CN115563397B - Electronic file recommendation method and terminal - Google Patents
Electronic file recommendation method and terminal Download PDFInfo
- Publication number
- CN115563397B CN115563397B CN202211557102.4A CN202211557102A CN115563397B CN 115563397 B CN115563397 B CN 115563397B CN 202211557102 A CN202211557102 A CN 202211557102A CN 115563397 B CN115563397 B CN 115563397B
- Authority
- CN
- China
- Prior art keywords
- recommendation
- recommendation list
- electronic file
- user
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an electronic file recommendation method and a terminal, wherein office piece planning information and contact control configuration information are read, and the office piece planning information comprises user group information and a target electronic file; acquiring a recommendation model corresponding to user group information, and acquiring a first recommendation list corresponding to a user group according to the recommendation model; obtaining a fusion calculation result according to the first recommendation list and the office planning information; obtaining a target recommendation list according to the fusion calculation result; pushing a target electronic file according to the target recommendation list and the contact control configuration information; according to the method, the trained recommendation model is used for matching the first recommendation list for the user group, the calculated first recommendation list and the set office piece planning information can be fused, the comprehensive setting information and the model calculation information are matched, and finally the contact control configuration information is introduced, so that the accurate setting of the pushing process is realized, and the use habits of different user groups can be matched.
Description
Technical Field
The invention relates to the field of electronic government affairs, in particular to an electronic file recommendation method and a terminal.
Background
Because various policy documents in different regions have gaps, and the subject to which each document is directed is different, if the subject does not pay special attention to the release and change of the policy documents, preferential policies which can be declared by the subject or events which can be participated in by the subject can be missed, so that certain inconvenience is brought to production, operation or life.
In a traditional operation mode, an APP end is usually used as a carrier, and a preset carousel advertisement space and a floating advertisement space are usually used as recommended channels. The decision of recommended contents and materials depends on the control of main requirements of decision makers, and the recommendation mode is usually defined as 'expert experience'. There are several drawbacks to this traditional model: firstly, the accuracy of recommended content and materials completely depends on the prejudgment of experts, the influence of subjective factors is large, and the operation risk is high; secondly, recommended contents are uniformly configured by a system background, one of thousands of people is lack of personalized visual impact and personalized recommendation modes, and the purpose of accurate recommendation is difficult to achieve; and thirdly, the recommended content is kept unchanged before being artificially changed, and iteration is not carried out along with the change of the user behavior.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the electronic file recommendation method and the terminal are provided, and accurate matching of the electronic file and a demander is achieved.
In order to solve the technical problem, the invention adopts a technical scheme that:
an electronic file recommendation method includes the steps:
reading office piece planning information and contact control configuration information, wherein the office piece planning information comprises user group information and a target electronic file;
acquiring a recommendation model corresponding to the user group information, and acquiring a first recommendation list corresponding to the user group according to the recommendation model;
obtaining a fusion calculation result according to the first recommendation list and the office planning information;
obtaining a target recommendation list according to the fusion calculation result;
and pushing the target electronic file according to the target recommendation list and the contact control configuration information.
In order to solve the technical problem, the invention adopts another technical scheme as follows:
an electronic document recommendation terminal comprising 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:
reading office piece planning information and contact control configuration information, wherein the office piece planning information comprises user group information and a target electronic file;
acquiring a recommendation model corresponding to the user group information, and acquiring a first recommendation list corresponding to the user group according to the recommendation model;
obtaining a fusion calculation result according to the first recommendation list and office element planning information;
obtaining a target recommendation list according to the fusion calculation result;
and pushing the target electronic file according to the target recommendation list and the contact control configuration information.
The invention has the beneficial effects that: the method comprises the steps of obtaining a first recommendation list corresponding to a user group according to a recommendation model corresponding to user group information matching set in office piece planning information, then carrying out fusion calculation with the office piece planning information to obtain a target recommendation list, finally carrying out pushing of a target electronic file according to the target recommendation list and contact control configuration information, matching the first recommendation list for the user group by using a trained recommendation model, fusing the calculated first recommendation list with the set office piece planning information, matching the comprehensive setting information with the model calculation information, and finally introducing the contact control configuration information to realize accurate setting of a pushing process and match use habits of different user groups.
