CN113781062A - User label display method and device - Google Patents
User label display method and device Download PDFInfo
- Publication number
- CN113781062A CN113781062A CN202010768746.2A CN202010768746A CN113781062A CN 113781062 A CN113781062 A CN 113781062A CN 202010768746 A CN202010768746 A CN 202010768746A CN 113781062 A CN113781062 A CN 113781062A
- Authority
- CN
- China
- Prior art keywords
- user
- scene
- tag
- service provider
- determining
- 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 48
- 238000012163 sequencing technique Methods 0.000 claims abstract description 79
- 238000012549 training Methods 0.000 claims description 48
- 238000012545 processing Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 abstract description 24
- 238000010586 diagram Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 8
- 238000002372 labelling Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q30/01—Customer relationship services
-
- 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
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Development Economics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a method and a device for displaying a user label, and relates to the technical field of computers. One embodiment of the method comprises: acquiring a user number of a current session, and determining a user tag corresponding to the user number; identifying a current scene corresponding to the current session, wherein the current scene is one of one or more scenes processed by a service provider; determining a target user label from user labels corresponding to the user numbers according to a sequencing model and the current scene, wherein the sequencing model is used for determining the arrangement sequence of the user labels related to the scene; and displaying the target user label in the current session corresponding to the service provider. The embodiment reduces the calculation amount for determining the target user label, reduces the display cost, improves the subsequent service efficiency and improves the user experience.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for displaying a user label.
Background
Service providers (customer service, sales staff and the like) in the online customer service system usually perform session communication with users through an instant messaging tool based on a webpage, and provide customized services for the users according to user tags of the users so as to achieve the purpose of accurate services.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
1. the number of labels corresponding to each user is large, element points concerned by different service providers under different scenes are different, and the conventional method cannot show the concerned user labels to the service providers, so that the service efficiency is low and the user experience is poor;
2. based on the concerned elements of the service provider and the number of the user tags, particularly under the condition that new user tags are added, the concerned user tags are accurately displayed to the service provider, the calculation amount is large, and the display cost is high.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for displaying a user tag, where a target user tag corresponding to a current session user is determined by a user tag ordering determined by a service provider in a current scene indicated by an ordering model, and is displayed to the service provider, so that a calculation amount for determining the target user tag is reduced, a display cost is reduced, a subsequent service efficiency is improved, and a user experience is improved.
In order to achieve the above object, according to a first aspect of the embodiments of the present invention, there is provided a method for displaying a user tag, including:
acquiring a user number of a current session, and determining a user tag corresponding to the user number;
identifying a current scene corresponding to the current session, wherein the current scene is one of one or more scenes processed by a service provider;
determining a target user label from user labels corresponding to the user numbers according to a sequencing model and the current scene, wherein the sequencing model is used for determining the arrangement sequence of the user labels related to the scene;
and displaying the target user label in the current session corresponding to the service provider.
Optionally, determining the user tag corresponding to the user number further includes:
acquiring historical data of users corresponding to the user numbers, and analyzing and processing the historical data to obtain a label set consisting of a plurality of user labels;
and determining a user label corresponding to the user number according to the historical data of the user who carries out the current session with the service provider.
Optionally, the ranking model is trained by:
for a scene, selecting a plurality of user tags from a tag set and displaying the user tags to a service provider;
receiving an arrangement order of a plurality of user tags selected by a service provider for a scene;
and for the scene, training the sequencing model by taking the arrangement sequence of the plurality of user labels as a training set.
Optionally, for a scene, the ranking order of multiple user tags is used as a training set, and the training of the ranking model includes:
the sequencing model is a two-classification sequencing model;
for a scene, determining the arrangement sequence of every two user tags in the plurality of user tags based on the arrangement sequence of the plurality of user tags, and training the binary sorting model by taking the arrangement sequence of every two user tags as a training set.
Optionally, in a case that a user tag is newly added to the tag set, the method for displaying the user tag further includes: and updating the label set, and retraining the sequencing model based on the updated label set.
Optionally, the step of determining the target user tag from the user tags corresponding to the user numbers according to the ranking model and the current scene further includes:
and determining the target user label from the user labels corresponding to the user numbers according to the sorting model, the target user label quantity threshold and the current scene.
Optionally, before the step of presenting the target user tag in the current session corresponding to the service provider, the method for presenting the user tag further includes:
identifying a sub-scene of a current scene corresponding to a current session;
determining a target user label related to the sub-scene, wherein the target user label related to the sub-scene is selected from the target user labels related to the current scene.
According to a second aspect of the embodiments of the present invention, there is provided a display apparatus for a user tag, including:
the user tag determining module is used for acquiring the user number of the current session and determining a user tag corresponding to the user number;
the current scene identification module is used for identifying a current scene corresponding to the current session, wherein the current scene is one of one or more scenes processed by a service provider;
the target user tag determining module is used for determining a target user tag from user tags corresponding to user numbers according to a sequencing model and a current scene, wherein the sequencing model is used for determining the arrangement sequence of the user tags related to the scene;
and the display module is used for displaying the target user label in the current session corresponding to the service provider.
