fall in the plurality of preset age groups.
Further, the intersection fetching module 63 includes:
the first intersection taking submodule is used for taking intersections of applicable age groups in all the behavior records in all the preset age groups according to behavior categories to obtain intersection results of all non-empty sets in all the preset age groups;
and the second intersection fetching submodule is used for fetching the intersection of the intersection results of all the non-empty sets in each preset age group to obtain the target age group corresponding to each preset age group.
Further, the first intersection fetching submodule is specifically configured to:
aiming at each behavior category in each preset age group, the following operations are respectively executed:
judging whether the largest left endpoint value is less than or equal to the smallest right endpoint value in the left endpoint value and the right endpoint value of all applicable age groups corresponding to the behavior category;
if so, taking the age range from the maximum left endpoint value to the minimum right endpoint value as the intersection result of the non-empty sets corresponding to the behavior categories;
and if not, filtering all applicable age groups corresponding to the behavior types as invalid data.
Further, the second intersection fetching submodule is specifically configured to:
for each preset age group, the following operations are respectively executed:
judging whether the largest left endpoint value is less than or equal to the smallest right endpoint value in the left endpoint value and the right endpoint value corresponding to the intersection result of all the non-empty sets in the preset age group;
if so, taking the age group between the maximum left endpoint value and the minimum right endpoint value as a target age group corresponding to a preset age group;
and if not, determining the intersection result of the non-empty sets corresponding to the behavior categories with high priority as the target age group corresponding to the preset age group according to the priority order of each behavior category.
Further, the age estimation module 65 is specifically configured to:
taking intersection of target age groups corresponding to all preset age groups, and judging whether an intersection age group of a non-empty set corresponding to the user identification exists or not;
if so, taking the intersection age group of the non-empty set corresponding to the user identifier as a final age group corresponding to the user identifier;
if not, judging whether the number of all the target age groups is two or not;
if so, taking the two target age groups as two final age groups corresponding to the user identification;
if not, all target age groups are determined as invalid data.
Further, the apparatus further comprises:
the score acquisition module is used for acquiring the score corresponding to each behavior category in each preset age group according to the preset scoring rule and the occurrence frequency of each behavior category in each preset age group;
the first calculation module is used for calculating the score value of a target age group in each preset age group according to the score value corresponding to each behavior class in each preset age group;
and the second calculating module is used for calculating the score value of the final age group according to the calculated score values of the target age groups in the preset age groups.
Further, the apparatus further comprises:
and the result output module is used for outputting the final age group corresponding to the user identification and the reliability grade obtained based on the scoring value of the final age group.
The age estimation device provided by the embodiment of the invention belongs to the same inventive concept as the age estimation method provided by the embodiment of the invention, can execute the age estimation method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the age estimation method. For details of the technology that are not described in detail in this embodiment, reference may be made to the age estimation method provided in this embodiment of the present invention, which is not described herein again.
In addition, an embodiment of the present invention further provides a computer device, where the computer device includes:
one or more processors;
storage means for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the steps of the age estimation method as in the above embodiments.
Another embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the age estimation method as described in the above embodiment.
As will be appreciated by one of skill in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method of age estimation, the method comprising:
acquiring a plurality of behavior records associated with user identification, wherein each behavior record comprises an applicable age range of a commodity and a corresponding behavior category;
dividing each behavior record into corresponding preset age groups according to respective applicable age groups;
performing intersection taking on all the behavior records in each preset age group according to behavior categories, and acquiring a target age group corresponding to each preset age group according to intersection taking results;
and estimating a final age group corresponding to the user identifier according to the target age group corresponding to each preset age group.
2. The method of claim 1, wherein said dividing each of said behavior records into respective predetermined age groups according to a respective applicable age group comprises:
calculating a midpoint value corresponding to the applicable age group in each behavior record according to the left endpoint value and the right endpoint value corresponding to the applicable age group in each behavior record;
and in a plurality of preset age groups, dividing each behavior record into preset age groups in which the corresponding midpoint values fall.
3. The method of claim 1, wherein the step of performing intersection-taking on all behavior records in each preset age group according to behavior categories and obtaining a target age group corresponding to each preset age group according to a result of intersection-taking comprises:
performing intersection taking on applicable age groups in all the behavior records in all the preset age groups according to behavior categories to obtain intersection results of all non-empty sets in all the preset age groups;
and taking intersection of intersection results of all the non-empty sets in each preset age group to obtain a target age group corresponding to each preset age group.
4. The method according to claim 3, wherein the intersecting applicable age groups in the behavior records in the preset age groups according to behavior categories to obtain intersection results of non-empty sets in the preset age groups comprises:
and respectively executing the following operations aiming at each behavior category in each preset age group:
judging whether the largest left endpoint value is less than or equal to the smallest right endpoint value in the left endpoint values and the right endpoint values of all applicable age groups corresponding to the behavior categories;
if so, taking the age range from the maximum left endpoint value to the minimum right endpoint value as the intersection result of the non-empty sets corresponding to the behavior categories;
and if not, filtering all applicable age groups corresponding to the behavior types as invalid data.
5. The method according to claim 3, wherein the intersecting the intersection result of all the non-empty sets in each of the preset age groups to obtain the target age group corresponding to each of the preset age groups comprises:
and aiming at each preset age group, respectively executing the following operations:
judging whether the largest left endpoint value is smaller than or equal to the smallest right endpoint value in the left endpoint value and the right endpoint value corresponding to the intersection result of all the non-empty sets in the preset age group;
if so, taking the age group between the maximum left endpoint value and the minimum right endpoint value as a target age group corresponding to the preset age group;
and if not, determining the intersection result of the non-empty sets corresponding to the behavior categories with high priority as the target age group corresponding to the preset age group according to the priority order of each behavior category.
6. The method according to any one of claims 1 to 5, wherein estimating a final age group corresponding to the user identifier according to a target age group corresponding to each of the preset age groups comprises:
taking intersection of the target age groups corresponding to all the preset age groups, and judging whether an intersection age group of a non-empty set corresponding to the user identifier exists or not;
if so, taking the intersection age group of the non-empty set corresponding to the user identifier as a final age group corresponding to the user identifier;
if not, judging whether the number of all the target age groups is two or not;
if so, taking the two target age groups as two final age groups corresponding to the user identification;
and if not, determining all the target age groups as invalid data.
7. The method of any of claims 1 to 5, further comprising:
obtaining a score value corresponding to each behavior category in each preset age group according to a preset score rule and the occurrence frequency of each behavior category in each preset age group;
calculating the score value of a target age group in each preset age group according to the score value corresponding to each behavior category in each preset age group;
and calculating the score value of the final age group according to the calculated score value of the target age group in each preset age group.
8. The method of claim 7, further comprising:
and outputting the final age group corresponding to the user identification and the reliability grade obtained based on the scoring value of the final age group.
9. An age estimation apparatus, characterized in that the apparatus comprises:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a plurality of behavior records associated with user identifications, and each behavior record comprises an applicable age group and a corresponding behavior category of a commodity;
the age dividing module is used for dividing each behavior record into corresponding preset age groups according to the respective applicable age groups;
the intersection taking module is used for taking an intersection of all the behavior records in the preset age groups according to behavior categories;
the second acquisition module is used for acquiring a target age group corresponding to each preset age group according to the intersection acquisition result;
and the age estimation module is used for estimating a final age group corresponding to the user identifier according to the target age group corresponding to each preset age group.
10. The apparatus of claim 9, further comprising:
the score acquisition module is used for acquiring the score corresponding to each behavior category in each preset age group according to a preset scoring rule and the occurrence frequency of each behavior category in each preset age group;
the first calculation module is used for calculating the score value of a target age group in each preset age group according to the score value corresponding to each behavior category in each preset age group;
and the second calculation module is used for calculating the score value of the final age group according to the calculated score value of the target age group in each preset age group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911166552.9A CN111080401A (en) | 2019-11-25 | 2019-11-25 | Age estimation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911166552.9A CN111080401A (en) | 2019-11-25 | 2019-11-25 | Age estimation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111080401A true CN111080401A (en) | 2020-04-28 |
Family
ID=70311553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911166552.9A Pending CN111080401A (en) | 2019-11-25 | 2019-11-25 | Age estimation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111080401A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220398244A1 (en) * | 2021-09-23 | 2022-12-15 | Beijing Baidu Netcom Science Technology Co., Ltd. | Query method and device and storage medium |
| CN116248931A (en) * | 2023-03-16 | 2023-06-09 | 北京奇艺世纪科技有限公司 | Resource information pushing method and device, electronic equipment and readable storage medium |
| US20230245202A1 (en) * | 2022-01-31 | 2023-08-03 | Walmart Apollo, Llc | Methods and systems for determining household characteristics |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110269175A1 (en) * | 2003-03-28 | 2011-11-03 | Inguran, Llc | Methods for sorting particles |
| CN105868243A (en) * | 2015-12-14 | 2016-08-17 | 乐视网信息技术（北京）股份有限公司 | Information processing method and apparatus |
| CN107239456A (en) * | 2016-03-28 | 2017-10-10 | 阿里巴巴集团控股有限公司 | Age bracket recognition methods and device |
-
2019
- 2019-11-25 CN CN201911166552.9A patent/CN111080401A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110269175A1 (en) * | 2003-03-28 | 2011-11-03 | Inguran, Llc | Methods for sorting particles |
| CN105868243A (en) * | 2015-12-14 | 2016-08-17 | 乐视网信息技术（北京）股份有限公司 | Information processing method and apparatus |
| CN107239456A (en) * | 2016-03-28 | 2017-10-10 | 阿里巴巴集团控股有限公司 | Age bracket recognition methods and device |
Non-Patent Citations (2)
| Title |
|---|
| HANZHOU XIE等: "Simulation-based study on a pre-signal control system at isolated intersection with separate left turn phase", 《PROCEEDINGS OF 2012 9TH IEEE INTERNATIONAL CONFERENCE ON NETWORKING, SENSING AND CONTROL》 * |
| 蒋胜: "集成社会化标签和用户背景信息的协同过滤推荐方法", 《计算机应用》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220398244A1 (en) * | 2021-09-23 | 2022-12-15 | Beijing Baidu Netcom Science Technology Co., Ltd. | Query method and device and storage medium |
| US20230245202A1 (en) * | 2022-01-31 | 2023-08-03 | Walmart Apollo, Llc | Methods and systems for determining household characteristics |
| CN116248931A (en) * | 2023-03-16 | 2023-06-09 | 北京奇艺世纪科技有限公司 | Resource information pushing method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102890803B (en) | The defining method of the abnormal process of exchange of electronic goods and device thereof | |
| CN111080401A (en) | Age estimation method and device | |
| CN104111938B (en) | A kind of method and device of information recommendation | |
| CN112529663B (en) | Commodity recommendation method, commodity recommendation device, terminal equipment and storage medium | |
| CN102446326B (en) | A kind of method of information pushing, system and equipment | |
| WO2017028735A1 (en) | Method and device for selecting and recommending display object | |
| CN110807669B (en) | Cross-platform user information management method and device | |
| CN111415216A (en) | Commodity recommendation method and device, server and storage medium | |
| CN108805598A (en) | Similarity information determines method, server and computer readable storage medium | |
| CN111461836A (en) | Information processing method and device for promoting commodity transaction | |
| CN108664605B (en) | Model evaluation method and system | |
| CN111160783A (en) | Method and system for evaluating digital asset value and electronic equipment | |
| CN112396433A (en) | Method and system for identifying false commodity comments based on behavior of person to be evaluated | |
| CN107133811A (en) | The recognition methods of targeted customer a kind of and device | |
| CN108268519B (en) | Method and device for recommending network object | |
| WO2017177834A1 (en) | Method and system for translating | |
| CN107330709B (en) | Method and device for determining target object | |
| CN116934418B (en) | Abnormal order detection and early warning method, system, equipment and storage medium | |
| CN111507804B (en) | Emotion perception commodity recommendation method based on mixed information fusion | |
| CN108304407B (en) | Method and system for sequencing objects | |
| CN107239456B (en) | Age group identification method and device | |
| CN110019983B (en) | Expansion method and device of label structure and electronic equipment | |
| CN104331823B (en) | It is determined that the method and device for the middle keyword reservation price that releases news | |
| CN113971612B (en) | Service data processing method, device, equipment and storage medium | |
| CN110020918A (en) | Recommendation information generation method and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200428 |
|
| RJ01 | Rejection of invention patent application after publication |