Drawings
FIG. 1 is a flowchart illustrating steps of a method for recommending electronic documents according to an embodiment of the present invention;
FIG. 2 is another flowchart illustrating an electronic document recommendation method according to an embodiment of the invention;
fig. 3 is a schematic structural diagram of an electronic file recommendation terminal according to an embodiment of the present invention;
description of reference numerals:
1. an electronic file recommendation terminal; 2. a processor; 3. a memory.
Detailed Description
In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.
Referring to fig. 1, an electronic file recommendation method includes the steps of:
office piece planning information and contact control configuration information are read, wherein the office piece planning information comprises user group information and a target electronic file;
acquiring a recommendation model corresponding to the user group information, and obtaining a first recommendation list corresponding to the user group according to the recommendation model;
obtaining a fusion calculation result according to the first recommendation list and the office planning information;
obtaining a target recommendation list according to the fusion calculation result;
and pushing the target electronic file according to the target recommendation list and the contact control configuration information.
As can be seen from the above description, the beneficial effects of the present invention are: the method comprises the steps of matching a corresponding recommendation model according to user group information set in office piece planning information to obtain a first recommendation list corresponding to a user group, performing fusion calculation with the office piece planning information to obtain a target recommendation list, pushing a target electronic file according to the target recommendation list and the contact control configuration information, fusing the calculated first recommendation list with the set office piece planning information, matching comprehensive setting information with model calculation information, and introducing the contact control configuration information to realize accurate setting of a pushing process and match use habits of different user groups.
Further, the obtaining a first recommendation list corresponding to the user group according to the recommendation model includes:
obtaining a recommendation label corresponding to each user in the user group information by the user group information through the recommendation model;
and associating the user and the recommendation label to obtain the first recommendation list.
According to the description, matching a corresponding recommendation label for each user in the user group information through the recommendation model, and obtaining a first recommendation list according to the association relationship between the recommendation label and the user; the trained recommendation model can automatically mark a label for a user, the user and the target electronic file can be conveniently associated, the subsequent electronic file can be accurately pushed, different users can match different target electronic files according to different labels, personalized recommendation of the electronic file can be achieved, and the most suitable electronic file can be matched for the user.
Further, the office planning information comprises a second recommendation list and preset filtering conditions;
the obtaining of the fusion calculation result according to the first recommendation list and the office element planning information comprises:
merging the same items in the first recommendation list and the second recommendation list;
sorting the items in the first recommendation list and the second recommendation list according to preset keywords to obtain an initial recommendation list;
and filtering the items in the initial recommendation list according to the preset filtering condition to obtain a fusion calculation result.
According to the description, the second recommendation list can be set in the office planning information and is fused with the first recommendation list obtained by the recommendation model calculation, the fusion comprises combination, sorting and filtering, the fusion calculation result obtained by fusion is more convenient to read, the calculation result of the model and the setting of people are integrated, and the flexibility of recommendation is improved.
Further, after the pushing of the target electronic file according to the target recommendation list and the contact control configuration information, the method includes:
acquiring click data, wherein the click data comprises click user information, click time and a click electronic file;
and updating the recommendation model according to the click user information, the click time and the click electronic file.
According to the description, after the pushing is carried out, the recommendation model is optimized according to the actual click data of the user, the recommendation model can be automatically updated according to the change of the user behavior, the self-adaption of the recommendation model is realized, and the new model does not need to be retrained even if the user group behavior changes.
Further, the contact control configuration information comprises a pushing channel corresponding to the target electronic file, a pushing time period associated with the pushing channel, and a pushing frequency;
the pushing of the target electronic file according to the target recommendation list and the contact control configuration information comprises:
obtaining a recommended user corresponding to the target electronic file according to the target recommendation list;
and sending the target electronic file to the recommending user according to a pushing channel corresponding to the target electronic file, a pushing time period associated with the pushing channel and a pushing frequency.
According to the description, the push time periods and the push frequencies corresponding to the push channels and the push channels are configured, so that targeted push can be performed according to the habits of users in different push channels, and the accuracy of pushing the target electronic file is improved.
Referring to fig. 3, an electronic document recommendation terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the following steps:
reading office piece planning information and contact control configuration information, wherein the office piece planning information comprises user group information and a target electronic file;
acquiring a recommendation model corresponding to the user group information, and obtaining a first recommendation list corresponding to the user group according to the recommendation model;
obtaining a fusion calculation result according to the first recommendation list and office element planning information;
obtaining a target recommendation list according to the fusion calculation result;
and pushing the target electronic file according to the target recommendation list and the contact control configuration information.