According to a third aspect of embodiments of the present invention, there is provided an electronic apparatus including:
one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method for presenting a user tag as described above.
According to a fourth aspect of the embodiments of the present invention, there is provided a computer-readable medium, on which a computer program is stored, which when executed by a processor, implements the method for presenting a user tag as described in any one of the above.
One embodiment of the above invention has the following advantages or benefits: the user number of the current session is obtained, and the user label corresponding to the user number is determined; identifying a current scene corresponding to the current session, wherein the current scene is one of one or more scenes processed by a service provider; determining a target user label from user labels corresponding to the user numbers according to a sequencing model and the current scene, wherein the sequencing model is used for determining the arrangement sequence of the user labels related to the scene; the technical means for displaying the target user label in the current session corresponding to the service provider solves the technical problems that in the existing method, due to different attention factors and a large number of user labels of the service provider, the calculation amount for accurately displaying the concerned user label to the service provider is large, the display cost is high, the subsequent service efficiency is low and the user experience is poor, and further achieves the technical effects of reducing the calculation amount for determining the target user label, reducing the display cost, improving the subsequent service efficiency and improving the user experience.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
fig. 1 is a schematic diagram of a main flow of a method for displaying a user tag according to a first embodiment of the present invention;
fig. 2a is a schematic diagram of a main flow of a method for displaying a user tag according to a second embodiment of the present invention;
FIG. 2b is a schematic diagram of a main flow of obtaining a user tag in the method of FIG. 2 a;
FIG. 2c is a schematic diagram of a main flow of training a ranking model in the method of FIG. 2 a;
FIG. 3 is a schematic diagram of the main modules of a display device of user tags provided in accordance with a fifth embodiment of the present invention;
FIG. 4 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
FIG. 5 is a block diagram of a computer system suitable for use with a terminal device implementing an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of a main flow of a method for displaying a user tag according to a first embodiment of the present invention; as shown in fig. 1, the method for displaying a user tag provided by the embodiment of the present invention mainly includes:
step S101, obtaining the user number of the current session, and determining the user label corresponding to the user number.
The user labels are quite rich, each user corresponds to more user labels (such as age, gender, hobbies, interests, occupation, historical complaint rate, risk level, purchasing power level and the like), and with the expansion of basic data dimensions, each user can continuously expand new user notes. By obtaining the user number of the current session, a plurality of (greater than or equal to two) tags corresponding to the user can be determined according to the user number. For the newly added user, under the condition that a large number of user tags are not expanded, only one user tag may be used, but in this case, only the one user tag needs to be displayed to the service provider, and the user tag ordering determined according to the concerned elements of the service provider does not need to be considered any more.
Specifically, according to the embodiment of the present invention, before the step of obtaining the user number of the current session, the method further includes: the method comprises the steps of obtaining historical data of users corresponding to user numbers, obtaining a plurality of user labels based on analysis processing of the historical data, and enabling the user labels to form a label set, wherein the user labels correspond to the user numbers.
The user label is obtained by abstract processing of historical data of the user, the user image can be described through the user label, user characteristics are obtained, and the purpose of accurate service is achieved. Through the arrangement, the user tags obtained by processing the historical data are placed in the tag set, so that all corresponding user numbers can be conveniently determined according to the user numbers, the more comprehensive the user tags corresponding to the obtained user numbers are, the more accurate the subsequently determined target user tags displayed on the service provider are, the quality of corresponding services performed by the service provider according to the target user tags can be improved, and the user experience can be improved.
Step S102, identifying a current scene corresponding to the current session, wherein the current scene is one of one or more scenes processed by the service provider.
The scene corresponding to the session may be a pre-sale scene, a post-sale scene, an order scene, a logistics scene, etc. In different scenes, the service provider may pay different attention to the elements, for example, in a pre-sale scene, the customer service pays more attention to user labels such as user preference, ordering data after user consultation, commodity understanding degree of the user, purchasing power level of the user and the like; in the pre-sale scene, the customer service pays more attention to user labels such as user risk level and tendency, user consultation and evaluation conditions, user after-sale frequency, user influence and the like. Therefore, by identifying the current scene corresponding to the current session, the accuracy rate of displaying the target user tag to the service provider can be further improved.
Step S103, according to the sequencing model and the current scene, determining a target user label from the user labels corresponding to the user numbers, wherein the sequencing model is used for determining the arrangement sequence of the user labels related to the scene.
And sequencing the plurality of user tags determined based on the concerned elements of the service provider under each scene processed by the service provider in the sequencing model, and determining the target user tag according to the current scene and the plurality of user tags corresponding to the user number. It is to be understood that the number of the target user tags is at least one, and in the case that there are a plurality of target user tags, the rank of each user tag is also indicated in the target user tags.
Specifically, according to an embodiment of the present invention, the ranking model is trained by:
for a scene, selecting a plurality of user tags from a tag set and displaying the user tags to a service provider; receiving an arrangement order of a plurality of user tags selected by a service provider for a scene; for a scene, a plurality of user labels are used as a training set to train the ranking model.
The label set comprises user labels corresponding to user numbers, the user labels corresponding to at least one user label are obtained from the label set, then the arrangement sequence of the user labels in the label set under each scene is determined according to the selection of a service provider (the selection is determined by the service provider based on the attention elements under each scene), then the arrangement sequence of the user labels in each scene is used as a training set to train a sequencing model, so that the sequencing model converges, the sequencing of the user labels determined by the service provider under each scene can be obtained, then the target user labels can be determined according to the sequencing model and the current scene, the calculation amount for determining the target user labels is reduced, and the display cost of the subsequent target user labels is reduced.
Further, according to the embodiment of the present invention, for a scene, taking the arrangement order of a plurality of user tags as a training set, the step of training the ranking model includes: the sequencing model is a two-classification sequencing model; for a scene, determining the arrangement sequence of every two user tags in the plurality of user tags based on the arrangement sequence of the plurality of user tags, and training the binary sorting model by taking the arrangement sequence of every two user tags as a training set.
By means of the arrangement, the arrangement sequence of every two user tags in each scene is used as a training set, and Pairwise (PairWise labeling sequencing model/binary sequencing model which sequences every two objects to obtain the partial sequence relation of the training set) is trained to obtain the final sequencing result of the plurality of user tags determined based on the attention element of the service provider in each scene, so that the calculation amount for determining the sequencing result of the plurality of user tags in each scene in the sequencing model can be reduced, and the calculation cost is reduced. It should be noted that any existing ranking model using a ranking learning algorithm, such as PointWise (single-point labeling ranking model, whose main idea is to convert the ranking problem into a multi-classification problem or a regression problem) and LiseWise (list labeling ranking model, which takes all objects as a training set and then obtains a final ranking result through training), may be used as the ranking model.
Preferably, according to an embodiment of the present invention, in a case where a user tag is newly added to a tag set, the method for displaying a user tag further includes: and updating the label set, and retraining the sequencing model based on the updated label set.
With the expansion of basic data dimensions or the increase of the number of acquired user historical data, new user tags are often expanded, for the situation of the new user tags, the arrangement sequence of the new user tags and the plurality of data tags acquired from the tag set under each scene is determined only based on the selection of a service provider, the arrangement sequence of the new user tags and the plurality of user tags under each scene is added into a training set, and the sequencing model is trained again, so that the updating of the sequencing result of the plurality of user tags under each scene in the sequencing model can be realized, the timeliness of the sequencing model is improved, meanwhile, the sequencing model can be adjusted according to the actual requirements of the service provider, and the determination accuracy of the target user tags is improved.
Further, according to the embodiment of the present invention, the step of determining the target user tag from the user tags corresponding to the user numbers according to the ranking model and the current scene further includes:
and determining the target user label from the user labels corresponding to the user numbers according to the sorting model, the target user label quantity threshold and the current scene.
Although the ranking of the plurality of user tags in each scene determined based on the attention elements of the service provider is obtained through the ranking model, when the target user tag is determined, the plurality of user tags corresponding to the user tag do not necessarily need to be displayed with all user tags matching the user tag ranking indicated in the ranking model, and the target user tag can be filtered by setting the threshold of the number of target user tags, so that only the user tag corresponding to the most attention element of the service provider is determined as the target user tag.
And step S104, displaying the target user label in the current session corresponding to the service provider.
Specifically, according to the embodiment of the present invention, before the step of presenting the target user tag in the current session corresponding to the service provider, the method for presenting the user tag further includes:
identifying a sub-scene of a current scene corresponding to a current session;
determining a target user label related to the sub-scene, wherein the target user label related to the sub-scene is selected from the target user labels related to the current scene.
In practical application, the scene is further divided into at least one sub-scene according to the attention elements of the service provider. If the concern element of the service provider in the sub-scenario is the user black yield risk, when the user tag representing the user risk is displayed as "normal", the user tag is meaningless to the service provider, and therefore, in order to improve the accuracy of the target user tag displayed to the service provider and further improve the service efficiency of the subsequent service provider, the target user tag is screened according to the sub-scenario of the current scenario corresponding to the current session. It is to be understood that the above screening step may be understood as a further division of the session scenario, such as for the session scenario determining the risk of the user, the corresponding sub-scenarios may be the sub-scenario determining the risk of black production of the user, and the sub-scenario determining the normal risk of the user.
According to the technical scheme of the embodiment of the invention, the user number of the current session is obtained, and the user label corresponding to the user number is determined; identifying a current scene corresponding to the current session, wherein the current scene is one of one or more scenes processed by a service provider; determining a target user label from user labels corresponding to the user numbers according to a sequencing model and the current scene, wherein the sequencing model is used for determining the arrangement sequence of the user labels related to the scene; the technical means for displaying the target user label in the current session corresponding to the service provider solves the technical problems that in the existing method, due to different attention factors and a large number of user labels of the service provider, the calculation amount for accurately displaying the concerned user label to the service provider is large, the display cost is high, the subsequent service efficiency is low and the user experience is poor, and further achieves the technical effects of reducing the calculation amount for determining the target user label, reducing the display cost, improving the subsequent service efficiency and improving the user experience.
Fig. 2a is a schematic diagram of a main flow of a method for displaying a user tag according to a second embodiment of the present invention; as shown in fig. 2a, the method for displaying a user tag according to the embodiment of the present invention mainly includes:
step S21, obtaining the historical data of the user corresponding to each user number, and analyzing and processing the historical data to obtain a label set consisting of a plurality of user labels; and determining a user label corresponding to the user number according to the historical data of the user who carries out the current session with the service provider.
Specifically, according to the embodiment of the present invention, as shown in fig. 2b, the step S21 mainly includes steps S211 to S213, which are as follows:
step S211, obtaining the historical data of the user corresponding to each user number, wherein the historical data comprises the information of user image, commodity purchasing preference, historical consultation data, appearance preference and the like.
Step S212, a plurality of user tags are obtained based on the analysis processing of the historical data, wherein the analysis processing comprises at least one of the following processing modes: clustering analysis, numerical segmentation, condition judgment and logic calculation, wherein the types corresponding to the data labels comprise Boolean types, character string types, numerical types and the like.
Step S213, placing each user number and its corresponding data tag in a tag set.
The historical data is statistics of data generated by historical behaviors of a user in a past period of time, and specifically, the historical data can be determined by historical consultation session records (only as an example, the historical data can be acquired by a plurality of platforms/channels in practical application), the historical data mainly comprises session evaluation records, ordering records, after-sales records and risk analysis data of the user by a customer service system, and the user portrait can be comprehensively depicted by the historical data to generate a corresponding user label. Through the setting, analyzing and processing the user historical data in one or more modes of cluster analysis, data segmentation, condition judgment and logic calculation to obtain a user label; further, the label values can be divided into different types of user labels such as a Boolean type, a text type, a character string type, a numerical value type and the like according to the label values. For example, the label value of the user label 'historical complaint rate' is data between 0 and 1, and the type of the data is a numerical type; the label value corresponding to the user label 'whether the user label is pregnant' is yes or no, and the type of the label is a Boolean type; the label value corresponding to the user label "occupation" is student, teacher, etc., and the type is text type.
According to a specific implementation manner of the embodiment of the present invention, the step of obtaining the user tag may be performed by a tag relation system.
Step S22, selecting a plurality of user tags from the tag set for a scenario (a scenario handled by the service provider) and presenting the selected user tags to the service provider; receiving an arrangement sequence of a plurality of user tags selected by a service provider according to a scene; for the scene, the ranking model is trained by taking the arrangement sequence of a plurality of user labels as a training set.
Through the arrangement, the sequencing of the user tags determined based on the service provider under each scene is obtained, and then the target user tags can be subsequently determined according to the sequencing model and the current scene, so that the calculation amount for determining the target user tags is reduced, and the display cost of the subsequent target user tags is reduced.
Further, according to the embodiment of the present invention, the ranking model is a two-class ranking model, the ranking order of the plurality of user tags in each scene is determined according to the selection of the service provider, and the training of the ranking model using the ranking order of the plurality of user tags in each scene as a training set includes:
and determining the arrangement sequence of every two user tags in the plurality of user tags under each scene, and training the two-classification ordering model by taking the arrangement sequence of every two user tags under each scene as a training set.
By means of the arrangement, Pairwise (PairWise labeling sequencing model/two-classification sequencing model which is used for sequencing every two objects to obtain the partial sequencing relation of a training set) is adopted for training to obtain the final sequencing result of the plurality of user labels determined based on the attention elements of the service provider under each scene, the calculation amount of the sequencing result of the plurality of user labels under each scene in the sequencing model can be reduced, and the calculation cost is reduced.
Preferably, according to an embodiment of the present invention, in a case where a user tag is newly added to a tag set, the method for displaying a user tag further includes: and determining the arrangement sequence of the newly added user tag and the plurality of user tags in each scene according to the selection of the service provider, adding the arrangement sequence of the newly added user tag and the plurality of user tags in each scene into a training set, and training the sequencing model.
Through the arrangement, the sequencing results of the plurality of user tags in each scene in the sequencing model are updated, the timeliness of the sequencing model is improved, meanwhile, the sequencing model is convenient to adjust according to the actual requirements of the service provider, and the determination accuracy of the target user tags is improved.
Further, according to the embodiment of the present invention, the step of determining the target user tag from the plurality of user tags according to the ranking model and the current scene further includes:
and determining the target user label from the plurality of user labels according to the sorting model, the target user label quantity threshold and the current scene.
By setting the threshold value of the number of the target user tags, the target user tags can be filtered, and only the user tag corresponding to the most concerned element of the service provider is determined as the target user tag.
Further, according to the embodiment of the present invention, as shown in fig. 2c, the training step of the ranking model shown in step S22 above may be further implemented by:
step S221, generating a consultation problem list based on each scene, wherein the consultation problem list indicates the user label display sequence which can be selected by the service provider.
Step S222, receiving the display sequence selected by the service provider, and splitting the display sequence to obtain an arrangement sequence corresponding to any two user tags.
Step S223, inputting the corresponding arrangement order of any two user tags as a training sample into the two-classification ranking model, and training the two-classification ranking model.
Further, according to the embodiment of the present invention, the aforementioned consultation question list may further include consultation questions (e.g., in which order the service provider desires the following labels to be shown in the after-sales consultation scenario), and random N user labels (randomly extracted from the label set, such as [ a. The display sequence expected by the service provider is obtained by counting the selections of the service provider determined based on the concerned elements of the service provider. Specifically, the two-classification ranking model may be an AdaBoost-based RankBoost model (for example only), and the trained ranking model may be used to recommend the user tag.
Step S23, the user number of the current session is acquired, and the user tag corresponding to the user number is determined.
By obtaining the user number of the current session, a plurality of (greater than or equal to two) tags corresponding to the user can be determined according to the user number.
In step S24, a current scene corresponding to the current session is identified, where the current scene is one of one or more scenes handled by the service provider.
Because the concerned elements of the service provider may be different in different scenes, the accuracy rate of displaying the target user tag to the service provider can be further improved by identifying the current scene corresponding to the current session.
And step S25, determining a target user label from the user labels corresponding to the user numbers according to the sequencing model and the current scene.
And determining the sequence of the plurality of user tags determined based on the concerned elements of the service provider in each scene in the sequencing model, and determining the target user tag according to the current scene and the plurality of user tags corresponding to the user number. It is to be understood that the number of the target user tags is at least one, and in the case that there are a plurality of target user tags, the rank of each user tag is also indicated in the target user tags.
And step S26, identifying the sub-scenes of the current scene corresponding to the current session, and determining the target user labels related to the sub-scenes.
In practical application, the scene is further divided into at least one sub-scene according to the attention elements of the service provider. If the concern element of the service provider in the sub-scenario is the user black yield risk, when the user tag representing the user risk is displayed as "normal", the user tag is meaningless to the service provider, and therefore, in order to improve the accuracy of the target user tag displayed to the service provider and further improve the service efficiency of the subsequent service provider, the target user tag is screened according to the sub-scenario of the current scenario corresponding to the current session. It is to be understood that the above screening step may be understood as a further division of the session scenario, such as for the session scenario determining the risk of the user, the corresponding sub-scenarios may be the sub-scenario determining the risk of black production of the user, and the sub-scenario determining the normal risk of the user.
And step S27, displaying the target user label in the current session corresponding to the service provider.
According to the technical scheme of the embodiment of the invention, the user number of the current session is obtained, and the user label corresponding to the user number is determined; identifying a current scene corresponding to a current session; determining a target user label from user labels corresponding to the user numbers according to a sequencing model and a current scene, wherein the sequencing model is obtained according to sequencing of a plurality of user labels by a service provider under each scene; the technical means for displaying the target user label in the current session corresponding to the service provider solves the technical problems that in the existing method, due to different attention factors and a large number of user labels of the service provider, the calculation amount for accurately displaying the concerned user label to the service provider is large, the display cost is high, the subsequent service efficiency is low and the user experience is poor, and further achieves the technical effects of reducing the calculation amount for determining the target user label, reducing the display cost, improving the subsequent service efficiency and improving the user experience.
FIG. 3 is a schematic diagram of the main modules of a display device of user tags provided in accordance with a fifth embodiment of the present invention; as shown in fig. 3, the apparatus 300 for displaying a user tag according to an embodiment of the present invention mainly includes:
the user tag determining module 301 is configured to obtain a user number of a current session, and determine a user tag corresponding to the user number.
The user labels are quite rich, each user corresponds to more user labels (such as age, sex, hobbies, interests, risk levels, purchasing power levels and the like), and with the expansion of basic data dimensions, each user can continuously expand new user notes. By obtaining the user number of the current session, a plurality of (greater than or equal to two) tags corresponding to the user can be determined according to the user number. For the newly added user, under the condition that a large number of user tags are not expanded, only one user tag may be used, but in this case, only the one user tag needs to be displayed to the service provider, and the user tag ordering determined according to the concerned elements of the service provider does not need to be considered any more.
Specifically, according to an embodiment of the present invention, the apparatus 300 for displaying a user tag further includes a tag set combining module, and before the step of obtaining the user number of the current session, the tag set combining module is configured to: the method comprises the steps of obtaining historical data of users corresponding to user numbers, obtaining a plurality of user labels based on analysis processing of the historical data, and enabling the user labels to form a label set, wherein the user labels correspond to the user numbers.
The user label is obtained by abstract processing of historical data of the user, the user image can be described through the user label, user characteristics are obtained, and the purpose of accurate service is achieved. Through the arrangement, the user tags obtained by processing the historical data are placed in the tag set, so that all corresponding user numbers can be conveniently determined according to the user numbers, the more comprehensive the user tags corresponding to the obtained user numbers are, the more accurate the subsequently determined target user tags displayed on the service provider are, the quality of corresponding services performed by the service provider according to the target user tags can be improved, and the user experience can be improved.
A current scene identification module 302, configured to identify a current scene corresponding to the current session, where the current scene is one of the one or more scenes processed by the service provider.
In different scenes, the service provider may pay different attention to the elements, for example, in a pre-sale scene, the customer service pays more attention to user labels such as user preference, ordering data after user consultation, commodity understanding degree of the user, purchasing power level of the user and the like; in the pre-sale scene, the customer service pays more attention to user labels such as user risk level and tendency, user consultation and evaluation conditions, user after-sale frequency, user influence and the like. Therefore, by identifying the current scene corresponding to the current session, the accuracy rate of displaying the target user tag to the service provider can be further improved.
And a target user tag determining module 303, configured to determine a target user tag from the user tags corresponding to the user numbers according to a ranking model and the current scene, where the ranking model is used to determine an arrangement order of the user tags related to the scene.
And sequencing the plurality of user tags determined based on the concerned elements of the service provider under each scene processed by the service provider in the sequencing model, and determining the target user tag according to the current scene and the user tag corresponding to the user number. It is to be understood that the number of the target user tags is at least one, and in the case that there are a plurality of target user tags, the rank of each user tag is also indicated in the target user tags.
Specifically, according to the embodiment of the present invention, the apparatus 300 for displaying user tags further includes a ranking model training module, configured to:
for a scene, selecting a plurality of user tags from a tag set and displaying the user tags to a service provider; receiving an arrangement order of a plurality of user tags selected by a service provider for a scene; for a scene, a plurality of user labels are used as a training set to train the ranking model.
The label set comprises user labels corresponding to user numbers, the user labels corresponding to at least one user label are obtained from the label set, then the arrangement sequence of the user labels in the label set under each scene is determined according to the selection of a service provider (the selection is determined by the service provider based on the attention elements under each scene), then the arrangement sequence of the user labels in each scene is used as a training set to train a sequencing model, so that the sequencing model converges, the sequencing of the user labels determined by the service provider under each scene can be obtained, then the target user labels can be determined according to the sequencing model and the current scene, the calculation amount for determining the target user labels is reduced, and the display cost of the subsequent target user labels is reduced.
Further, according to an embodiment of the present invention, the ranking model is a two-class ranking model, and the ranking model training module is further configured to:
for a scene, determining the arrangement sequence of every two user tags in the plurality of user tags based on the arrangement sequence of the plurality of user tags, and training the binary sorting model by taking the arrangement sequence of every two user tags as a training set. By means of the arrangement, the arrangement sequence of every two user tags in each scene is used as a training set, and Pairwise (PairWise labeling sequencing model/binary sequencing model which sequences every two objects to obtain the partial sequence relation of the training set) is trained to obtain the final sequencing result of the plurality of user tags determined based on the attention element of the service provider in each scene, so that the calculation amount for determining the sequencing result of the plurality of user tags in each scene in the sequencing model can be reduced, and the calculation cost is reduced. It should be noted that any existing ranking model using a ranking learning algorithm, such as PointWise (single-point labeling ranking model, whose main idea is to convert the ranking problem into a multi-classification problem or a regression problem) and LiseWise (list labeling ranking model, which takes all objects as a training set and then obtains a final ranking result through training), may be used as the ranking model.
Preferably, according to the embodiment of the present invention, in a case that a user tag is newly added to the tag set, the ranking model training module is further configured to: and updating the label set, and retraining the sequencing model based on the updated label set.
With the expansion of basic data dimensions or the increase of the number of acquired user historical data, new user tags are often expanded, for the situation of the new user tags, the arrangement sequence of the new user tags and the plurality of data tags acquired from the tag set under each scene is determined only based on the selection of a service provider, the arrangement sequence of the new user tags and the plurality of user tags under each scene is added into a training set, and the sequencing model is trained again, so that the updating of the sequencing result of the plurality of user tags under each scene in the sequencing model can be realized, the timeliness of the sequencing model is improved, meanwhile, the sequencing model can be adjusted according to the actual requirements of the service provider, and the determination accuracy of the target user tags is improved.
Further, according to the embodiment of the present invention, the target user tag determining module 303 is further configured to: and determining the target user label from the user labels corresponding to the user numbers according to the sorting model, the target user label quantity threshold and the current scene.
Although the ranking of the plurality of user tags in each scene determined based on the attention elements of the service provider is obtained through the ranking model, when the target user tag is determined, the plurality of user tags corresponding to the user tag do not necessarily need to be displayed with all user tags matching the user tag ranking indicated in the ranking model, and the target user tag can be filtered by setting the threshold of the number of target user tags, so that only the user tag corresponding to the most attention element of the service provider is determined as the target user tag.
And the display module 304 is configured to display the target user tag in the current session corresponding to the customer service.
Specifically, according to an embodiment of the present invention, the apparatus 300 for displaying a user tag further includes a target user tag screening module, and before the step of displaying the target user tag in the current session corresponding to the service provider, the target user tag screening module is configured to:
identifying a sub-scene of a current scene corresponding to a current session;
determining a target user label related to the sub-scene, wherein the target user label related to the sub-scene is selected from the target user labels related to the current scene.
In practical application, the scene is further divided into at least one sub-scene according to the attention elements of the service provider. If the concern element of the service provider in the sub-scenario is the user black yield risk, when the user tag representing the user risk is displayed as "normal", the user tag is meaningless to the service provider, and therefore, in order to improve the accuracy of the target user tag displayed to the service provider and further improve the service efficiency of the subsequent service provider, the target user tag is screened according to the sub-scenario of the current scenario corresponding to the current session. It is to be understood that the above screening step may be understood as a further division of the session scenario, such as for the session scenario determining the risk of the user, the corresponding sub-scenarios may be the sub-scenario determining the risk of black production of the user, and the sub-scenario determining the normal risk of the user.
According to the technical scheme of the embodiment of the invention, the user number of the current session is obtained, and the user label corresponding to the user number is determined; identifying a current scene corresponding to the current session, wherein the current scene is one of one or more scenes processed by a service provider; determining a target user label from user labels corresponding to the user numbers according to a sequencing model and the current scene, wherein the sequencing model is used for determining the arrangement sequence of the user labels related to the scene; the technical means for displaying the target user label in the current session corresponding to the service provider solves the technical problems that in the existing method, due to different attention factors and a large number of user labels of the service provider, the calculation amount for accurately displaying the concerned user label to the service provider is large, the display cost is high, the subsequent service efficiency is low and the user experience is poor, and further achieves the technical effects of reducing the calculation amount for determining the target user label, reducing the display cost, improving the subsequent service efficiency and improving the user experience.
Fig. 4 shows an exemplary system architecture 400 of a method or apparatus for presenting a user tag to which embodiments of the present invention may be applied.
As shown in fig. 4, the system architecture 400 may include terminal devices 401, 402, 403, a network 404, and a server 405. The network 404 serves to provide a medium for communication links between the terminal devices 401, 402, 403 and the server 405. Network 404 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 401, 402, 403 to interact with a server 405 over a network 404 to receive or send messages or the like. The terminal devices 401, 402, 403 may have various communication client applications installed thereon, such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, and the like.
The terminal devices 401, 402, 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 405 may be a server providing various services, such as a background management server providing support for pictures or information acquired by the user using the terminal device 401, 402, 403. The background management server may analyze and perform other processing on the received data such as the user number and the current scene, and feed back a processing result (e.g., a target user tag) to the terminal device.
It should be noted that, the method for displaying the user tag provided by the embodiment of the present invention is generally executed by the terminal device 401, 402, or 403 or the server 405, and accordingly, a device for displaying the user tag is generally disposed in the terminal device 401, 402, or 403 or the server 405.
It should be understood that the number of terminal devices, networks, and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 5, shown is a block diagram of a computer system 500 suitable for use with a terminal device implementing an embodiment of the present invention. The terminal device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU)501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 501.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor comprising: the system comprises a user tag determining module, a current scene identifying module, a target user tag determining module and a display module. The names of these modules do not constitute a limitation to the module itself in some cases, for example, the user tag determination module may also be described as "a module for obtaining a user number of a current session, determining a user tag corresponding to the user number".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: acquiring a user number of a current session, and determining a user tag corresponding to the user number; identifying a current scene corresponding to the current session, wherein the current scene is one of one or more scenes processed by a service provider; determining a target user label from user labels corresponding to the user numbers according to a sequencing model and the current scene, wherein the sequencing model is used for determining the arrangement sequence of the user labels related to the scene; and displaying the target user label in the current session corresponding to the service provider.
According to the technical scheme of the embodiment of the invention, the user number of the current session is obtained, and the user label corresponding to the user number is determined; identifying a current scene corresponding to the current session, wherein the current scene is one of one or more scenes processed by a service provider; determining a target user label from user labels corresponding to the user numbers according to a sequencing model and the current scene, wherein the sequencing model is used for determining the arrangement sequence of the user labels related to the scene; the technical means for displaying the target user label in the current session corresponding to the service provider solves the technical problems that in the existing method, due to different attention factors and a large number of user labels of the service provider, the calculation amount for accurately displaying the concerned user label to the service provider is large, the display cost is high, the subsequent service efficiency is low and the user experience is poor, and further achieves the technical effects of reducing the calculation amount for determining the target user label, reducing the display cost, improving the subsequent service efficiency and improving the user experience.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for displaying a user tag is characterized by comprising the following steps:
acquiring a user number of a current session, and determining a user tag corresponding to the user number;
identifying a current scene corresponding to the current session, wherein the current scene is one of one or more scenes processed by a service provider;
determining a target user label from the user labels corresponding to the user numbers according to a sorting model and the current scene, wherein the sorting model is used for determining the arrangement sequence of the user labels related to the scene;
and displaying the target user label in a current session corresponding to a service provider.
2. The method for displaying a user tag according to claim 1, wherein the determining the user tag corresponding to the user number further comprises:
acquiring historical data of users corresponding to the user numbers, and analyzing and processing the historical data to obtain a label set consisting of a plurality of user labels;
and determining the user label corresponding to the user number according to the historical data of the user who carries out the current session with the service provider.
3. The method of claim 2, wherein the ranking model is trained by:
for the scene, selecting a plurality of user tags from the tag set and displaying the user tags to a service provider;
receiving an arrangement order of the plurality of user tags selected by the service provider for the scene;
and for the scene, training the sequencing model by taking the arrangement sequence of the plurality of user labels as a training set.
4. The method according to claim 3, wherein the training the ranking model with the ranking order of the plurality of user labels as a training set for the scene comprises:
the sorting model is a two-classification sorting model;
and for the scene, determining the arrangement sequence of every two user tags in the user tags based on the arrangement sequence of the user tags, and training the two-classification ordering model by taking the arrangement sequence of every two user tags as a training set.
5. The method for displaying the user tag according to claim 3, wherein in a case where a user tag is newly added to the tag set, the method for displaying the user tag further comprises: and updating the label set, and retraining the sequencing model based on the updated label set.
6. The method for displaying user tags according to claim 1, wherein the step of determining the target user tag from the user tags corresponding to the user numbers according to the ranking model and the current scene further comprises:
and determining a target user label from the user labels corresponding to the user numbers according to the sorting model, the target user label quantity threshold and the current scene.
7. The method as claimed in claim 1, wherein before the step of presenting the target user tag in the current session corresponding to the service provider, the method further comprises:
identifying a sub-scene of a current scene corresponding to the current session;
determining a target user label associated with the sub-scene, wherein the target user label associated with the sub-scene is selected from the target user labels associated with the current scene.
8. A user tag display apparatus, comprising:
the user tag determining module is used for acquiring the user number of the current session and determining a user tag corresponding to the user number;
a current scene identification module, configured to identify a current scene corresponding to the current session, where the current scene is one of one or more scenes processed by a service provider;
a target user tag determining module, configured to determine a target user tag from user tags corresponding to the user numbers according to a ranking model and the current scene, where the ranking model is used to determine an arrangement order of the user tags related to the scene;
and the display module is used for displaying the target user label in the current session corresponding to the service provider.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.
10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010768746.2A CN113781062A (en) | 2020-08-03 | 2020-08-03 | User label display method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010768746.2A CN113781062A (en) | 2020-08-03 | 2020-08-03 | User label display method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113781062A true CN113781062A (en) | 2021-12-10 |
Family
ID=78835118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010768746.2A Pending CN113781062A (en) | 2020-08-03 | 2020-08-03 | User label display method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113781062A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108242016A (en) * | 2018-01-25 | 2018-07-03 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus of Products Show |
| US20190026367A1 (en) * | 2017-07-24 | 2019-01-24 | International Business Machines Corporation | Navigating video scenes using cognitive insights |
| CN110197188A (en) * | 2018-02-26 | 2019-09-03 | 北京京东尚科信息技术有限公司 | Method, system, equipment and the storage medium of business scenario prediction, classification |
| CN110275692A (en) * | 2019-05-20 | 2019-09-24 | 北京百度网讯科技有限公司 | A kind of recommended method of phonetic order, device, equipment and computer storage medium |
| CN110427546A (en) * | 2018-04-28 | 2019-11-08 | 北京京东尚科信息技术有限公司 | A kind of information displaying method and device |
-
2020
- 2020-08-03 CN CN202010768746.2A patent/CN113781062A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190026367A1 (en) * | 2017-07-24 | 2019-01-24 | International Business Machines Corporation | Navigating video scenes using cognitive insights |
| CN108242016A (en) * | 2018-01-25 | 2018-07-03 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus of Products Show |
| CN110197188A (en) * | 2018-02-26 | 2019-09-03 | 北京京东尚科信息技术有限公司 | Method, system, equipment and the storage medium of business scenario prediction, classification |
| CN110427546A (en) * | 2018-04-28 | 2019-11-08 | 北京京东尚科信息技术有限公司 | A kind of information displaying method and device |
| CN110275692A (en) * | 2019-05-20 | 2019-09-24 | 北京百度网讯科技有限公司 | A kind of recommended method of phonetic order, device, equipment and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460513B (en) | Method and apparatus for generating click rate prediction model | |
| CN109522483B (en) | Method and device for pushing information | |
| CN107944481B (en) | Method and apparatus for generating information | |
| CN107426328B (en) | Information pushing method and device | |
| CN110020162B (en) | User identification method and device | |
| US20160189201A1 (en) | Enhanced targeted advertising system | |
| CN108280200B (en) | Method and device for pushing information | |
| CN111125574A (en) | Method and apparatus for generating information | |
| CN110866040B (en) | User portrait generation method, device and system | |
| CN112241327A (en) | Shared information processing method and device, storage medium and electronic equipment | |
| CN111695041B (en) | Method and device for recommending information | |
| CN111104590A (en) | Information recommendation method, device, medium and electronic equipment | |
| CN112749323A (en) | Method and device for constructing user portrait | |
| CN111125502B (en) | Method and device for generating information | |
| CN113763004A (en) | Information matching method and device | |
| CN111782850A (en) | Object searching method and device based on hand drawing | |
| CN113781062A (en) | User label display method and device | |
| CN111125501B (en) | Method and device for processing information | |
| CN111126649B (en) | Method and device for generating information | |
| CN111857875A (en) | Method and device for displaying plug-ins | |
| CN107368597B (en) | Information output method and device | |
| CN116911912B (en) | Method and device for predicting interaction objects and interaction results | |
| CN107180037B (en) | Man-machine interaction method and device | |
| CN111626805B (en) | Information display method and device | |
| CN109857461B (en) | Page generation method and device |
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 |