CN112287243B - Service information recommendation device and method based on collaborative filtering algorithm - Google Patents
Service information recommendation device and method based on collaborative filtering algorithm Download PDFInfo
- Publication number
- CN112287243B CN112287243B CN202011122955.6A CN202011122955A CN112287243B CN 112287243 B CN112287243 B CN 112287243B CN 202011122955 A CN202011122955 A CN 202011122955A CN 112287243 B CN112287243 B CN 112287243B
- Authority
- CN
- China
- Prior art keywords
- information
- personnel
- potential
- recommendation
- module
- 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
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention provides a service information recommendation device and method based on a collaborative filtering algorithm, which are used for acquiring a target data set, screening and positioning target people and determining potential people participating in different activities; recommending the activity information which can be interested in the potential crowd participating in different activities based on a collaborative filtering recommendation algorithm; extracting address information aiming at recommended activity information, and combining weather and traffic early warning information related to the address information to obtain travel plan suggestion information; according to the invention, different service information is accurately recommended to different people based on the collaborative filtering algorithm by identifying different crowd characteristics, so that the pertinence is stronger, and the user experience can be improved.
Description
Technical Field
The invention belongs to the technical field of information recommendation and computers, and particularly relates to a service information recommendation device and method based on a collaborative filtering algorithm.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
At present, a collaborative filtering recommendation method based on user behaviors is to find out users similar to a target user through data mining based on existing user behavior data, and then recommend the target user. However, according to the inventor, the information recommended based on the public recommendation algorithm is often not strong enough in pertinence, and the recommended content is not accurate and detailed enough; meanwhile, people of different ages and physical states have personal information on many service contents, such as weather states, but the current service information recommendation can not provide related information aiming at the differences, so that the user experience is poor.
Disclosure of Invention
In order to solve the problems, the invention provides a service information recommendation device and method based on a collaborative filtering algorithm.
According to some embodiments, the present invention employs the following technical solutions:
a method for service information recommendation based on collaborative filtering algorithm, comprising the following steps:
acquiring a target data set, screening and positioning target people, and determining potential people participating in different activities;
recommending the activity information which can be interested in the potential crowd participating in different activities based on a collaborative filtering recommendation algorithm;
and extracting address information aiming at the recommended activity information, and combining weather and traffic early warning information related to the address information to obtain travel plan suggestion information.
In an alternative embodiment, the specific process of screening and positioning the target crowd includes:
predicting the health level of all target people in the data set by using the GRU neural network, taking the prediction result as a health assessment label of the personnel, and screening the people according to the health assessment label;
analyzing a target data set by using a heterogeneous database, and establishing a personnel knowledge base participating in different activities;
and (3) establishing a Cox proportional risk model, screening dimension indexes, and preliminarily determining potential crowds interested in each activity by using K-means clustering.
As a further defined embodiment, the health level prediction is performed on the target crowd through the GRU neural network, the crowd with the health level less than the set value is removed, a personnel knowledge base participating in different activities is built for the rest crowd, then a Cox proportional risk model is built, dimension indexes including age and gender are screened out, and potential crowd participating in different activities is primarily determined by using K-means clustering.
As an alternative embodiment, for potential people participating in different activities, based on collaborative filtering recommendation algorithm, the specific process of recommending the activity information that may be interested in the potential people is as follows:
based on the screened dimension indexes, the dimension indexes are expressed in a matrix form, the similarity of the dimension indexes between the participated personnel and the potential crowd is calculated, the similarity between the participated personnel and the potential crowd is calculated by adopting the pearson correlation coefficient, the potential personnel with the similarity larger than a set value are selected, and the activities or similar activities which the potential personnel have participated in are selected for recommendation.
As an alternative implementation manner, the specific process of extracting the address information and combining the weather and traffic early warning information related to the address information to obtain the travel plan suggestion information is as follows:
when the activity recommendation is carried out, the position information of the recommended information person is obtained, if the position information of the recommended information person cannot be obtained, the position information of the recommended information person is determined according to the area where the recommended information person belongs to in the past, a data service interface opened by a weather bureau or a related website is called, the weather information of the current position and the weather information of the activity place are obtained, and weather forecast pushing and traffic service information pushing in the current day and a future period of time are carried out for corresponding personnel in advance.
An apparatus for service information recommendation based on collaborative filtering algorithm, comprising:
the system comprises a module for acquiring a target data set, screening and positioning target people, and determining potential people participating in different activities;
means for recommending activity information that may be of interest to potential people attending different activities based on collaborative filtering recommendation algorithms;
and the module is used for extracting address information aiming at the recommended activity information and combining weather and traffic early warning information related to the address information to obtain travel plan suggestion information.
As an alternative embodiment, the module for acquiring the target data set, screening and positioning the target crowd, and determining the potential crowd participating in different activities includes:
the data acquisition module is used for acquiring a target data set;
the health prediction module is used for predicting the body health level of related personnel in the target data set and constructing a health evaluation label through the GRU neural network;
the recommendation screening module is used for judging whether related personnel in the target data set participate in related activities or not;
and the data database building module is used for analyzing the target data set and building a personnel knowledge base which has participated in different activities by using the heterogeneous database.
A module for recommending activity information that may be of interest to a potential crowd attending different activities based on collaborative filtering recommendation algorithms, comprising:
the index representation module is configured to represent the dimension indexes in a matrix form based on the screened dimension indexes;
the similarity calculation module is configured to calculate the similarity of the dimension indexes between the attendees and the potential crowd, and calculate the similarity between the attendees and the potential crowd by adopting the pearson correlation coefficient;
and the selection recommending module is configured to select potential personnel with similarity larger than the set value and select activities or similar activities which the potential personnel have participated in to conduct recommendation.
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the steps of the method of collaborative filtering algorithm based service information recommendation.
A terminal device comprising a processor and a computer readable storage medium, the processor configured to implement instructions; the computer readable storage medium is for storing a plurality of instructions adapted to be loaded by a processor and to perform the steps of the one collaborative filtering algorithm based service information recommendation method.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, different crowd characteristics are identified through the collection application of the open data, different entertainment and study travel schemes are accurately recommended for different retired personnel based on the collaborative filtering algorithm, the pertinence is stronger, and the content is more accurate and detailed.
According to the invention, route planning including weather forecast and travel conditions of traffic can be provided in real time by using open traffic and meteorological data according to the recommended activity route, the age and physical conditions of different people are fully considered, the provided service is more comprehensive and finer, and the user experience can be improved more effectively.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a schematic view of the structure of the device according to the present embodiment;
fig. 2 is a flowchart of a recommendation method in this embodiment.
The specific embodiment is as follows:
the invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
In this embodiment, a retirement person is taken as a target person, and mental culture life service information is taken as a recommended information item. Of course, in other embodiments, different information may be recommended for other types of target personnel, such as movie information recommendation, meal recommendation, and the like.
Example 1
The invention provides a retirement personnel mental culture life service recommending device based on a collaborative filtering algorithm.
Referring to fig. 1, the retirement personnel mental culture life service recommending device based on the collaborative filtering algorithm of the present invention is composed of a business information base module 101, a data acquisition module 102, a health prediction module 103, a recommendation screening module 104, a data database building module 105, a crowd classification module 106, an activity recommending module 107, a travel service module 108 and a personal information base module 109.
A business information base module 101 for collecting retirement personnel information in a public dataset integrating each business department;
a data acquisition module 102 for acquiring a target data set;
a health prediction module 103 for predicting the physical health level of retirees in the target dataset, constructing health assessment tags through the GRU neural network;
a recommendation screening module 104, configured to determine whether the retired personnel in the target data set have travelled, participated in college of senior citizens to visit, and enjoy the museum;
a database creation module 105 for analyzing the target data set, creating a personnel knowledge base of the museum for use in a subsequent collaborative filtering algorithm, using the heterogeneous database, for travel, participation in college of senior citizens, visit of the cultural museum, and appreciation;
the crowd classification module 106 is used for determining potential crowds of four activities of travel, college learning, visiting a cultural house and enjoying a museum, and screening out service objects by using K-means clustering;
an activity recommendation module 107 for recommending activities to potential people based on knowledge base data sets of four activity retirers participating in travel, college learning, visiting a cultural museum, enjoying a museum, and based on collaborative filtering algorithms of users;
the trip service module 108 is used for recommending specific trip route services to the service object, including weather forecast and traffic forecast.
A personal information base module 109 for storing the recommended activities for the retirees for timely recommending the mental cultural life services for the retirees.
Example 2
The invention provides a retirement personnel mental culture life service recommending method based on a collaborative filtering algorithm.
Referring to fig. 2, the method for recommending the mental culture life service of the retirement personnel based on the collaborative filtering algorithm comprises the following specific steps:
In the step, health level prediction can be performed on target people through the GRU neural network, people with unqualified health level, namely people with serious diseases or inconvenient travel, are removed, recommendation services are not provided for the people, a personnel knowledge base participating in different activities is built for the rest of people, then a Cox proportional risk model is built, whether indexes such as age, sex and the like have influence on the participating activities is screened out, relevant dimension indexes are removed after the relevant dimension indexes are screened out, K-means clustering is used according to the rest of dimension indexes, and potential people participating in different activities are primarily determined.
In this embodiment, based on the selected dimension indexes such as business data information (personnel basic information, personnel treatment information, medical settlement data, medical institution information, disease information), open data information (university of elderly, museum information of cultural museum, etc.), the dimension indexes are represented in a matrix form, the similarity of the dimension indexes between the attendees and the potential crowd is calculated, the similarity between the attendees and the potential crowd is calculated by pearson correlation coefficient, and the value interval of the result is [ -1,1]. -1 represents a complete negative correlation, 1 represents a complete positive correlation, 0 represents no linear correlation, the person with the highest similarity, i.e. closest to 1, is selected, the activity he has participated in is selected, and recommended to the potential person, thus completing the recommendation of activity information.
In step 208, the similarity between the person knowledge base established by the database establishment module 105 and the four retired persons classified by the person classification module 106 is calculated, and collaborative filtering recommendation is performed on the four potential persons through the activity recommendation module 107, namely, activity recommendation is performed.
When the personnel are recommended to the activities, the position information of the current personnel can be acquired, if the position information cannot be acquired, an open data service interface of a weather bureau or a related website is called according to the area where the personnel are located when the personnel are retired, the weather information of the current position and the weather information of the activities are acquired, the weather forecast pushing of the current day and the 3 days in the future is carried out on the personnel in advance, the traffic early warning is also called by the traffic bureau or the open traffic service information interface of the related website, and the traffic early warning information of the current day and the 3 days in the future is acquired and pushed to the personnel.
Of course, based on the health condition of the personnel, the personnel who are not suitable for traveling under bad health condition directly exit the recommendation, travel plans or service information suggestions are given by combining the health information of the personnel, the personnel who are not particularly good under the health condition are given the activity recommendation at proper time, such as recommending the activities with less flow of the personnel as much as possible and not violent activity, and the situation of better weather condition is selected, so that cold is avoided to catch a cold.
Example 3
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the steps of the method presented in embodiment 2.
A terminal device comprising a processor and a computer readable storage medium, the processor configured to implement instructions; the computer readable storage medium is for storing a plurality of instructions adapted to be loaded by a processor and to perform the steps of the method presented in embodiment 2.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (5)
1. A service information recommendation method based on collaborative filtering algorithm is characterized in that: the method comprises the following steps:
acquiring a target data set, screening and positioning target people, and determining potential people participating in different activities;
recommending the activity information which can be interested in the potential crowd participating in different activities based on a collaborative filtering recommendation algorithm;
extracting address information aiming at recommended activity information, and combining weather and traffic early warning information related to the address information to obtain travel plan suggestion information;
the specific process for screening and positioning the target crowd comprises the following steps:
predicting the health level of all target people in the data set by using the GRU neural network, removing people with the health level not reaching the standard, taking the prediction result as a health evaluation label of the people, screening the people according to the health evaluation label, and not providing recommended service for people with serious diseases or inconvenient travel;
using a heterogeneous database to analyze a target data set and establishing a personnel knowledge base participating in different activities for people with health level reaching standards;
establishing a Cox proportion risk model, screening out dimension indexes including age and gender, and preliminarily determining potential crowds interested in each activity by using K-means clustering;
the specific process of recommending the activity information which is possibly interested in the potential crowd participating in different activities based on the collaborative filtering recommendation algorithm is as follows:
based on the screened dimension indexes, the dimension indexes are expressed in a matrix form, the similarity of the dimension indexes between the participated personnel and the potential crowd is calculated, the similarity between the participated personnel and the potential crowd is calculated by adopting pearson correlation coefficients, the value interval of the result is [ -1,1], -1 represents complete negative correlation, 1 represents complete positive correlation, 0 represents no linear correlation, the personnel with the highest similarity, namely the closest similarity to 1, is selected, and the activities or similar activities which the participated personnel have participated in are selected for recommendation.
2. The method for recommending service information based on collaborative filtering algorithm according to claim 1, wherein: extracting address information, and combining weather and traffic early warning information related to the address information to obtain specific process of travel plan suggestion information:
when the activity recommendation is carried out, the position information of the recommended information person is obtained, if the position information of the recommended information person cannot be obtained, the position information of the recommended information person is determined according to the area where the recommended information person belongs to in the past, a data service interface opened by a weather bureau or a related website is called, the weather information of the current position and the weather information of the activity place are obtained, and weather forecast pushing and traffic service information pushing in the current day and a future period of time are carried out for corresponding personnel in advance.
3. A service information recommending device based on collaborative filtering algorithm is characterized in that: comprising the following steps:
the system comprises a module for acquiring a target data set, screening and positioning target people, and determining potential people participating in different activities;
means for recommending activity information that may be of interest to potential people attending different activities based on collaborative filtering recommendation algorithms;
the module is used for extracting address information aiming at recommended activity information and combining weather and traffic early warning information related to the address information to obtain travel plan suggestion information;
the module for acquiring the target data set, screening and positioning the target crowd, and determining the potential crowd participating in different activities comprises:
the data acquisition module is used for acquiring a target data set;
the health prediction module is used for predicting the body health level of related personnel in the target data set, constructing a health evaluation label through the GRU neural network, removing personnel with the health level not reaching the standard, screening the crowd according to the health evaluation label, namely, the personnel with serious diseases or inconvenient travel, and not providing recommended service for the personnel;
the recommendation screening module is used for judging whether concentrated related personnel with the standard health level in the target data participate in related activities or not;
the data base building module is used for analyzing the target data set and building a personnel knowledge base which takes part in different activities for the crowd with the health level reaching the standard by using the heterogeneous database;
the crowd classification module: establishing a Cox proportion risk model, screening out dimension indexes including age and gender, and preliminarily determining potential crowds interested in each activity by using K-means clustering;
the module for recommending the activity information which can be interested in the potential crowd participating in different activities based on the collaborative filtering recommendation algorithm comprises the following steps:
the index representation module is configured to represent the dimension indexes in a matrix form based on the screened dimension indexes;
the similarity calculation module is configured to calculate the similarity of the dimension indexes between the attendees and the potential crowd, and calculate the similarity between the attendees and the potential crowd by adopting the pearson correlation coefficient;
and the selection recommending module is configured to select potential personnel with similarity larger than the set value and select activities or similar activities which the potential personnel have participated in to conduct recommendation.
4. A computer-readable storage medium, characterized by: in which a plurality of instructions are stored, which instructions are adapted to be loaded by a processor of a terminal device and to carry out the steps of a method of collaborative filtering algorithm based service information recommendation according to any of claims 1-2.
5. A terminal device, characterized by: comprising a processor and a computer-readable storage medium, the processor configured to implement instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and to perform the steps of a collaborative filtering algorithm based service information recommendation method according to any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011122955.6A CN112287243B (en) | 2020-10-20 | 2020-10-20 | Service information recommendation device and method based on collaborative filtering algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011122955.6A CN112287243B (en) | 2020-10-20 | 2020-10-20 | Service information recommendation device and method based on collaborative filtering algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112287243A CN112287243A (en) | 2021-01-29 |
| CN112287243B true CN112287243B (en) | 2023-04-28 |
Family
ID=74423125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011122955.6A Active CN112287243B (en) | 2020-10-20 | 2020-10-20 | Service information recommendation device and method based on collaborative filtering algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112287243B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779946A (en) * | 2016-12-16 | 2017-05-31 | Tcl集团股份有限公司 | A kind of film recommends method and device |
| CN108052639A (en) * | 2017-12-21 | 2018-05-18 | 中国联合网络通信集团有限公司 | Industry user based on carrier data recommends method and device |
| CN108062366A (en) * | 2017-12-07 | 2018-05-22 | 中国科学院自动化研究所 | Public culture information recommendation system |
| CN110110237A (en) * | 2017-12-19 | 2019-08-09 | 福建天泉教育科技有限公司 | User interest information recommended method, storage medium |
| CN110135893A (en) * | 2019-04-16 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Determination method, apparatus, computer equipment and the storage medium of potential user |
| CN110543603A (en) * | 2019-09-06 | 2019-12-06 | 上海喜马拉雅科技有限公司 | Collaborative filtering recommendation method, device, equipment and medium based on user behaviors |
| CN111767469A (en) * | 2020-06-17 | 2020-10-13 | 中国建设银行股份有限公司 | Endowment service recommendation method and device |
-
2020
- 2020-10-20 CN CN202011122955.6A patent/CN112287243B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779946A (en) * | 2016-12-16 | 2017-05-31 | Tcl集团股份有限公司 | A kind of film recommends method and device |
| CN108062366A (en) * | 2017-12-07 | 2018-05-22 | 中国科学院自动化研究所 | Public culture information recommendation system |
| CN110110237A (en) * | 2017-12-19 | 2019-08-09 | 福建天泉教育科技有限公司 | User interest information recommended method, storage medium |
| CN108052639A (en) * | 2017-12-21 | 2018-05-18 | 中国联合网络通信集团有限公司 | Industry user based on carrier data recommends method and device |
| CN110135893A (en) * | 2019-04-16 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Determination method, apparatus, computer equipment and the storage medium of potential user |
| CN110543603A (en) * | 2019-09-06 | 2019-12-06 | 上海喜马拉雅科技有限公司 | Collaborative filtering recommendation method, device, equipment and medium based on user behaviors |
| CN111767469A (en) * | 2020-06-17 | 2020-10-13 | 中国建设银行股份有限公司 | Endowment service recommendation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112287243A (en) | 2021-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113010572B (en) | Public digital life scene rule model prediction early warning method based on deep Bayesian network | |
| Polyakova et al. | Managerial decision support algorithm based on network analysis and big data | |
| Xiao et al. | Detecting travel modes from smartphone-based travel surveys with continuous hidden Markov models | |
| Adejoro | Does location also matter?: a spatial analysis of social achievements of young South Australians | |
| Khatibi et al. | Fine-grained tourism prediction: Impact of social and environmental features | |
| Gutiérrez-Posada et al. | Heterogeneity in the determinants of population growth at the local level: Analysis of the Spanish case with a GWR approach | |
| Hafezi et al. | Daily activity and travel sequences of students, faculty and staff at a large Canadian university | |
| Howard | Race, neighborhood, and drug court graduation | |
| Nadikattu | Fundamental applications of machine learning across the globe | |
| Pryss et al. | Machine learning findings on geospatial data of users from the trackyourstress mhealth crowdsensing platform | |
| Mikhailov et al. | Tourist behaviour analysis based on digital pattern of life—an approach and case study | |
| Bratanova et al. | Differentiating artificial intelligence activity clusters in Australia | |
| Kubiszewski et al. | Subjective wellbeing at different spatial scales for individuals satisfied and dissatisfied with life | |
| Vildjiounaite et al. | Unobtrusive assessment of stress of office workers via analysis of their motion trajectories | |
| Papadimitriou et al. | Needs and priorities of road safety stakeholders for evidence-based policy making | |
| CN112287243B (en) | Service information recommendation device and method based on collaborative filtering algorithm | |
| Tekieh et al. | Analysing healthcare coverage with data mining techniques | |
| Huang et al. | Detecting neighborhood gentrification at scale via street-level visual data | |
| Kiselev et al. | Predicting verbal reasoning from virtual community membership in a sample of Russian young adults | |
| Carlson et al. | Unique views on obesity-related behaviors and environments: research using still and video images | |
| Daepp | Small-area moving ratios and the spatial connectivity of neighborhoods: Insights from consumer credit data | |
| Breetzke et al. | The Mongrel Mob or Head Hunters? The association between neighbourhood-level factors on different types of gang membership in Aotearoa/New Zealand | |
| CN112685654B (en) | Student identification method and device, computing equipment and readable computer storage medium | |
| Namaki Araghi | A methodology for business process discovery and diagnosis based on indoor location data: Application to patient pathways improvement | |
| Oatley et al. | Changing faces: identifying complex behavioural profiles |
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 |