The invention has the beneficial effects that: the method comprises the steps of obtaining a first recommendation list corresponding to a user group according to a recommendation model corresponding to user group information matching set in office piece planning information, then carrying out fusion calculation with the office piece planning information to obtain a target recommendation list, finally carrying out pushing of a target electronic file according to the target recommendation list and contact control configuration information, matching the first recommendation list for the user group by using a trained recommendation model, fusing the calculated first recommendation list with the set office piece planning information, matching the comprehensive setting information with the model calculation information, and finally introducing the contact control configuration information to realize accurate setting of a pushing process and match use habits of different user groups.
Further, the obtaining of the first recommendation list corresponding to the user group according to the recommendation model includes:
obtaining a recommendation label corresponding to each user in the user group information by the user group information through the recommendation model;
and associating the user and the recommendation label to obtain the first recommendation list.
According to the description, matching a corresponding recommendation label for each user in the user group information through the recommendation model, and obtaining a first recommendation list according to the association relationship between the recommendation label and the user; the trained recommendation model can automatically mark a label for a user, the user and the target electronic file can be conveniently associated, the subsequent electronic file can be accurately pushed, different users can match different target electronic files according to different labels, personalized recommendation of the electronic file can be achieved, and the most suitable electronic file can be matched for the user.
Further, the office planning information comprises a second recommendation list and a preset filtering condition;
the obtaining of the fusion calculation result according to the first recommendation list and the office element planning information comprises:
merging the same items in the first recommendation list and the second recommendation list;
sorting the items in the first recommendation list and the second recommendation list according to preset keywords to obtain an initial recommendation list;
and filtering the items in the initial recommendation list according to the preset filtering condition to obtain a fusion calculation result.
According to the description, the second recommendation list can be set in the office planning information and is fused with the first recommendation list obtained by the recommendation model calculation, the fusion comprises combination, sorting and filtering, the fusion calculation result obtained by fusion is more convenient to read, the calculation result of the model and the setting of people are integrated, and the flexibility of recommendation is improved.
Further, after the pushing of the target electronic file according to the target recommendation list and the contact control configuration information, the method includes:
acquiring click data, wherein the click data comprises click user information, click time and a click electronic file;
and updating the recommendation model according to the click user information, the click time and the click electronic file.
According to the description, after the pushing is carried out, the recommendation model is optimized according to the actual click data of the user, the recommendation model can be automatically updated according to the change of the user behavior, the self-adaption of the recommendation model is realized, and the new model does not need to be retrained even if the user group behavior changes.
Further, the contact control configuration information comprises a pushing channel corresponding to the target electronic file, a pushing time period associated with the pushing channel, and a pushing frequency;
the pushing of the target electronic file according to the target recommendation list and the contact control configuration information comprises:
obtaining a recommended user corresponding to the target electronic file according to the target recommendation list;
and sending the target electronic file to the recommending user according to a pushing channel corresponding to the target electronic file, a pushing time period associated with the pushing channel and a pushing frequency.
According to the description, the push time periods and the push frequencies corresponding to the push channels and the push channels are configured, so that targeted push can be performed according to the habits of users in different push channels, and the accuracy of pushing the target electronic file is improved.
The electronic file recommendation method and the terminal of the invention are suitable for accurately pushing various electronic files, especially for pushing government electronic files, and are described below by a specific embodiment.
Referring to fig. 1-3, a first embodiment of the present invention is:
an electronic file recommendation method, comprising the steps of:
s1, office piece planning information and contact control configuration information are read, wherein the office piece planning information comprises user group information, a target electronic file, a second recommendation list and preset filtering conditions;
the contact control configuration information comprises a pushing channel corresponding to the target electronic file, a pushing time period relevant to the pushing channel and a pushing frequency;
s2, acquiring a recommendation model corresponding to the user group information, and acquiring a first recommendation list corresponding to the user group according to the recommendation model, wherein the recommendation model comprises the following steps:
s21, obtaining a recommendation label corresponding to each user in the user group information by the user group information through the recommendation model;
s22, associating the user and the recommendation label to obtain the first recommendation list;
s3, obtaining a fusion calculation result according to the first recommendation list and the office planning information, wherein the fusion calculation result comprises S301-S303:
s301, merging the same items in the first recommendation list and the second recommendation list;
the first recommendation list/the second recommendation list includes prediction groups (i.e. a recommendation label and its corresponding user) and a prediction accuracy label or a weight label corresponding to each prediction group, i.e. both the prediction accuracy label and the weight label or one of them may be included; combining the first recommendation list and the second recommendation list according to the weight label or the prediction accuracy label; that is, if the value of the weight label/prediction accuracy label of the first recommendation list is the same as that of the second recommendation list, only one result is saved;
s302, sorting the items in the first recommendation list and the second recommendation list according to preset keywords to obtain an initial recommendation list;
sorting prediction groups with the same recommendation labels in the combined first recommendation list and the combined second recommendation list according to weight or prediction accuracy, namely sorting according to one of the two prediction groups or weighting the two prediction groups, and sorting from good to bad according to the weighted value;
s303, filtering the items in the initial recommendation list according to the preset filtering condition to obtain a fusion calculation result;
selecting the first prediction group sorted in the step S302;
s4, obtaining a target recommendation list according to the fusion calculation result; the method comprises the following steps: obtaining a recommended user corresponding to the target electronic file according to the target recommendation list;
the target recommendation list corresponds to the prediction group in step S303;
in an alternative embodiment, the recommendation list includes a user ID (i.e. the user ID of the user in the prediction group), a user click number, a user stay time, a user click content ID, user portrait information, etc. (e.g. gender, age, academic history, income, whether the user should end up, etc.); the user portrait information takes different values according to different service scenes;
s5, pushing the target electronic file according to the target recommendation list and the contact control configuration information; sending the target electronic file to the recommending user according to a pushing channel corresponding to the target electronic file, a pushing time period associated with the pushing channel and a pushing frequency;
specifically, the matching degree (for example, a Pearson correlation coefficient R) between the user portrait and the electronic file portrait is calculated according to the user portrait in the target recommendation list, and if the matching degree exceeds a preset value, the electronic file corresponding to the electronic file portrait is recommended to the user corresponding to the user portrait;
s6, acquiring click data, wherein the click data comprises click user information, click time and a click electronic file; and updating the recommendation model according to the click user information, the click time and the click electronic file.
The second embodiment of the invention is as follows:
an electronic file recommendation method is different from the first embodiment in that:
providing a training process of a recommendation model:
before step S2, further comprising:
s01, selecting user behavior data of nearly 1 year, and initializing the user behavior data;
in an alternative embodiment, the current user behavior is also converted into training data to be included in the model, i.e. the data is dynamically changed, so the predicted result is also dynamically changed; the portrait of the user is also dynamically changed, if the user has room buying qualification when clicking for the first time and does not have room buying qualification when clicking for the second time, the portrait of the user is updated, and the model dynamically updates the prediction result according to the portrait result of the user;
the initialization includes: selecting relevant indexes of user behavior data, and customizing time periods such as weeks, months, years and the like;
predicting the user behavior of the current time period according to the user behavior data of the previous time period to obtain a predicted value;
in an alternative embodiment, different time periods are set according to different service characteristics;
reconstructing the user behavior data into training data adapted to the recommendation model, for example, reconstructing the recommendation model into training data in a [ sample, time step, feature ] format if the recommendation model is an LSTM model;
carrying out null value processing, data standardization and data normalization;
s02, splitting a training data set and a testing data set according to the proportion of 4:1, and training a recommendation model; specifically, a threshold value for correctly predicting the model is defined as that the output model is continuously iterated and optimized on the premise that the error does not exceed 10%; specifically, taking the model as an LSTM model as an example, parameters such as the number of hidden layers of the model, the number of nodes of the hidden layers, the learning rate, the time step, the number of iterations, and the like are iteratively adjusted and optimized.
Referring to fig. 3, a third embodiment of the present invention is:
an electronic file recommendation terminal 1 comprises a processor 2, a memory 3 and a computer program stored on the memory 3 and capable of running on the processor 2, wherein the processor 2 implements each step of the first embodiment or the second embodiment when executing the computer program.
In summary, the present invention provides an electronic file recommendation method and a terminal, which collect historical behavior data of a user, predict a current possible behavior of the user, and simultaneously mark a corresponding tag for the user, where the tag is matched with a tag of a target electronic file, so as to implement accurate matching between the user and the corresponding electronic file; meanwhile, the corresponding user click behaviors after the electronic file is pushed are collected, and the recommendation model is further modified according to the user click behaviors, so that the self-adaptive change of the recommendation model is realized.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to the related technical fields, are included in the scope of the present invention.
Claims (8)
1. An electronic file recommendation method, characterized by comprising the steps of:
reading office piece planning information and contact control configuration information, wherein the office piece planning information comprises user group information and a target electronic file;
acquiring a recommendation model corresponding to the user group information, and obtaining a first recommendation list corresponding to the user group according to the recommendation model;
obtaining a fusion calculation result according to the first recommendation list and the office planning information;
obtaining a target recommendation list according to the fusion calculation result;
pushing the target electronic file according to the target recommendation list and the contact control configuration information;
the office planning information comprises a second recommendation list and a preset filtering condition;
obtaining a fusion calculation result according to the first recommendation list and the office planning information, wherein the fusion calculation result comprises S301-S303:
s301, merging the same items in the first recommendation list and the second recommendation list; the first recommendation list/the second recommendation list comprises prediction groups and prediction accuracy labels or weight labels corresponding to the prediction groups; the prediction group is a recommendation label and a user corresponding to the recommendation label; merging the first recommendation list and the second recommendation list according to the weight label or the prediction accuracy label;
s302, sorting prediction groups with the same recommendation labels in the merged first recommendation list and the merged second recommendation list according to weight or prediction accuracy;
s303, selecting the first prediction group sequenced in the step S302 as a fusion calculation result.
2. The method of claim 1, wherein obtaining the first recommendation list corresponding to the user group according to the recommendation model comprises:
obtaining a recommendation label corresponding to each user in the user group information by the user group information through the recommendation model;
and associating the user and the recommendation label to obtain the first recommendation list.
3. The method of claim 1, wherein after the pushing the target electronic file according to the target recommendation list and the contact control configuration information, the method comprises:
acquiring click data, wherein the click data comprises click user information, click time and a click electronic file;
and updating the recommendation model according to the click user information, the click time and the click electronic file.
4. The method for recommending electronic files according to claim 1, wherein said contact control configuration information includes a push channel corresponding to said target electronic file, a push time period associated with said push channel, and a push frequency;
the pushing of the target electronic file according to the target recommendation list and the contact control configuration information comprises:
obtaining a recommended user corresponding to the target electronic file according to the target recommendation list;
and sending the target electronic file to the recommending user according to a pushing channel corresponding to the target electronic file, a pushing time period associated with the pushing channel and a pushing frequency.
5. An electronic document recommendation terminal comprising a memory, a processor and a computer program stored on said memory and operable on said processor, wherein said processor when executing said computer program implements the steps of:
reading office piece planning information and contact control configuration information, wherein the office piece planning information comprises user group information and a target electronic file;
acquiring a recommendation model corresponding to the user group information, and obtaining a first recommendation list corresponding to the user group according to the recommendation model;
obtaining a fusion calculation result according to the first recommendation list and the office planning information;
obtaining a target recommendation list according to the fusion calculation result;
pushing the target electronic file according to the target recommendation list and the contact control configuration information;
the office planning information comprises a second recommendation list and a preset filtering condition;
obtaining a fusion calculation result according to the first recommendation list and the office planning information, wherein the fusion calculation result comprises S301-S303:
s301, merging the same items in the first recommendation list and the second recommendation list; the first recommendation list/the second recommendation list comprises prediction groups and prediction accuracy labels or weight labels corresponding to the prediction groups; the prediction group is a recommendation label and a user corresponding to the recommendation label; merging the first recommendation list and the second recommendation list according to the weight label or the prediction accuracy label;
s302, sorting prediction groups with the same recommendation labels in the combined first recommendation list and the combined second recommendation list according to weight or prediction accuracy;
s303, selecting the first prediction group sequenced in the step S302 as a fusion calculation result.
6. The electronic file recommendation terminal of claim 5, wherein said obtaining a first recommendation list corresponding to the user group according to the recommendation model comprises:
obtaining a recommendation label corresponding to each user in the user group information by the user group information through the recommendation model;
and associating the user and the recommendation label to obtain the first recommendation list.
7. The electronic file recommendation terminal according to claim 5, wherein said pushing the target electronic file according to the target recommendation list and the contact control configuration information comprises:
acquiring click data, wherein the click data comprises click user information, click time and a click electronic file;
and updating the recommendation model according to the click user information, the click time and the click electronic file.
8. The electronic file recommendation terminal according to claim 5, wherein the contact control configuration information includes a push channel corresponding to the target electronic file, a push time period associated with the push channel, and a push frequency;
the pushing of the target electronic file according to the target recommendation list and the contact control configuration information comprises:
obtaining a recommended user corresponding to the target electronic file according to the target recommendation list;
and sending the target electronic file to the recommending user according to a pushing channel corresponding to the target electronic file, a pushing time period associated with the pushing channel and a pushing frequency.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211557102.4A CN115563397B (en) | 2022-12-06 | 2022-12-06 | Electronic file recommendation method and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211557102.4A CN115563397B (en) | 2022-12-06 | 2022-12-06 | Electronic file recommendation method and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115563397A CN115563397A (en) | 2023-01-03 |
| CN115563397B true CN115563397B (en) | 2023-03-21 |
Family
ID=84769819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211557102.4A Active CN115563397B (en) | 2022-12-06 | 2022-12-06 | Electronic file recommendation method and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115563397B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814034A (en) * | 2019-07-04 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Information processing method, information processing apparatus, storage medium, and electronic device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011530875A (en) * | 2008-08-05 | 2011-12-22 | メディアフレンズ，インク． | SMS technology for computerized equipment |
| CN102982042B (en) * | 2011-09-07 | 2015-08-19 | 中国移动通信集团公司 | A kind of personalization content recommendation method, platform and system |
| CN109064268A (en) * | 2018-07-20 | 2018-12-21 | 中国建设银行股份有限公司 | Business recommended method, apparatus, server-side and storage medium |
| CN111737558A (en) * | 2020-05-21 | 2020-10-02 | 苏宁金融科技(南京)有限公司 | Information recommendation method and device and computer readable storage medium |
| CN113792211A (en) * | 2021-08-18 | 2021-12-14 | 五八有限公司 | Resource pushing processing method and device, electronic equipment and storage medium |
-
2022
- 2022-12-06 CN CN202211557102.4A patent/CN115563397B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814034A (en) * | 2019-07-04 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Information processing method, information processing apparatus, storage medium, and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115563397A (en) | 2023-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107423442B (en) | Application recommendation method and system based on user portrait behavior analysis, storage medium and computer equipment | |
| CN111444428B (en) | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium | |
| US20210224326A1 (en) | Dressing recommendation method and dressing recommendation apparatus | |
| CN110188331A (en) | Model training method, conversational system evaluation method, device, equipment and storage medium | |
| CN111241992B (en) | Face recognition model construction method, recognition method, device, equipment and storage medium | |
| CN111523055B (en) | Collaborative recommendation method and system based on agricultural product characteristic attribute comment tendency | |
| CN107730286A (en) | A kind of target customer's screening technique and device | |
| CN111783873B (en) | User portrait method and device based on increment naive Bayes model | |
| CN112288554B (en) | Commodity recommendation method and device, storage medium and electronic device | |
| CN112149352B (en) | Prediction method for marketing activity clicking by combining GBDT automatic characteristic engineering | |
| CN111611488A (en) | Information recommendation method and device based on artificial intelligence and electronic equipment | |
| Shanthini et al. | A taxonomy on impact of label noise and feature noise using machine learning techniques | |
| CN114595323B (en) | Portrait construction, recommendation, model training method, apparatus, device and storage medium | |
| US11682039B2 (en) | Determining a target group based on product-specific affinity attributes and corresponding weights | |
| Di Mauro et al. | Grape: An expert review assignment component for scientific conference management systems | |
| Lee et al. | Effective evolutionary multilabel feature selection under a budget constraint | |
| CN118364176A (en) | Next interest point recommendation method based on double-comparison learning | |
| CN110807693A (en) | Album recommendation method, device, equipment and storage medium | |
| CN115563397B (en) | Electronic file recommendation method and terminal | |
| CN109474516B (en) | Method and system for recommending instant messaging connection strategy based on convolutional neural network | |
| CN112541010B (en) | User gender prediction method based on logistic regression | |
| CN113836388A (en) | Information recommendation method and device, server and storage medium | |
| CN111860870A (en) | Training method, device, equipment and medium for interactive behavior determination model | |
| Gregory et al. | MarkerMap: nonlinear marker selection for single-cell studies | |
| Benáček et al. | Postprocessing of Ensemble Weather Forecast Using Decision Tree–Based Probabilistic Forecasting Methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |