CN109919437B - big data-based intelligent tourism target matching method and system - Google Patents
big data-based intelligent tourism target matching method and system Download PDFInfo
- Publication number
- CN109919437B CN109919437B CN201910087016.3A CN201910087016A CN109919437B CN 109919437 B CN109919437 B CN 109919437B CN 201910087016 A CN201910087016 A CN 201910087016A CN 109919437 B CN109919437 B CN 109919437B
- Authority
- CN
- China
- Prior art keywords
- user
- tourism
- target user
- data
- travel
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides intelligent tourism target matching methods and systems based on big data, the method comprises the steps of constructing a tourism information big data system through existing tourism data to obtain a tourism standard feature library, acquiring historical tourism data of a target user to obtain tourism information of the target user, extracting the tourism information of the target user to obtain a tourism multidimensional feature of the target user, comparing the tourism multidimensional feature of the target user with the tourism standard feature library to classify the target user to obtain a target user portrait, comparing the target user portrait with the existing data of the target user to obtain a tourism matching result of the target user, comparing by means of cosine similarity, sorting the tourism matching result of the target user and returning the result.
Description
Technical Field
The application relates to the field of big data and intelligent tourism, in particular to intelligent tourism target matching methods and systems based on big data.
Background
In the traditional smart travel target matching process, is matched only through a single dimension characteristic of a tourist, and the relevance of multidimensional travel characteristics such as the personal characteristic of the tourist, a social circle, a trip, a lodging and the like is not considered, the integrity of the whole travel process of the tourist is cut, the matching accuracy is low, and the data utilization efficiency is low.
Disclosure of Invention
In view of this, the present application aims to provide methods and systems for matching smart tourism targets based on big data, so as to improve the utilization efficiency of tourism data and solve the technical problem of low target matching accuracy in the current smart tourism time process.
Based on the above purpose, the present application proposes kinds of smart travel target matching methods based on big data, including:
constructing a tourism information big data system through the existing tourism data to obtain a tourism standard feature library; the big data system adopts a Lambda architecture;
collecting historical tourism data of a target user to obtain tourism information of the target user, and extracting the tourism information of the target user to obtain tourism multidimensional characteristics of the target user;
comparing the target user tourism multi-dimensional characteristics with the tourism standard characteristic library, and classifying the target users to obtain a target user portrait;
comparing the target user portrait with the existing data of the target user to obtain a target user tourism matching result; the comparison is carried out by adopting cosine similarity;
and sequencing the travel matching results of the target users and returning the results.
In embodiments, the big data system includes:
the batch processing layer is responsible for processing the offline data, comparing, classifying and recommending the offline data, and processing the offline data by adopting a Hadoop or Spark architecture;
the real-time processing layer is responsible for processing real-time data and generating real-time recommendation information, and or more architectures in flash, zoom eeper, Kafaka and spark streaming are adopted for processing;
and the service layer is used for realizing interaction with the user and visually displaying the recommendation information to the user.
In , the target user travel characteristics include a user basic characteristic, a user social characteristic, a user route characteristic, a user travel characteristic, a user hotel characteristic, and a network access characteristic;
the user basic characteristics comprise age, gender, position, occupation, ethnicity and belief;
the social characteristics of the user comprise participation organization, friend circle, peer frequency and interaction frequency;
the user travel characteristics comprise a traffic mode, travel mileage, travel time and route characteristics;
the user hotel characteristics include order time, consumption level, geographic location;
the network access characteristics comprise internet access time, access content, internet access mode and network speech.
In , comparing the travel multidimensional feature of the target user with the travel standard feature library, and solving a formula:
implementation of, wherein tiA representation of the target user is provided,
is the feature vector of the target user, G is a travel standard feature library, tjFor the jth user in G,
is the feature vector of the jth user,
the cosine similarity between the target user characteristic and the travel standard characteristic library.
In , the comparing the target user representation with the target user current data to obtain the target user travel matching result includes:
the target user travel information forms a set stThe tourism standard feature library forms a plurality of sets S ═ S1，s2…snWill set stPerforming intersection operation with all the sets in the S to obtain a matching preselection set Sp＝{s1∩st，s2∩st…sn∩stAnd removing the duplication of the elements in each set in the matching preselection set, and classifying according to different characteristics to obtain a user travel matching result.
In , the ranking includes at least of a matchmaker match ranking, a route match ranking, a ticket match ranking, and a hotel match ranking.
Based on above-mentioned purpose, this application has also proposed kinds of wisdom tourism target matching systems based on big data, its characterized in that includes:
the construction module is used for constructing a tourism information big data system through the existing tourism data to obtain a tourism standard feature library;
the characteristic extraction module is used for acquiring historical tourism data of a target user to obtain tourism information of the target user and extracting the tourism information of the target user to obtain tourism multidimensional characteristics of the target user;
the user portrait module is used for comparing the target user tourism multi-dimensional characteristics with the tourism standard characteristic library, classifying the target users and obtaining a target user portrait;
the user matching module is used for comparing the target user portrait with the existing data of the target user to obtain a target user tourism matching result;
and the matching return module is used for sequencing the tour matching results of the target users and returning the results.
In , the building module includes:
the tourism data cleaning unit is used for performing the grouping processing on the tourism data, removing noise and converting the data into standard data;
and the tourism data storage unit is used for storing mass user tourism data in a big data storage mode.
In , the feature extraction module includes:
the user basic feature extraction unit is used for extracting the age, the gender, the position, the occupation, the ethnicity and the belief of the user;
the user social characteristic extraction unit is used for extracting the participation organization, the friend circle, the peer frequency and the interaction frequency of the user;
the user travel characteristic extraction unit is used for extracting the traffic mode, travel mileage, travel time and route characteristics of the user;
the hotel characteristic extraction unit of the user is used for extracting the ordering time, the consumption level and the geographic position of the user;
and the network access characteristic extraction unit is used for extracting the internet access time, the access content, the internet access mode and the network speech of the user.
In , the big data based intelligent travel target matching system further comprises:
the task scheduling module is used for controlling the distribution and resource allocation of the tourism target matching tasks;
and the efficiency monitoring module is used for monitoring the execution efficiency of the matched tasks of the tourism targets and sending the monitoring result to the task scheduling module.
Drawings
In the drawings, like numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified, and in which not are drawn to scale, it should be understood that these drawings depict only embodiments of in accordance with the present disclosure and are not to be considered limiting of the scope of the disclosure.
FIG. 1 is a flow chart illustrating a big data based smart travel object matching method according to an embodiment of the present invention.
FIG. 2 is a block diagram of a big data based intelligent travel target matching system according to an embodiment of the present invention.
Fig. 3 shows a building block composition diagram according to an embodiment of the present invention.
Fig. 4 shows a feature extraction module configuration diagram according to an embodiment of the present invention.
FIG. 5 illustrates a block diagram of a big data based smart travel target matching system, according to an embodiment of the present invention.
Detailed Description
The present application is described in further detail in with reference to the drawings and the examples, it being understood that the specific examples are set forth herein for the purpose of illustration and not as a definition of the limits of the invention.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
FIG. 1 is a flowchart of a big data-based smart travel target matching method according to an embodiment of the present invention, as shown in FIG. 1, the big data-based smart travel target matching method includes:
s11, constructing a tourism information big data system through the existing tourism data to obtain a tourism standard feature library;
in , the big data system of travel information adopts Lambda architecture, comprising:
the batch processing layer is responsible for processing the offline data, comparing, classifying and recommending the offline data, and processing the offline data by adopting a Hadoop or Spark architecture;
the real-time processing layer is responsible for processing real-time data and generating real-time recommendation information, and or more architectures in Flume, ZooKeeper, Kafaka and spark streaming are adopted for processing;
and the service layer is used for realizing interaction with the user and visually displaying the recommendation information to the user.
The Lambda framework integrates offline calculation and real-time calculation, integrates series framework principles such as invariability, read-write separation, complexity isolation and the like, can integrate various big data components such as Hadoop, Kafka, Storm, Spark, Hbase and the like, and is suitable for being applied to various data types such as smart tourism, which relate to social circles, travel modes, lodging habits, geographic information and the like, and simultaneously needs to meet the practical requirements of high user timeliness requirements, fast service change and the like.
In embodiments, the travel standard feature library is a data mining means such as clustering and social network analysis on data of multiple dimensions such as travel modes, travel experiences, lodging preferences, social interactions of donkey friends, consumption modes and the like based on existing various user travel data to obtain different typical user features, and a travel standard feature library is formed.
S12, collecting historical tourism data of the target user to obtain tourism information of the target user, and extracting to obtain tourism multidimensional characteristics of the target user;
in embodiments, the multidimensional feature of travel of the target user refers to information of users who need to be matched and are exposed to the internet and the real society, and the information is embodied in multiple dimensions such as geography, social intercourse, lodging, travel and the like, so that travel data of the target user in multiple dimensions needs to be mastered to form the multidimensional feature of donkey friends of the target user.
In , the target user travel characteristics comprise a user basic characteristic, a user social characteristic, a user route characteristic, a user travel characteristic, a user hotel characteristic and a network access characteristic;
the user basic characteristics include age, gender, location, occupation, ethnicity, and belief, and these data are typically from the user's registration information;
the social characteristics of the users comprise participation organization, friend circle, peer frequency and interaction frequency, and the data can be obtained by extracting information such as user network access records, interaction records and the like;
the user travel characteristics comprise traffic modes, travel mileage, travel time and route characteristics, and the data can be obtained by statistical mining of user historical order data;
the hotel characteristics of the user comprise ordering time, consumption level and geographical position, and the data can also be obtained through later statistical analysis according to historical order data of the user;
the network access characteristics comprise internet access time, access content, internet access modes and network speech, and the data are obtained through machine learning and data mining through the historical records of the user in the internet.
Step S13, comparing the tourism multidimensional characteristics of the target user with the tourism standard characteristic library, and classifying the target user to obtain a target user portrait;
in embodiments, by comparing the target multidimensional feature obtained in step S12 with the travel standard feature library obtained in step S11, a user group type similar to the target user can be obtained, and thus, the matching work of the user can be continued.
In , comparing the travel multidimensional feature of the target user with the travel standard feature library, and solving a formula:
implementation of, wherein tiA representation of the target user is provided,
is the feature vector of the target user, G is a travel standard feature library, tjFor the jth user in G,
is the feature vector of the jth user,
the cosine similarity between the target user characteristic and the travel standard characteristic library.
In embodiments, since the smart tourism object matching process is faced with massive big data and is built in the Lambda framework, the similarity calculation process can utilize the characteristics of the Lambda framework to perform distributed multi-task parallel calculation, thereby improving the similarity calculation efficiency.
In embodiments, since the target data is continuously obtained from the internet, Spark Streaming may be considered to process each block of data as RDDs (flexible distributed data sets) and process each small blocks of data using RDD operations, each block generates Spark Job processes, and the end result returns multiple blocks of data.
Step S14, comparing the target user portrait with the existing data of the target user to obtain a target user tourism matching result;
in embodiments, the target user travel information constitutes a set stThe tourism standard feature library forms a plurality of sets S ═ S1，s2…snWill set stPerforming intersection operation with all the sets in the S to obtain a matching preselection set Sp＝{s1∩st，s2∩st…sn∩stAnd removing the duplication of the elements in each set in the matching preselection set, and classifying according to different characteristics to obtain a user travel matching result.
Specifically, intersection operation is performed on the travel information of the target user and the standard feature library obtained in the step S11, so that a field that the target user does not relate to in the target type of the target user can be obtained, and therefore matching of the target is achieved.
And step S15, sequencing the travel matching results of the target users and returning the results.
In , the ranking process includes at least of a donglet match ranking, a route match ranking, a ticket match ranking, and a hotel match ranking.
In embodiments, the matching ranking of the donkey friends relates to the field of social network analysis, and social network analysis maps can be constructed through social network data such as closeness and communication frequency between donkey friends, and by means of a formula:
wherein, wiWeighted value f for social dimension of i-th donkey friends(j)Is the degree of social dimension relation with the user j. After weighted summation, the relation degree of each user is obtained, and the weighted scores are sorted, so that matching sorting of the donkey friends can be realized.
In , the route matching sequence relates to geographic information system sequence, which needs to be comprehensively considered for sequence by considering various information such as historical route, geographic coordinate, altitude, shortest route, route cost, etc.
In embodiments, the ticket matching ranking and the hotel matching ranking can be ranked and matched by a quick ranking algorithm, a merge ranking algorithm, or a hill ranking algorithm as they are faced with formatted historical order data.
FIG. 2 is a block diagram of a big data based intelligent travel target matching system according to an embodiment of the present invention. As shown in FIG. 2, the overall system for matching intelligent travel targets based on big data can be divided into:
the construction module 21 is used for constructing a tourism information big data system through the existing tourism data to obtain a tourism standard feature library;
the characteristic extraction module 22 is used for acquiring historical travel data of the target user to obtain travel information of the target user, and extracting the travel information of the target user to obtain travel multidimensional characteristics of the target user;
the user portrait module 23 is used for comparing the target user tourism multidimensional characteristics with the tourism standard characteristic library, classifying the target users and obtaining a target user portrait;
the user matching module 24 is used for comparing the target user portrait with the existing data of the target user to obtain a target user tourism matching result;
and the matching returning module 25 is used for sequencing the travel matching results of the target users and returning the results.
Fig. 3 shows a constitutional diagram of a building block according to an embodiment of the present invention. As shown in fig. 3, the building blocks can be divided into:
the tourism data cleaning unit is used for performing the grouping processing on the tourism data, removing noise and converting the tourism data into standard data;
for example, the information from the website A shows that the user goes to Tokyo, the information from the website B shows that the user goes to Tokyo, and the information from the website C shows that the user goes to imperial Beijing (とうきょう), wherein the three are actually about Tokyo and about , so that the tourism data from different paths need to be named differently and refer to the same information to be subjected to .
In embodiments, the noise removal can be performed by regression analysis, missing value cleaning, outlier analysis, and the like.
And the tourism data storage unit is used for storing mass user tourism data in a big data storage mode.
In embodiments, because the system has a Lambda architecture, the data of each type of travel is different in characteristics, so all the data entering the system is distributed to a batch layer and a rapid processing layer, the batch layer has two functions of managing the master data and preprocessing the data converted into batch views, the service layer is used for loading and implementing the batch views in the database, so that the user can inquire about the rapid processing layer for processing new data and high delay compensation caused by the update of the service layer, and any matching result can be obtained by combining the results of the batch views and the real-time views.
Fig. 4 shows a configuration diagram of a feature extraction module according to an embodiment of the present invention. As shown in fig. 4, the feature extraction module can be divided into:
the user basic feature extracting unit 221 is configured to extract age, gender, location, occupation, ethnicity, and belief of the user, the user basic data is derived from formatted standard data provided during user registration, and is a description of basic feature attributes of the user.
The user social characteristic extraction unit 222 is configured to extract user participation organization, friend group, peer frequency, and interaction frequency, the user social data is generally derived from group information, interaction information, speech information, and the like of the user exposed to the internet, and needs to be extracted by a social network extraction method.
The user travel characteristic extraction unit 223 is used for extracting user traffic mode, travel mileage, travel time and route characteristics, the user travel characteristic data are from formatted standard order data of a user on the internet or travel note data written by the user, the formatted data are easy to extract, the unformatted data need named entity recognition on a text, key travel nouns are extracted, and the user travel characteristic data are extracted.
The hotel characteristics extraction unit 224 is used for extracting the ordering time, the consumption level and the geographical position of the user, the hotel characteristics data of the user are also generally from formatted standard order data of the user on the Internet and also can be from description data of the user.
A network access feature extraction unit 225, configured to extract a user internet access time, access content, internet access mode, and network speech. The network access characteristic data is used as data exposed by the user on the internet and is obtained in a data mining mode of user log analysis.
FIG. 5 is a block diagram of a big data based intelligent travel target matching system, according to an embodiment of the present invention. As shown in fig. 5, the big data based intelligent travel target matching system further includes:
the task scheduling module 26 is used for controlling the distribution and resource allocation of the travel target matching tasks;
and the efficiency monitoring module 27 is used for monitoring the execution efficiency of the matched tasks of the tourism targets and sending a monitoring result to the task scheduling module.
In the description herein, reference to the terms " embodiments," " embodiments," "examples," "specific examples," or " examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least embodiments or examples of the invention.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include or more executable instructions for implementing specific logical functions or steps in the process, and the scope of the preferred embodiments of the present invention includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
For the purposes of this description, a "computer-readable medium" can be any medium that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device (e.g., a computer-based system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions).
For example, if implemented in hardware, and in another embodiment , it may be implemented using any item or combination thereof known in the art, a discrete logic circuit having logic circuits for implementing logic functions on data signals, an application specific integrated circuit having appropriate combinational logic circuits, a programmable array (PGA), a field programmable array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware associated with instructions of a program, which may be stored in computer readable storage media, and when executed, the program includes or a combination of the steps of the method embodiments.
In addition, each functional unit in each embodiment of the present invention may be integrated into processing modules, or each unit may exist alone physically, or two or more units are integrated into modules.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various changes or substitutions within the technical scope of the present invention, and these should be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (4)
1, kinds of big data-based intelligent tourism object matching method, characterized by comprising:
constructing a tourism information big data system through the existing tourism data to obtain a tourism standard feature library; the big data system adopts a Lam bda architecture;
collecting historical tourism data of a target user to obtain tourism information of the target user, and extracting the tourism information of the target user to obtain tourism multidimensional characteristics of the target user;
comparing the target user tourism multi-dimensional characteristics with the tourism standard characteristic library, and classifying the target users to obtain a target user portrait;
comparing the target user portrait with the existing data of the target user to obtain a target user tourism matching result; comparing the target user portrait with the existing data of the target user by adopting cosine similarity;
sequencing the travel matching results of the target users and returning the results; wherein the content of the first and second substances,
comparing the target user tourism multidimensional characteristics with the tourism standard characteristic library, and solving a formula:
implementation of, wherein tiA representation of the target user is provided,
is the feature vector of the target user, G is a travel standard feature library, tjFor the jth user in G,
is the feature vector of the jth user,the cosine similarity between the target user characteristic and the travel standard characteristic library is obtained;
the step of comparing the target user portrait with the existing data of the target user to obtain a target user tourism matching result comprises the following steps: the target user travel information forms a set stThe tourism standard feature library forms a plurality of sets S ═ S1，s2…snWill set stPerforming intersection operation with all the sets in the S to obtain a matching preselection set Sp＝{s1∩st，s2∩st…sn∩stAnd removing the duplication of the elements in each set in the matching preselection set, and classifying according to different characteristics to obtain a user travel matching result.
2. The method of claim 1, wherein the big data system comprises:
the batch processing layer is responsible for processing the offline data, comparing, classifying and recommending the offline data, and processing the offline data by adopting a Hadoop or Spark architecture;
the real-time processing layer is responsible for processing real-time data and generating real-time recommendation information, and or more architectures in flash, zoom eeper, Kafaka and Spark Streaming are adopted for processing;
and the service layer is used for realizing interaction with the user and visually displaying the recommendation information to the user.
3. The method of claim 1, wherein the target user travel multi-dimensional features comprise a user base feature, a user social feature, a user route feature, a user travel feature, a user hotel feature, a network access feature;
the user basic characteristics comprise age, gender, position, occupation, ethnicity and belief;
the social characteristics of the user comprise participation organization, friend circle, peer frequency and interaction frequency;
the user travel characteristics comprise a traffic mode, travel mileage, travel time and route characteristics;
the user hotel characteristics include order time, consumption level, geographic location;
the network access characteristics comprise internet access time, access content, internet access mode and network speech.
4. The method of claim 1,
the sorting comprises at least sorts of matching sorting of donkey friends, line matching sorting, air ticket matching sorting and hotel matching sorting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910087016.3A CN109919437B (en) | 2019-01-29 | 2019-01-29 | big data-based intelligent tourism target matching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910087016.3A CN109919437B (en) | 2019-01-29 | 2019-01-29 | big data-based intelligent tourism target matching method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109919437A CN109919437A (en) | 2019-06-21 |
| CN109919437B true CN109919437B (en) | 2020-01-31 |
Family
ID=66961055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910087016.3A Active CN109919437B (en) | 2019-01-29 | 2019-01-29 | big data-based intelligent tourism target matching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109919437B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110444133A (en) * | 2019-08-13 | 2019-11-12 | 上饶市中科院云计算中心大数据研究院 | A kind of method and apparatus of tourist attraction intelligent guide |
| CN110827124B (en) * | 2019-11-05 | 2021-12-10 | 上海景域文化传播股份有限公司 | Method for realizing tourism-first and payment-later product, composition system and electronic equipment |
| CN111445308A (en) * | 2020-03-26 | 2020-07-24 | 四川旅游学院 | Tourist attraction recommendation method based on user portrait |
| CN113946748A (en) * | 2020-10-13 | 2022-01-18 | 王琰 | Big data-based intelligent tourism target matching system |
| CN112989184A (en) * | 2021-02-20 | 2021-06-18 | 广州城建职业学院 | Personalized travel service big data application system and method |
| CN113779418B (en) * | 2021-11-12 | 2022-03-11 | 杭州明融科技有限公司 | Tourism message subscription push system |
| CN117495619B (en) * | 2023-12-25 | 2024-04-05 | 西安文理学院 | Intelligent travel method and system based on big data sharing |
| CN117992677A (en) * | 2024-04-07 | 2024-05-07 | 北京中景合天科技有限公司 | Intelligent travel market prediction recommendation method and system based on big data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| CN107341350A (en) * | 2017-07-05 | 2017-11-10 | 百度在线网络技术（北京）有限公司 | Food materials intelligent management and device, server, intelligent refrigerator, storage medium |
| CN108510321A (en) * | 2018-03-23 | 2018-09-07 | 北京焦点新干线信息技术有限公司 | A kind of construction method and device of house property user portrait |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3062279A1 (en) * | 2015-02-27 | 2016-08-31 | BBVA Data & Analytics, S.L.U. | Method and system for generation of parameters |
| CN108154401B (en) * | 2018-01-15 | 2022-03-29 | 阿里巴巴（中国）有限公司 | User portrait depicting method, device, medium and computing equipment |
-
2019
- 2019-01-29 CN CN201910087016.3A patent/CN109919437B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| CN107341350A (en) * | 2017-07-05 | 2017-11-10 | 百度在线网络技术（北京）有限公司 | Food materials intelligent management and device, server, intelligent refrigerator, storage medium |
| CN108510321A (en) * | 2018-03-23 | 2018-09-07 | 北京焦点新干线信息技术有限公司 | A kind of construction method and device of house property user portrait |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109919437A (en) | 2019-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109919437B (en) | big data-based intelligent tourism target matching method and system | |
| Zhao et al. | A trajectory clustering approach based on decision graph and data field for detecting hotspots | |
| Brockett et al. | Using rank statistics for determining programmatic efficiency differences in data envelopment analysis | |
| US11294981B2 (en) | System and method for large scale crowdsourcing of map data cleanup and correction | |
| JP2021108183A (en) | Method, apparatus, device and storage medium for intention recommendation | |
| CN110472163B (en) | Method, device, electronic equipment and medium for determining display of map search result | |
| CN107168991B (en) | Search result display method and device | |
| US20080126523A1 (en) | Hierarchical clustering of large-scale networks | |
| CN111738596B (en) | Work order dispatching method and device | |
| US20110082803A1 (en) | Business flow retrieval system, business flow retrieval method and business flow retrieval program | |
| US11544307B2 (en) | Personnel selecting device, personnel selecting system, personnel selecting method, and recording medium | |
| Markou et al. | Predicting taxi demand hotspots using automated internet search queries | |
| CN110737805B (en) | Method and device for processing graph model data and terminal equipment | |
| CN106933883B (en) | Method and device for classifying common search terms of interest points based on search logs | |
| CN109446253A (en) | Data query control method, device, computer equipment and storage medium | |
| Rahaman et al. | Wait time prediction for airport taxis using weighted nearest neighbor regression | |
| CN111191111A (en) | Content recommendation method, device and storage medium | |
| CN110427574B (en) | Route similarity determination method, device, equipment and medium | |
| CN110245286B (en) | travel recommendation method and device based on data mining | |
| Zhang et al. | Automatic latent street type discovery from web open data | |
| Belcastro et al. | Parallel extraction of Regions‐of‐Interest from social media data | |
| CN117709968A (en) | Personnel allocation method, apparatus, computer device and storage medium | |
| CN107798450B (en) | Service distribution method and device | |
| CN115935076A (en) | Travel service information pushing method and system based on artificial intelligence | |
| CN112328752B (en) | Course recommendation method and device based on search content, computer equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |