CN117573945A - User tag processing method, device, equipment and medium - Google Patents
User tag processing method, device, equipment and medium Download PDFInfo
- Publication number
- CN117573945A CN117573945A CN202410066620.9A CN202410066620A CN117573945A CN 117573945 A CN117573945 A CN 117573945A CN 202410066620 A CN202410066620 A CN 202410066620A CN 117573945 A CN117573945 A CN 117573945A
- Authority
- CN
- China
- Prior art keywords
- type
- tag
- user
- target
- labels
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title description 6
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000012216 screening Methods 0.000 claims abstract description 20
- 238000004590 computer program Methods 0.000 claims description 11
- 239000003086 colorant Substances 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90348—Query processing by searching ordered data, e.g. alpha-numerically ordered data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The present disclosure relates to the field of electronic digital data processing technologies, and in particular, to a method, an apparatus, a device, and a medium for processing a user tag. The method comprises the following steps: acquiring a first type tag corresponding to each user in the global users; obtaining a second type label corresponding to the target identifier; obtaining a tag association table, wherein a plurality of entries are stored in the tag association table, each entry comprises a first type tag, a second type tag and a first weight corresponding to the first type tag and the second type tag in the entry, and the sources of the first type tag and the second type tag are different; matching the second type of labels corresponding to the target identification in the label association table to obtain matched items; and screening target users of the target identification from the global users according to the first type labels and the matched items corresponding to each user in the global users. The method and the device can screen matched users from the users with the known corresponding first type tags according to the second type tags of the target identification.
Description
Technical Field
The present invention relates to the field of electronic digital data processing technologies, and in particular, to a method, an apparatus, a device, and a medium for processing a user tag.
Background
The tags of some brands (i.e. logos) existing can be obtained by way of a question with a large model (e.g. ChatGPT), but the tags of the same brands stored in the existing database often differ from the tags obtained by way of a question with a large model, e.g. the tags of a certain net coffee brand obtained from the existing database (i.e. the first source) are individual, game and life services etc. while the tags of the net coffee brand obtained by way of a question with a large model (i.e. the second source) are internet cultures, easy entertainment, game fans and young people etc. The existing database also stores labels of different users, and the labels are identical to the labels of brands stored in the existing database in expression; how to screen matching users from a first source according to a label of a certain identifier obtained from a second source is a problem to be solved.
Disclosure of Invention
The invention aims to provide a processing method, a processing device, processing equipment and a processing medium for user labels, so that matched users can be screened from a first source according to a label of a certain identifier acquired by a second source.
According to a first aspect of the present invention, there is provided a method of processing a user tag, the method comprising the steps of:
and obtaining a first type label corresponding to each user in the global users.
And obtaining a second type label corresponding to the target identifier.
Obtaining a tag association table, wherein a plurality of entries are stored in the tag association table, each entry comprises a first type tag, a second type tag and a first weight corresponding to the first type tag and the second type tag in the entry, and the sources of the first type tag and the second type tag are different.
And matching the second type of labels corresponding to the target identification in the label association table to obtain matched items.
And screening target users of the target identification from the global users according to the first type labels and the matched items corresponding to each user in the global users.
Further, the step of screening the target users of the target identifiers from the global users according to the first type tags and the matched items corresponding to each user in the global users comprises the following steps:
and comparing the first type tag corresponding to each user in the global users with the first type tag included in the matched item, and if the first type tag corresponding to the user includes the first type tag existing in the matched item, acquiring the association weight of the user and the target identifier according to the first weight corresponding to the first type tag corresponding to the user and existing in the matched item.
And sequencing the association weights corresponding to each user in the global users, and determining the users with the largest corresponding association weights as target users of the target identification.
Further, each item further includes a second weight corresponding to the first type tag and the second type tag in the item, and the method further includes the following steps:
and displaying the first type labels corresponding to each target user of the target identifier, wherein when displaying the first type labels corresponding to any target user, the colors displayed by different first type labels in the first type labels corresponding to the target user are determined according to the first weights corresponding to different first type labels in the first type labels corresponding to the target user, and the sizes of the areas displayed by different first type labels in the first type labels corresponding to the target user are determined according to the second weights corresponding to different first type labels in the first type labels corresponding to the target user.
Further, the tag association table obtaining process includes:
and acquiring a first type label and a second type label corresponding to the plurality of sample identifiers.
And obtaining target population indexes of each first type of tag and each second type of tag corresponding to each sample identifier.
And acquiring a first association coefficient of the target population index of each first type of tag and each second type of tag corresponding to the same sample identifier.
And acquiring first weights of the first type labels and the second type labels corresponding to the same sample identification according to first association coefficients of the same first type labels and the same second type labels corresponding to different sample identifications.
And constructing a tag association table according to the first weight.
Further, each item further includes a second weight corresponding to the first type tag and the second type tag in the item, and the obtaining process of the tag association table further includes:
and acquiring the information value of each first type tag corresponding to each sample identifier.
And acquiring the association degree of each second type label corresponding to each sample identifier and the sample identifier.
And acquiring a second association coefficient of the association degree and the information value of each first type of tag and each second type of tag corresponding to the same sample identifier.
And obtaining second weights of the first type labels and the second type labels corresponding to the same sample identification according to the second association coefficients and the first association coefficients of the same first type labels and the same second type labels corresponding to the different sample identifications.
And constructing a tag association table according to the second weight.
According to a second aspect of the present invention, there is provided a processing apparatus for a user tag, the apparatus comprising:
the first acquisition module is used for acquiring the first type labels corresponding to each user in the global users.
The second acquisition module is used for acquiring a second type of tag corresponding to the target identifier.
The third acquisition module is used for acquiring a label association table, a plurality of items are stored in the label association table, each item comprises a first type label, a second type label and a first weight corresponding to the first type label and the second type label in the item, and the sources of the first type label and the second type label are different.
And the first matching module is used for matching the second type of labels corresponding to the target identification in the label association table to obtain matched items.
And the first screening module is used for screening target users of the target identification from the global users according to the first type labels and the matched items corresponding to each user in the global users.
Further, the first screening module includes:
and the first comparison module is used for comparing the first type tag corresponding to each user in the global users with the first type tag included in the matched item, and if the first type tag corresponding to the user includes the first type tag existing in the matched item, the association weight of the user and the target identifier is obtained according to the first weight corresponding to the first type tag corresponding to the user and existing in the matched item.
The first ordering module is used for ordering the association weights corresponding to each user in the global users, and determining the users with the corresponding association weights with the largest preset number as target users of the target identification.
Further, each item further includes a second weight corresponding to the first type tag and the second type tag in the item, and the processing device further includes:
the first display module is used for displaying the first type of labels corresponding to each target user of the target identifier, wherein when displaying the first type of labels corresponding to any target user, colors displayed by different first type of labels in the first type of labels corresponding to the target user are determined according to first weights corresponding to different first type of labels in the first type of labels corresponding to the target user, and the sizes of areas displayed by different first type of labels in the first type of labels corresponding to the target user are determined according to second weights corresponding to different first type of labels in the first type of labels corresponding to the target user.
Further, the third obtaining module includes:
and the fourth acquisition module is used for acquiring the first type labels and the second type labels corresponding to the sample identifiers.
And a fifth acquisition module, configured to acquire a target population index of each first type tag and each second type tag corresponding to each sample identifier.
The sixth acquisition module is used for acquiring a first association coefficient of the target population index of each first type of tag and each second type of tag corresponding to the same sample identifier.
The seventh obtaining module is configured to obtain, according to first association coefficients of the same first type tag and the same second type tag corresponding to different sample identifiers, first weights of the first type tag and the second type tag corresponding to the same sample identifier.
And the first construction module is used for constructing a label association table according to the first weight.
Further, each item further includes a second weight corresponding to the first type tag and the second type tag in the item, and the third obtaining module further includes:
and the eighth acquisition module is used for acquiring the information value of each first type tag corresponding to each sample identifier.
And a ninth acquisition module, configured to acquire a degree of association between each second type tag corresponding to each sample identifier and the sample identifier.
And a tenth acquisition module, configured to acquire a second association coefficient of the association degree and the information value of each first type tag and each second type tag corresponding to the same sample identifier.
The eleventh acquisition module is configured to acquire second weights of the first type tag and the second type tag corresponding to the same sample identifier according to second association coefficients and first association coefficients of the same first type tag and the same second type tag corresponding to different sample identifiers.
And the second construction module is used for constructing a label association table according to the second weight.
According to a third aspect of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the method of processing a user tag as described above when executing the computer program.
According to a fourth aspect of the present invention, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, implements the above-described user tag processing method.
Compared with the prior art, the invention has at least the following beneficial effects:
under the condition that a first type label corresponding to each user and a second type label corresponding to a target identifier in a global user are obtained, a label association table is also obtained, a plurality of items are stored in the label association table, each item corresponds to a different label combination, each label combination comprises a first type label and a second type label, the first type label and the second type label corresponding to different label combinations are different, or the first type label and the second type label are different; on the basis, the second type labels corresponding to the target identifications are matched in the label association table, corresponding matching items are found, the first type labels in the matching items are the first type labels related to the target identifications, on the basis of obtaining the first type labels related to the target identifications, the first type labels corresponding to each user in the global users are combined, the target users of the target identifications can be screened out from the global users, and the purpose of screening the matched users from the users with the known first type labels according to the second type labels of the target identifications is achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a processing method of a user tag according to a first embodiment of the present invention;
fig. 2 is a flowchart of a tag association table acquisition process according to a first embodiment of the present invention;
FIG. 3 is a flowchart illustrating steps for screening out target users with target identifiers according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a process for obtaining another tag association table according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a processing device for a user tag according to a second embodiment of the present invention;
fig. 6 is a schematic diagram of a third obtaining module according to a second embodiment of the present invention;
fig. 7 is a schematic diagram of a first screening module according to a second embodiment of the present invention;
fig. 8 is a schematic diagram of another third obtaining module according to the second embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
Embodiment one:
as shown in fig. 1, the present embodiment provides a method for processing a user tag, including the following steps:
s100, obtaining a first type tag corresponding to each user in the global users.
In this embodiment, the global user is a, a= (a) 1 ,a 2 ,…,a n ,…,a N )，a n For the nth user, a n The corresponding first type label is a fea n ，fea n =(fea n,1 ,fea n,2 ,…,fea n,i(n) ,…,fea n,m(n) )，fea n,i(n) Is a as n The corresponding ith (n) first class label has a value range of i (n) from 1 to m (n), m (n) being a n The number of corresponding first type tags.
In this embodiment, the first type of tag refers to a tag obtained from a first source, and the first type of tag corresponding to the user refers to a tag associated with the user obtained from the first source; alternatively, the first source is a pre-built database having each a stored therein n Corresponding first class tags. A in the present embodiment n The corresponding first type of tag refers to the tag obtained from the first source and a n Associated tag, with a n The associated label refers to a n Having labels that are distinct from other users. For example, a certain a n The corresponding first type of tags are male, young, games, etc.
S200, obtaining a second type label corresponding to the target identifier.
In this embodiment, the second type tag corresponding to the target identifier is b, b= (tag) 1 ,tag 2 ,…,tag j ,…,tag u )，tag j And j is the number of the second class labels corresponding to the target identifier, the value range of j is 1 to u, and u is the number of the second class labels corresponding to the target identifier.
In this embodiment, the second type of tag refers to a tag obtained from a second source, the second type of tag corresponding to the target identifier refers to a tag associated with the target identifier obtained from the second source, and the tag associated with the target identifier refers to a tag which is different from other identifiers and is possessed by the target identifier; in this embodiment the second source is a source different from the first source, alternatively the second source is a large model or a database different from the first source. Those skilled in the art know that any large model in the prior art falls within the protection scope of the present invention, and optionally, the large model is ChatGPT, and the tag associated with the target identifier is obtained by way of a chat question; optionally, some questions are preset, keywords are extracted according to the answers of the ChatGPT to the questions, and the extracted keywords are used as labels associated with the target identifications.
An identifier in this embodiment may be used to uniquely characterize a thing, alternatively identified as a brand.
S300, a label association table is obtained, a plurality of items are stored in the label association table, each item comprises a first type label, a second type label and a first weight corresponding to the first type label and the second type label in the item, and the sources of the first type label and the second type label are different.
Specifically, as shown in fig. 2, the tag association table obtaining process includes:
s310, a first type label and a second type label corresponding to a plurality of sample identifiers are obtained.
In this embodiment, the obtained sample is identified as S, s= (S 1 ,s 2 ,…,s k ,…,s v )，s k For the kth sample mark, the value range of k is 1 to v, and v is the number of the obtained sample marks; s is(s) k The corresponding first type label is c k ，c k =(c k,1 ,c k,2 ,…,c k,e(k) ,…,c k,p(k) )，c k,e(k) Is s k The corresponding e (k) th first type label has the value range of e (k) from 1 to p (k), and p (k) is s k The number of corresponding first type tags; s is(s) k The corresponding second type label is d k ，d k =(d k,1 ,d k,2 ,…,d k,f(k) ,…,d k,q(k) )，d k,f(k) Is s k The corresponding f (k) th second class label has the value range of f (k) from 1 to q (k), and q (k) is s k The number of corresponding second class labels.
S320, obtaining target population indexes of each first type of tag and each second type of tag corresponding to each sample identifier.
In this embodiment, c k,e(k) Target population index of tgic k,e(k) ，d k,f(k) Target population index of tgid k,f(k) . In this embodiment, the target population index of each type of tag corresponding to each sample identifier and the target population index of each type of tag corresponding to each sample identifier are both known values, and are selectable, tgid k,f(k) 1, tgic k,e(k) According to the acquisition method of the target population index in the prior art.
S330, obtaining a first association coefficient of the target population index of each first type of tag and each second type of tag corresponding to the same sample identifier.
In this embodiment, s k Corresponding c k,e(k) And d k,f(k) The first correlation coefficient of the target population index of (2) is comtgi e(k),f(k) ，comtgi e(k),f(k) =tgid k,e(k) ×tgic k,e(k) 。
S340, according to the first association coefficients of the same first type tag and the same second type tag corresponding to different sample identifiers, first weights of the first type tag and the second type tag corresponding to the same sample identifier are obtained.
In this embodiment, if a certain sample identifier in S corresponds to a certain first type tag (denoted as β 1 ) And a tag of a second type (denoted beta 2 ) Meanwhile, the first type label and the second type label corresponding to the other R sample identifications in S are also identified, and then the first type label is beta 1 And a second class label beta 2 The first weight of (2) is: ，δ r For S comprising the first type tag beta 1 And a second class label beta 2 Corresponding beta is identified by the r-th sample of (c) 1 And beta 2 The value range of r is 1+R, and 1+R is S and contains beta 1 And beta 2 Is used for identifying the number of samples.
S350, constructing a tag association table according to the first weight.
In this embodiment, the constructed tag association table includes X entries, x= Σ v k=1 (p k ×q k ) The method comprises the steps of carrying out a first treatment on the surface of the Each item comprises a first type tag, a second type tag and a first weight corresponding to the first type tag and the second type tag. Optionally, the front p in the tag association table 1 ×q 1 The entries are used to store s 1 First weights of corresponding first class labels and second class labels, wherein the first q is 1 The entries are used to store s 1 Corresponding first-class labels and s 1 Corresponding q 1 First of second class of tagsWeight, f (1) th entry for storing s 1 Corresponding first-class labels and s 1 A first weight of a corresponding f (1) th second class label; front p in tag association table 1 ×q 1 +1 to front p 1 ×q 1 +p 2 ×q 2 The entry is used for storing s 2 The first weight of the corresponding first type label and the second type label; and so on.
S400, matching the second type of labels corresponding to the target identification in the label association table to obtain matched items.
In this embodiment, the tag association table is traversed, and if a second type tag included in an entry in the tag association table is a second type tag corresponding to the target identifier, then the entry is determined to be a matched entry; otherwise, it is determined that the entry is not a matching entry.
S500, target users with target identifiers are screened out from the global users according to the first type labels and the matched items corresponding to each user in the global users.
In this embodiment, the target user of the target identifier is the user matched with the target identifier.
Specifically, as shown in fig. 3, S500 includes:
s510, for each user in the global users, comparing the first type label corresponding to the user with the first type label included in the matched item, and if the first type label corresponding to the user includes the first type label existing in the matched item, acquiring the association weight of the user and the target identifier according to the first weight corresponding to the first type label corresponding to the user and existing in the matched item.
In the present embodiment, if a n Corresponding first-class tag fea n Excluding the first type tag present in the matching entry, then a n The association weight with the target mark is 0; if fea is n Includes a first type tag present in the matching entry, and fea n The first type of tag included in the matching entry is fea' n ，fea’ n =(fea’ n,1 ,fea’ n,2 ,…,fea’ n,y(n) ,…,fea’ n,Y(n) )，fea’ n,y(n) Is a fea n The Y (n) th tag is included in the first type tag in the matched item, the value of Y (n) ranges from 1 to Y (n), and Y (n) is fea n Including the number of first type tags present in the matching entry, then a n The association weight with the target identifier is sigma Y(n) y(n)=1 z y(n) ，z y(n) The entries for the match include fea' n,y(n) The entry of (1) includes a first weight.
S520, sorting the association weights corresponding to each user in the global users, and determining the users with the largest preset number of the corresponding association weights as target users of the target identification.
Specifically, the association weights corresponding to all users in the global users are arranged in the order from large to small, and the previous preset number of users are determined to be target users of the target identification.
As a specific implementation manner, each item further includes a second weight corresponding to the first type tag and the second type tag in the item, and the processing method of the user tag further includes the following steps:
s600, displaying the first type labels corresponding to each target user of the target identifier, wherein when displaying the first type labels corresponding to any target user, the colors displayed by different first type labels in the first type labels corresponding to the target user are determined according to the first weights corresponding to different first type labels in the first type labels corresponding to the target user, and the sizes of the areas displayed by different first type labels in the first type labels corresponding to the target user are determined according to the second weights corresponding to different first type labels in the first type labels corresponding to the target user.
In the embodiment, a first label corresponding to a target user is displayed on a user interface; optionally, the color of the display corresponding to the first type label with the larger corresponding first weight in the first type labels corresponding to the same target user is darker; the first type labels corresponding to the first weight values in the first type labels corresponding to the same target user are lighter in the corresponding display colors. The larger the corresponding second weight value of the first type labels corresponding to the same target user is, the larger the corresponding display area size of the first type labels is; the smaller the corresponding second weight value of the first type of labels corresponding to the same target user is, the smaller the corresponding displayed area size is.
In this embodiment, if each entry further includes a second weight corresponding to the first type tag and the second type tag in the entry, as shown in fig. 4, the tag association table obtaining process further includes:
s360, obtaining the information value of each first type tag corresponding to each sample identifier.
In this embodiment, the information value of each first type tag corresponding to each sample identifier is a known value, s k Corresponding e (k) th first class label c k,e(k) The information value of (a) is iv k,e(k) The method comprises the steps of carrying out a first treatment on the surface of the Those skilled in the art will appreciate that the method for obtaining the information value iv is the prior art, and will not be described herein.
And S370, acquiring the association degree of each second type label corresponding to each sample identifier and the sample identifier.
In this embodiment, the association degree between each second type of tag corresponding to each sample identifier and the sample identifier is a known value, and optionally, the association degree is given manually according to experience or given by using a large model; in this embodiment, s k Corresponding f (k) th second class label d k,f(k) The association with the sample identity is sco k,f(k) As a specific embodiment, sco k,f(k) =fen k,f(k) ×count k,f(k) ×weight k,f(k) ×(1+rand k,f(k) )，count k,f(k) D appears in answers to the large model in the case of L times for the large model of question k,f(k) Count of times of (a) k,f(k) L is less than or equal to L, L is preset number of questions, fen k,f(k) For d appearing in answer k,f(k) D of large model answer corresponding to question k,f(k) And s k Weight of the correlation degree of (C) k,f(k) Is d k,f(k) Corresponding weight, weight k,f(k) Equal toAppearance d in answer k,f(k) The sum of the weights corresponding to the questions in this embodiment, the weight corresponding to each question is a known value, rand k,f(k) Is d k,f(k) Corresponding random value, 0<rand k,f(k) <1。
S380, obtaining a second association coefficient of the association degree and the information value of each first type tag and each second type tag corresponding to the same sample identifier.
In this embodiment, s k Corresponding c k,e(k) And d k,f(k) A second association coefficient of the association degree and the information value of (2) is comsi e(k),f(k) ，comsi e(k),f(k) =(sco k,f(k) ×tgid k,f(k) +iv k,e(k) ×tgic k,e(k) )/(tgid k,f(k) +tgic k,e(k) )。
S390, obtaining second weights of the first type labels and the second type labels corresponding to the same sample identification according to the second association coefficients and the first association coefficients of the same first type labels and the same second type labels corresponding to different sample identifications.
In this embodiment, if a certain sample identifier in S corresponds to a certain first type tag (denoted as β 1 ) And a tag of a second type (denoted beta 2 ) Meanwhile, the first type label and the second type label corresponding to the other R sample identifications in S are also identified, and then the first type label is beta 1 And a second class label beta 2 The second weight of (2) is: (Sigma) R+1 r=1 (t r ×δ r ))/(∑ R+1 r=1 δ r )，t r For S comprising the first type tag beta 1 And a second class label beta 2 Corresponding beta is identified by the r-th sample of (c) 1 And beta 2 Is a second correlation coefficient of (a).
S3100, constructing a label association table according to the second weight.
In this embodiment, a tag association table is already constructed according to the first weight, and when a second weight is obtained, the second weight is added to a corresponding entry, so that further construction of the tag association table can be achieved, and each entry of the finally constructed tag association table includes a first type tag, a second type tag, a first weight and a second weight.
In this embodiment, under the condition of acquiring a first type tag corresponding to each user and a second type tag corresponding to a target identifier in a global user, a tag association table is also acquired, a plurality of entries are stored in the tag association table, each entry corresponds to a different tag combination, each tag combination includes a first type tag and a second type tag, the first type tags and the second type tags corresponding to different tag combinations are different, or the first type tag and the second type tag are different; on the basis, the second type labels corresponding to the target identifications are matched in the label association table, corresponding matching items are found, the first type labels in the matching items are the first type labels related to the target identifications, on the basis of obtaining the first type labels related to the target identifications, the first type labels corresponding to each user in the global users are combined, the target users of the target identifications can be screened out from the global users, and the purpose of screening the matched users from the users with the known first type labels according to the second type labels of the target identifications is achieved.
Embodiment two:
as shown in fig. 5, this embodiment provides a processing apparatus for a user tag, including:
the first obtaining module 100 is configured to obtain a first type tag corresponding to each user in the global user.
In this embodiment, the global user is a, a= (a) 1 ,a 2 ,…,a n ,…,a N )，a n For the nth user, a n The corresponding first type label is a fea n ，fea n =(fea n,1 ,fea n,2 ,…,fea n,i(n) ,…,fea n,m(n) )，fea n,i(n) Is a as n The corresponding ith (n) first class label has a value range of i (n) from 1 to m (n), m (n) being a n The number of corresponding first type tags.
In this embodiment, the first type of tag refers to a tag obtained from a first source, and the user corresponds toRefers to a tag associated with a user obtained from a first source; alternatively, the first source is a pre-built database having each a stored therein n Corresponding first class tags. A in the present embodiment n The corresponding first type of tag refers to the tag obtained from the first source and a n Associated tag, with a n The associated label refers to a n Having labels that are distinct from other users. For example, a certain a n The corresponding first type of tags are male, young, games, etc.
And the second obtaining module 200 is configured to obtain a second type of tag corresponding to the target identifier.
In this embodiment, the second type tag corresponding to the target identifier is b, b= (tag) 1 ,tag 2 ,…,tag j ,…,tag u )，tag j And j is the number of the second class labels corresponding to the target identifier, the value range of j is 1 to u, and u is the number of the second class labels corresponding to the target identifier.
In this embodiment, the second type of tag refers to a tag obtained from a second source, the second type of tag corresponding to the target identifier refers to a tag associated with the target identifier obtained from the second source, and the tag associated with the target identifier refers to a tag which is different from other identifiers and is possessed by the target identifier; in this embodiment the second source is a source different from the first source, alternatively the second source is a large model or a database different from the first source. Those skilled in the art know that any large model in the prior art falls within the protection scope of the present invention, and optionally, the large model is ChatGPT, and the tag associated with the target identifier is obtained by way of a chat question; optionally, some questions are preset, keywords are extracted according to the answers of the ChatGPT to the questions, and the extracted keywords are used as labels associated with the target identifications.
An identifier in this embodiment may be used to uniquely characterize a thing, alternatively identified as a brand.
The third obtaining module 300 is configured to obtain a tag association table, where a plurality of entries are stored in the tag association table, each entry includes a first type tag, a second type tag, and a first weight corresponding to the first type tag and the second type tag in the entry, where sources of the first type tag and the second type tag are different.
Specifically, as shown in fig. 6, the third acquisition module 300 includes:
a fourth obtaining module 310, configured to obtain a first type of tag and a second type of tag corresponding to the plurality of sample identifiers.
In this embodiment, the obtained sample is identified as S, s= (S 1 ,s 2 ,…,s k ,…,s v )，s k For the kth sample mark, the value range of k is 1 to v, and v is the number of the obtained sample marks; s is(s) k The corresponding first type label is c k ，c k =(c k,1 ,c k,2 ,…,c k,e(k) ,…,c k,p(k) )，c k,e(k) Is s k The corresponding e (k) th first type label has the value range of e (k) from 1 to p (k), and p (k) is s k The number of corresponding first type tags; s is(s) k The corresponding second type label is d k ，d k =(d k,1 ,d k,2 ,…,d k,f(k) ,…,d k,q(k) )，d k,f(k) Is s k The corresponding f (k) th second class label has the value range of f (k) from 1 to q (k), and q (k) is s k The number of corresponding second class labels.
A fifth obtaining module 320, configured to obtain the target population index of each first type of tag and each second type of tag corresponding to each sample identifier.
In this embodiment, c k,e(k) Target population index of tgic k,e(k) ，d k,f(k) Target population index of tgid k,f(k) . In this embodiment, the target population index of each type of tag corresponding to each sample identifier and the target population index of each type of tag corresponding to each sample identifier are both known values, and are selectable, tgid k,f(k) 1, tgic k,e(k) According to the acquisition method of the target population index in the prior art.
The sixth obtaining module 330 is configured to obtain a first association coefficient of the target population index of each first type of tag and each second type of tag corresponding to the same sample identifier.
In this embodiment, s k Corresponding c k,e(k) And d k,f(k) The first correlation coefficient of the target population index of (2) is comtgi e(k),f(k) ，comtgi e(k),f(k) =tgid k,e(k) ×tgic k,e(k) 。
The seventh obtaining module 340 is configured to obtain first weights of the first type tag and the second type tag corresponding to the same sample identifier according to first association coefficients of the same first type tag and the same second type tag corresponding to different sample identifiers.
In this embodiment, if a certain sample identifier in S corresponds to a certain first type tag (denoted as β 1 ) And a tag of a second type (denoted beta 2 ) Meanwhile, the first type label and the second type label corresponding to the other R sample identifications in S are also identified, and then the first type label is beta 1 And a second class label beta 2 The first weight of (2) is:，δ r for S comprising the first type tag beta 1 And a second class label beta 2 Corresponding beta is identified by the r-th sample of (c) 1 And beta 2 The value range of r is 1+R, and 1+R is S and contains beta 1 And beta 2 Is used for identifying the number of samples.
A first construction module 350, configured to construct a tag association table according to the first weight.
In this embodiment, the constructed tag association table includes X entries, x= Σ v k=1 (p k ×q k ) The method comprises the steps of carrying out a first treatment on the surface of the Each item comprises a first type tag, a second type tag and a first weight corresponding to the first type tag and the second type tag. Optionally, the front p in the tag association table 1 ×q 1 The entries are used to store s 1 First weights of corresponding first class labels and second class labels, wherein the first q is 1 The entries are used to store s 1 Corresponding first-class labels and s 1 Corresponding q 1 First weight of second class label, firstf (1) entries for storing s 1 Corresponding first-class labels and s 1 A first weight of a corresponding f (1) th second class label; front p in tag association table 1 ×q 1 +1 to front p 1 ×q 1 +p 2 ×q 2 The entry is used for storing s 2 The first weight of the corresponding first type label and the second type label; and so on.
And the first matching module 400 is configured to match the second type of tag corresponding to the target identifier in the tag association table, so as to obtain a matched entry.
In this embodiment, the tag association table is traversed, and if a second type tag included in an entry in the tag association table is a second type tag corresponding to the target identifier, then the entry is determined to be a matched entry; otherwise, it is determined that the entry is not a matching entry.
And the first screening module 500 is configured to screen the target user with the target identifier from the global users according to the first type tag and the matched entry corresponding to each user in the global users.
In this embodiment, the target user of the target identifier is the user matched with the target identifier.
Specifically, as shown in fig. 7, the first screening module 500 includes:
and the first comparison module 510 is configured to compare, for each user in the global users, a first type tag corresponding to the user with a first type tag included in the matched entry, and if the first type tag corresponding to the user includes a first type tag existing in the matched entry, obtain an association weight of the user with the target identifier according to a first weight corresponding to the first type tag corresponding to the user and existing in the matched entry.
In the present embodiment, if a n Corresponding first-class tag fea n Excluding the first type tag present in the matching entry, then a n The association weight with the target mark is 0; if fea is n Includes a first type tag present in the matching entry, and fea n Including being present in said matching entryThe first kind of label is fea' n ，fea’ n =(fea’ n,1 ,fea’ n,2 ,…,fea’ n,y(n) ,…,fea’ n,Y(n) )，fea’ n,y(n) Is a fea n The Y (n) th tag is included in the first type tag in the matched item, the value of Y (n) ranges from 1 to Y (n), and Y (n) is fea n Including the number of first type tags present in the matching entry, then a n The association weight with the target identifier is sigma Y(n) y(n)=1 z y(n) ，z y(n) The entries for the match include fea' n,y(n) The entry of (1) includes a first weight.
The first ranking module 520 ranks the association weights corresponding to each user in the global users, and determines the preset number of users with the largest corresponding association weights as target users of the target identifier.
Specifically, the association weights corresponding to all users in the global users are arranged in the order from large to small, and the previous preset number of users are determined to be target users of the target identification.
As a specific implementation manner, each item further includes a second weight corresponding to the first type tag and the second type tag in the item, and the processing device of the user tag further includes:
the first display module 600 is configured to display a first type of tag corresponding to each target user of the target identifier, where when displaying a first type of tag corresponding to any target user, colors displayed by different first type of tags in the first type of tag corresponding to the target user are determined according to first weights corresponding to different first type of tags in the first type of tag corresponding to the target user, and sizes of areas displayed by different first type of tags in the first type of tag corresponding to the target user are determined according to second weights corresponding to different first type of tags in the first type of tag corresponding to the target user.
In the embodiment, a first label corresponding to a target user is displayed on a user interface; optionally, the color of the display corresponding to the first type label with the larger corresponding first weight in the first type labels corresponding to the same target user is darker; the first type labels corresponding to the first weight values in the first type labels corresponding to the same target user are lighter in the corresponding display colors. The larger the corresponding second weight value of the first type labels corresponding to the same target user is, the larger the corresponding display area size of the first type labels is; the smaller the corresponding second weight value of the first type of labels corresponding to the same target user is, the smaller the corresponding displayed area size is.
In this embodiment, if each entry further includes a second weight corresponding to the first type tag and the second type tag in the entry, as shown in fig. 8, the third obtaining module 300 further includes:
an eighth obtaining module 360 is configured to obtain the information value of each first type tag corresponding to each sample identifier.
In this embodiment, the information value of each first type tag corresponding to each sample identifier is a known value, s k Corresponding e (k) th first class label c k,e(k) The information value of (a) is iv k,e(k) The method comprises the steps of carrying out a first treatment on the surface of the Those skilled in the art will appreciate that the method for obtaining the information value iv is the prior art, and will not be described herein.
A ninth obtaining module 370, configured to obtain a degree of association between each second type tag corresponding to each sample identifier and the sample identifier.
In this embodiment, the association degree between each second type of tag corresponding to each sample identifier and the sample identifier is a known value, and optionally, the association degree is given manually according to experience or given by using a large model; in this embodiment, s k Corresponding f (k) th second class label d k,f(k) The association with the sample identity is sco k,f(k) As a specific embodiment, sco k,f(k) =fen k,f(k) ×count k,f(k) ×weight k,f(k) ×(1+rand k,f(k) )，count k,f(k) D appears in answers to the large model in the case of L times for the large model of question k,f(k) Count of times of (a) k,f(k) L is less than or equal to L, L is preset number of questions, fen k,f(k) For d appearing in answer k,f(k) D of large model answer corresponding to question k,f(k) And s k Weight of the correlation degree of (C) k,f(k) Is d k,f(k) Corresponding weight, weight k,f(k) Equal to d appearing in the answer k,f(k) The sum of the weights corresponding to the questions in this embodiment, the weight corresponding to each question is a known value, rand k,f(k) Is d k,f(k) Corresponding random value, 0<rand k,f(k) <1。
A tenth obtaining module 380, configured to obtain a second association coefficient of association degree and information value of each first type tag and each second type tag corresponding to the same sample identifier.
In this embodiment, s k Corresponding c k,e(k) And d k,f(k) A second association coefficient of the association degree and the information value of (2) is comsi e(k),f(k) ，comsi e(k),f(k) =(sco k,f(k) ×tgid k,f(k) +iv k,e(k) ×tgic k,e(k) )/(tgid k,f(k) +tgic k,e(k) )。
The eleventh obtaining module 390 is configured to obtain second weights of the first type tag and the second type tag corresponding to the same sample identifier according to the second association coefficients and the first association coefficients of the same first type tag and the same second type tag corresponding to different sample identifiers.
In this embodiment, if a certain sample identifier in S corresponds to a certain first type tag (denoted as β 1 ) And a tag of a second type (denoted beta 2 ) Meanwhile, the first type label and the second type label corresponding to the other R sample identifications in S are also identified, and then the first type label is beta 1 And a second class label beta 2 The second weight of (2) is: (Sigma) R+1 r=1 (t r ×δ r ))/(∑ R+1 r=1 δ r )，t r For S comprising the first type tag beta 1 And a second class label beta 2 Corresponding beta is identified by the r-th sample of (c) 1 And beta 2 Is a second correlation coefficient of (a).
A second construction module 3100 is configured to construct a tag association table according to the second weight.
In this embodiment, a tag association table is already constructed according to the first weight, and when a second weight is obtained, the second weight is added to a corresponding entry, so that further construction of the tag association table can be achieved, and each entry of the finally constructed tag association table includes a first type tag, a second type tag, a first weight and a second weight.
In this embodiment, under the condition of acquiring a first type tag corresponding to each user and a second type tag corresponding to a target identifier in a global user, a tag association table is also acquired, a plurality of entries are stored in the tag association table, each entry corresponds to a different tag combination, each tag combination includes a first type tag and a second type tag, the first type tags and the second type tags corresponding to different tag combinations are different, or the first type tag and the second type tag are different; on the basis, the second type labels corresponding to the target identifications are matched in the label association table, corresponding matching items are found, the first type labels in the matching items are the first type labels related to the target identifications, on the basis of obtaining the first type labels related to the target identifications, the first type labels corresponding to each user in the global users are combined, the target users of the target identifications can be screened out from the global users, and the purpose of screening the matched users from the users with the known first type labels according to the second type labels of the target identifications is achieved.
Embodiment III:
the embodiment provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
and obtaining a first type label corresponding to each user in the global users.
And obtaining a second type label corresponding to the target identifier.
Obtaining a tag association table, wherein a plurality of entries are stored in the tag association table, each entry comprises a first type tag, a second type tag and a first weight corresponding to the first type tag and the second type tag in the entry, and the sources of the first type tag and the second type tag are different.
And matching the second type of labels corresponding to the target identification in the label association table to obtain matched items.
And screening target users of the target identification from the global users according to the first type labels and the matched items corresponding to each user in the global users.
Embodiment four:
the present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
and obtaining a first type label corresponding to each user in the global users.
And obtaining a second type label corresponding to the target identifier.
Obtaining a tag association table, wherein a plurality of entries are stored in the tag association table, each entry comprises a first type tag, a second type tag and a first weight corresponding to the first type tag and the second type tag in the entry, and the sources of the first type tag and the second type tag are different.
And matching the second type of labels corresponding to the target identification in the label association table to obtain matched items.
And screening target users of the target identification from the global users according to the first type labels and the matched items corresponding to each user in the global users.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
While certain specific embodiments of the invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the invention. Those skilled in the art will also appreciate that many modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.
Claims (12)
1. A method of handling user tags, the method comprising the steps of:
acquiring a first type tag corresponding to each user in the global users;
obtaining a second type label corresponding to the target identifier;
obtaining a tag association table, wherein a plurality of entries are stored in the tag association table, each entry comprises a first type tag, a second type tag and a first weight corresponding to the first type tag and the second type tag in the entry, and the sources of the first type tag and the second type tag are different;
Matching the second type of labels corresponding to the target identification in the label association table to obtain matched items;
and screening target users of the target identification from the global users according to the first type labels and the matched items corresponding to each user in the global users.
2. The method for processing the user tag according to claim 1, wherein the step of screening the target user of the target identifier from the global user according to the first type tag and the matching entry corresponding to each user in the global user comprises:
comparing a first type tag corresponding to each user in the global users with a first type tag included in the matched item, and if the first type tag corresponding to the user includes the first type tag existing in the matched item, acquiring the association weight of the user and the target identifier according to a first weight corresponding to the first type tag corresponding to the user and existing in the matched item;
and sequencing the association weights corresponding to each user in the global users, and determining the users with the largest corresponding association weights as target users of the target identification.
3. The method for processing a user tag according to claim 1, wherein each item further includes a second weight corresponding to the first type tag and the second type tag in the item, the method further comprising the steps of:
and displaying the first type labels corresponding to each target user of the target identifier, wherein when displaying the first type labels corresponding to any target user, the colors displayed by different first type labels in the first type labels corresponding to the target user are determined according to the first weights corresponding to different first type labels in the first type labels corresponding to the target user, and the sizes of the areas displayed by different first type labels in the first type labels corresponding to the target user are determined according to the second weights corresponding to different first type labels in the first type labels corresponding to the target user.
4. The method for processing a user tag according to claim 1, wherein the process of acquiring the tag association table includes:
acquiring a first type label and a second type label corresponding to a plurality of sample identifiers;
acquiring target population indexes of each first type of tag and each second type of tag corresponding to each sample identifier;
acquiring a first association coefficient of a target population index of each first type of tag and each second type of tag corresponding to the same sample identifier;
Acquiring first weights of the first type labels and the second type labels corresponding to the same sample identification according to first association coefficients of the same first type labels and the same second type labels corresponding to different sample identifications;
and constructing a tag association table according to the first weight.
5. The method for processing a user tag according to claim 4, wherein each entry further includes a second weight corresponding to the first type tag and the second type tag in the entry, and the tag association table obtaining process further includes:
acquiring the information value of each first type tag corresponding to each sample identifier;
acquiring the association degree of each second type label corresponding to each sample identifier and the sample identifier;
acquiring a second association coefficient of the association degree and the information value of each first type of tag and each second type of tag corresponding to the same sample identifier;
obtaining second weights of the first type labels and the second type labels corresponding to the same sample identification according to second association coefficients and first association coefficients of the same first type labels and the same second type labels corresponding to different sample identifications;
and constructing a tag association table according to the second weight.
6. A processing apparatus for user tags, the apparatus comprising:
The first acquisition module is used for acquiring a first type tag corresponding to each user in the global users;
the second acquisition module is used for acquiring a second type of tag corresponding to the target identifier;
the third acquisition module is used for acquiring a label association table, wherein a plurality of items are stored in the label association table, each item comprises a first type label, a second type label and a first weight corresponding to the first type label and the second type label in the item, and the sources of the first type label and the second type label are different;
the first matching module is used for matching the second type of labels corresponding to the target identification in the label association table to obtain matched items;
and the first screening module is used for screening target users of the target identification from the global users according to the first type labels and the matched items corresponding to each user in the global users.
7. The processing apparatus of user tags according to claim 6, wherein said first screening module comprises:
the first comparison module is used for comparing the first type tag corresponding to each user in the global users with the first type tag included in the matched item, and if the first type tag corresponding to the user includes the first type tag existing in the matched item, the association weight of the user and the target identifier is obtained according to the first weight corresponding to the first type tag corresponding to the user and existing in the matched item;
The first ordering module is used for ordering the association weights corresponding to each user in the global users, and determining the users with the corresponding association weights with the largest preset number as target users of the target identification.
8. The processing apparatus of a user tag of claim 6, wherein each entry further comprises a second weight corresponding to the first type tag and the second type tag in the entry, the processing apparatus further comprising:
the first display module is used for displaying the first type of labels corresponding to each target user of the target identifier, wherein when displaying the first type of labels corresponding to any target user, colors displayed by different first type of labels in the first type of labels corresponding to the target user are determined according to first weights corresponding to different first type of labels in the first type of labels corresponding to the target user, and the sizes of areas displayed by different first type of labels in the first type of labels corresponding to the target user are determined according to second weights corresponding to different first type of labels in the first type of labels corresponding to the target user.
9. The processing apparatus of claim 6, wherein the third acquisition module comprises:
A fourth obtaining module, configured to obtain a first type tag and a second type tag corresponding to the plurality of sample identifiers;
the fifth acquisition module is used for acquiring target population indexes of each first type of tag and each second type of tag corresponding to each sample identifier;
a sixth obtaining module, configured to obtain a first association coefficient of a target population index of each first type tag and each second type tag corresponding to the same sample identifier;
a seventh obtaining module, configured to obtain first weights of the first type tag and the second type tag corresponding to the same sample identifier according to first association coefficients of the same first type tag and the same second type tag corresponding to different sample identifiers;
and the first construction module is used for constructing a label association table according to the first weight.
10. The apparatus for processing a user tag according to claim 9, wherein each entry further includes a second weight corresponding to the first type tag and the second type tag in the entry, and the third obtaining module further includes:
an eighth obtaining module, configured to obtain an information value of each first type tag corresponding to each sample identifier;
a ninth obtaining module, configured to obtain a degree of association between each second class tag corresponding to each sample identifier and the sample identifier;
A tenth acquisition module, configured to acquire a second association coefficient of association degree and information value of each first type tag and each second type tag corresponding to the same sample identifier;
an eleventh obtaining module, configured to obtain second weights of the first type tag and the second type tag corresponding to the same sample identifier according to the second association coefficient and the first association coefficient of the same first type tag and the same second type tag corresponding to different sample identifiers;
and the second construction module is used for constructing a label association table according to the second weight.
11. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method of handling a user tag according to any of claims 1 to 5 when executing the computer program.
12. A computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the method of processing a user tag according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410066620.9A CN117573945B (en) | 2024-01-17 | 2024-01-17 | User tag processing method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410066620.9A CN117573945B (en) | 2024-01-17 | 2024-01-17 | User tag processing method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117573945A true CN117573945A (en) | 2024-02-20 |
| CN117573945B CN117573945B (en) | 2024-05-03 |
Family
ID=89888615
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410066620.9A Active CN117573945B (en) | 2024-01-17 | 2024-01-17 | User tag processing method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117573945B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665345A (en) * | 2018-05-07 | 2018-10-16 | 北京科码先锋互联网技术股份有限公司 | Label mapping method |
| CN108960892A (en) * | 2018-06-05 | 2018-12-07 | 北京市商汤科技开发有限公司 | Information processing method and device, electronic equipment and storage medium |
| US20210082026A1 (en) * | 2018-03-07 | 2021-03-18 | Alibaba Group Holding Limited | Content-recommendation method and apparatus, electronic device, and system |
| CN113190746A (en) * | 2021-04-27 | 2021-07-30 | 北京百度网讯科技有限公司 | Recommendation model evaluation method and device and electronic equipment |
| CN116957727A (en) * | 2023-07-21 | 2023-10-27 | 深圳千岸科技股份有限公司 | Commodity recommendation method and device |
-
2024
- 2024-01-17 CN CN202410066620.9A patent/CN117573945B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210082026A1 (en) * | 2018-03-07 | 2021-03-18 | Alibaba Group Holding Limited | Content-recommendation method and apparatus, electronic device, and system |
| CN108665345A (en) * | 2018-05-07 | 2018-10-16 | 北京科码先锋互联网技术股份有限公司 | Label mapping method |
| CN108960892A (en) * | 2018-06-05 | 2018-12-07 | 北京市商汤科技开发有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN113190746A (en) * | 2021-04-27 | 2021-07-30 | 北京百度网讯科技有限公司 | Recommendation model evaluation method and device and electronic equipment |
| CN116957727A (en) * | 2023-07-21 | 2023-10-27 | 深圳千岸科技股份有限公司 | Commodity recommendation method and device |
Non-Patent Citations (2)
| Title |
|---|
| YANRU WANG 等: "The multi-tag semantic correlation used for micro-blog user interest modeling", 《ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE》, 20 August 2019 (2019-08-20) * |
| 李中慧;: "基于标签的个性化信息服务研究", 无线互联科技, no. 05, 31 March 2015 (2015-03-31) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117573945B (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107391547B (en) | Human object data matching method and system | |
| Moreno-Martínez et al. | An ecological alternative to Snodgrass & Vanderwart: 360 high quality colour images with norms for seven psycholinguistic variables | |
| US8812519B1 (en) | Face photograph-based dating recommendation system | |
| CN112955883B (en) | Application recommendation method and device, server and computer-readable storage medium | |
| CN110008397B (en) | Recommendation model training method and device | |
| CN104252628B (en) | Face image annotation method and system | |
| US10210627B1 (en) | Image processing system for determining metrics of objects represented therein | |
| CN108427690A (en) | Information distribution method and device | |
| CN110069619A (en) | Source of houses methods of exhibiting, device, equipment and computer readable storage medium | |
| Tanalgo et al. | Small things matter: the value of rapid biodiversity surveys to understanding local bird diversity patterns in southcentral Mindanao, Philippines | |
| KR20170027576A (en) | Apparatus and method of researcher rcommendation based on matching studying career | |
| CN112231452A (en) | Question-answering method, device, equipment and storage medium based on natural language processing | |
| CN117573945B (en) | User tag processing method, device, equipment and medium | |
| CN113220827B (en) | Construction method and device of agricultural corpus | |
| CN111552810B (en) | Entity extraction and classification method, entity extraction and classification device, computer equipment and storage medium | |
| Merkle et al. | Likelihood‐based photograph identification: Application with photographs of free‐ranging bison | |
| US11360974B2 (en) | Ontology driven crowd sourced multi-dimensional question-answer processing for automated bid processing for rapid bid submission and win rate enhancement | |
| CN115860283B (en) | Contribution degree prediction method and device based on knowledge worker portrait | |
| CN109472197A (en) | A kind of video human face labeling method | |
| CN112818000B (en) | Label library management and application method, system and computer equipment based on multi-label main body | |
| CN111652767B (en) | User portrait construction method and device, computer equipment and storage medium | |
| CN116303910A (en) | Question and answer page recommendation method, device, equipment and storage medium | |
| CN113724044A (en) | User portrait based commodity recommendation, apparatus, computer device and storage medium | |
| CN112883267A (en) | Data heat degree statistical method and device based on deep learning | |
| CN110825898A (en) | Nail art recommendation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |