CN116089730B - Travel route recommending method - Google Patents
Travel route recommending method Download PDFInfo
- Publication number
- CN116089730B CN116089730B CN202310361854.1A CN202310361854A CN116089730B CN 116089730 B CN116089730 B CN 116089730B CN 202310361854 A CN202310361854 A CN 202310361854A CN 116089730 B CN116089730 B CN 116089730B
- Authority
- CN
- China
- Prior art keywords
- travel
- node
- nodes
- city
- route
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000009471 action Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000001932 seasonal effect Effects 0.000 description 4
- 241000222120 Candida <Saccharomycetales> Species 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- MKXZASYAUGDDCJ-NJAFHUGGSA-N dextromethorphan Chemical compound C([C@@H]12)CCC[C@]11CCN(C)[C@H]2CC2=CC=C(OC)C=C21 MKXZASYAUGDDCJ-NJAFHUGGSA-N 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- BULVZWIRKLYCBC-UHFFFAOYSA-N phorate Chemical compound CCOP(=S)(OCC)SCSCC BULVZWIRKLYCBC-UHFFFAOYSA-N 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
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
-
- 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
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- 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
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a travel route recommending method, in particular to the technical field of travel. The method comprises the following steps: and acquiring travel dates, travel days, departure cities, passing cities, arrival cities, travel recommendation types and travel preference types which are input by the user. And determining a target city journey according to the travel days, the departure city, the passing city and the arrival city based on a pre-constructed travel knowledge graph. And determining a node recommendation score corresponding to each travel node according to the travel preference type, the travel recommendation type, the travel date and the average selling proportion corresponding to the travel node associated with each city node in the target city travel based on a pre-constructed travel knowledge graph. And determining a travel recommended route according to the node recommended score corresponding to each travel node based on a pre-constructed travel knowledge graph, and pushing the travel recommended route to the user. By adopting the travel route recommendation method and device, travel routes can be recommended for users.
Description
Technical Field
The application relates to the technical field of travel, in particular to a travel route recommending method.
Background
At present, the small group spliced game gradually becomes a hot trip mode, and designing the proper small group spliced game is a complex and tedious matter, and needs to consider the problems of choosing and separating scenic spots, playing seasons, dates, time, whether routes are reasonable, traffic connection of strokes among all scenic spots and the like.
The user uses the intelligent terminal device to view the related travel information on the internet to conduct travel route planning, and a great deal of time and effort are required. Moreover, the travel route provided by the traditional travel website is also relatively fixed, so that accurate recommendation is difficult to provide for users, and the travel service quality and the travel experience of travelers are greatly reduced.
Therefore, it is highly desirable to provide personalized scenic spot recommendation and route planning services for users, so as to save time and economic cost of the users and improve the travel experience of the users, which has important significance for fully building and developing intelligent travel, meeting personalized requirements of tourists and improving the quality of travel service.
Disclosure of Invention
Based on this, it is necessary to provide a travel route recommendation method, aiming at the technical problems, the method includes:
acquiring travel dates, travel days, departure cities, passing cities, arrival cities, travel recommendation types and travel preference types input by a user;
Determining a target city journey according to the travel days, the departure city, the passing city and the arrival city based on a pre-constructed travel knowledge graph;
determining a node recommendation score corresponding to each travel node according to the travel preference type, the travel recommendation type, the travel date and the average selling proportion corresponding to the travel node associated with each city node in the target city travel based on the pre-constructed travel knowledge graph;
and determining a travel recommended route according to the node recommended score corresponding to each travel node based on the pre-constructed travel knowledge graph, and pushing the travel recommended route to the user.
As an optional implementation manner, the determining, based on the pre-constructed travel knowledge graph, a target city trip according to the travel days, the departure city, the passing city and the arrival city includes:
determining the shortest journey of all the passing cities as an initial city journey based on the pre-constructed travel knowledge graph;
and determining a target city journey based on the pre-constructed travel knowledge graph according to the travel days, the initial city journey, the breadth-first traversal algorithm and a preset first traversal constraint condition, wherein the target city journey at least comprises a departure city, a passing city and an arrival city.
As an optional implementation manner, the formula corresponding to the preset first traversal constraint condition is:
sum(J i )+k-i+1<D；
wherein J is i For the current city and the last city J i-1 Degree of connectivity between them, sum (J) i ) In order to reach the total connectivity of the current city from the departure city, k is the number of passing cities, i represents the serial number of the current city, and D is the travel days.
As an optional implementation manner, the determining, based on the pre-constructed travel knowledge graph, a node recommendation score corresponding to each travel node according to the travel preference type, the travel recommendation type, the travel date, and an average selling proportion corresponding to a travel node associated with each city node in the target city travel, includes:
inquiring travel nodes associated with each city node in the target city travel based on the pre-constructed travel knowledge graph, and forming a travel node set;
determining a date label node corresponding to the travel date and a travel preference node corresponding to the travel preference type in the pre-constructed travel knowledge graph;
determining the relevance of map nodes and all label nodes based on the pre-constructed travel knowledge map and a pre-set relevance algorithm, wherein the map nodes comprise the label nodes and the travel nodes in the travel node set, and the label nodes comprise date label nodes and travel preference nodes;
And determining a node recommendation score corresponding to each travel node according to the relevance of each travel node and each label node, the average selling proportion corresponding to each travel node and the travel recommendation type.
As an optional implementation manner, the calculation formula for determining the relevance between the map node and each label node based on the pre-constructed travel knowledge map and the pre-set relevance algorithm is as follows:
wherein,,Xrepresenting map nodesX，C l （X）Representing map nodesXThe degree of correlation with the tag node Ll,La sequence of tag nodes is represented and,L l representing tag nodes in a sequence of tag nodesL l ，aThe conversion rate parameter is represented by a number of bits,in（X）representing map nodesXA set of inflow nodes in the travel knowledge graph,Yrepresenting map nodesXIs used for the input degree node of the (1),C l （Y）inlet degree node of representationYWith tag nodeL l Is used for the correlation of the data in the database,∣out(Y)∣representing an input degree nodeYNumber of nodes in the outbound node set in the travel knowledge graph.
As an optional implementation manner, the trip recommendation types include a hot trip recommendation type and a crowd trip recommendation type, and the formula for determining the node recommendation score corresponding to each trip node according to the relevance of each trip node to each tag node, the average selling proportion corresponding to each trip node and the trip recommendation type is as follows:
Wherein Candida represents a travel node set, Z represents a travel node Z in the travel node set Candida,S（Z）representing travel nodesZThe corresponding node recommends a score that,P（Z）representing the average sales ratio for trip node Z, |candidate| represents the number of trip nodes in the set of trip nodes,C l （W）representing travel nodesWWith tag nodeL l Is used for the correlation of the data in the database,C l （Z）representing map nodesZWith tag nodeL l Is used for the correlation of the data in the database,nfor the number of travel preference nodes,pfor the number of date tag nodes,Qindicating the trip recommendation type.
As an optional implementation manner, the determining a trip recommended route according to the node recommendation score corresponding to each trip node based on the pre-constructed travel knowledge graph, and pushing the trip recommended route to the user includes:
determining a travel candidate route corresponding to each city node in the target city travel based on the pre-constructed travel knowledge graph according to the travel node, the depth-first traversal algorithm and a preset second traversal constraint condition associated with the city node;
for each route candidate route, determining a route recommendation score of the route candidate route according to the number of route nodes in the route candidate route, the node recommendation score corresponding to each route node and driving time consumption between two adjacent route nodes;
And determining the route candidate route with the highest first preset number of route recommendation scores as the route recommendation route according to the sequence from high to low, and pushing the route recommendation route to the user.
As an optional implementation manner, the formula corresponding to the preset second traversal constraint condition is:
wherein,,t end for a preset end-of-travel time,tfor the preset current time period to be set,pfor a preset starting trip node for the day,cis a preset termination journey node for the current day,s 1 for the 1 st trip node to play on the day,s i for playing on the same dayiThe number of travel nodes is one,T(p, s 1 )from p tos 1 Is time-consuming in the driving course of the vehicle,T(s j , c)is the slaves j The trip to c is time consuming,T(s i , s i+1 )is the slaves i To the point ofs i+1 Is time-consuming in driving process, w%s 1 ) Is a journey nodes 1 Recommended play time, w #s i ) Is a journey nodes i Recommended play time, w #s j ) Is a journey nodes j Is a recommended play time for (a).
As an optional implementation manner, for each route candidate route, according to the number of route nodes in the route candidate route, the node recommendation score corresponding to each route node, and the driving time consumption between two preset adjacent route nodes, the formula for determining the route recommendation score of the route candidate route is as follows:
Wherein,,Tas a route candidate for the journey,S(T)a route recommendation score for the route candidate route of the route,S(X i )candidate routes for journeyTMiddle (f)iThe nodes of the individual trip nodes recommend scores,scandidate routes for journeyTIs a function of the number of travel nodes in the network,t(X i ， X i-1 )for a predetermined travel nodeXiWith adjacent travel nodesX i-1 Is time-consuming in minutes.
As an alternative embodiment, the method further comprises:
adding month label nodes and holiday label nodes in an initial travel knowledge graph, establishing a two-way relation between adjacent month label nodes, and establishing a two-way relation between the month label nodes and the holiday label nodes;
adding travel preference nodes into the initial travel knowledge graph;
adding city nodes and city attribute information into the initial travel knowledge graph;
adding travel nodes and travel attribute information into the initial travel knowledge graph, and establishing an association relationship between city nodes and travel nodes;
in the initial travel knowledge graph, aiming at each travel route corresponding to each city node in each history travel of a user, taking the city node as a starting point, sequentially acquiring each travel node in the travel route, establishing an association relationship of adjacent travel nodes, and adding a history travel number and a travel time for the association relationship;
In the initial travel knowledge graph, establishing an association relationship between each historical travel and travel preference nodes, and establishing an association relationship between a first travel corresponding to each daily travel in each historical travel and travel preference nodes;
in the initial travel knowledge graph, acquiring the visit date of each travel node in a travel route aiming at each travel route of each city node in each history travel of a user, and establishing the association relationship between a month label node and a holiday label node corresponding to the visit date and the travel node;
in the initial travel knowledge graph, for each history journey of the user, if the number of passing cities in the history journey is greater than 1, establishing an association relationship between the history journey and the passing cities in the history journey.
The application provides a travel recommendation method, and the technical scheme provided by the embodiment of the application at least brings the following beneficial effects: and acquiring travel dates, travel days, departure cities, passing cities, arrival cities, travel recommendation types and travel preference types which are input by the user. And determining a target city journey according to the travel days, the departure city, the passing city and the arrival city based on a pre-constructed travel knowledge graph. And determining a node recommendation score corresponding to each travel node according to the travel preference type, the travel recommendation type, the travel date and the average selling proportion corresponding to the travel node associated with each city node in the target city travel based on the pre-constructed travel knowledge graph. And determining a travel recommended route according to the node recommended score corresponding to each travel node based on the pre-constructed travel knowledge graph, and pushing the travel recommended route to the user. The travel recommendation method provided by the application can establish correlation among the user, the travel and the travel products based on the travel knowledge graph, automatically analyze the choice of travel nodes associated with each city node for the user, judge whether the playing season, date, time and line of each travel node are reasonable, connect the traffic of each travel section and the like, and provide a depth customized travel product for the user.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a travel itinerary recommendation method according to an embodiment of the present application;
FIG. 2 is a flowchart of a method for determining a target city trip according to an embodiment of the present disclosure;
FIG. 3 is a flowchart of a method for determining a node recommendation score according to an embodiment of the present disclosure;
FIG. 4 is a flowchart of a method for determining a route recommended by a trip according to an embodiment of the present application;
FIG. 5 is a flowchart of another travel itinerary recommendation method provided by embodiments of the present application;
fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
In the following, a detailed description will be given of a travel route recommending method provided in the embodiment of the present application with reference to a specific implementation, and fig. 1 is a flowchart of a travel route recommending method provided in the embodiment of the present application, and as shown in fig. 1, specific steps are as follows:
step 101, obtaining travel dates, travel days, departure cities, approach cities, arrival cities, travel recommendation types and travel preference types input by a user.
In practice, travel has seasonal and regional characteristics, and the reasons for the seasonal characteristics mainly comprise influence of factors such as climate and influence of holiday system. Aiming at seasonal influence, the travel date and travel days input by the user can be acquired, so that holidays or seasons corresponding to the travel date range of the user can be determined, and travel products conforming to seasonal features can be recommended to the user in a targeted manner. Aiming at regional characteristics, the embodiment of the application can acquire the departure city, the passing city and the arrival city input by the user so as to determine the travel area of the user, and accordingly, corresponding travel products are recommended to the user in the area. In addition, the personal preference of the user is also an important factor affecting the travel, so that the travel recommendation type and the travel preference type input by the user are obtained, the preference of the user for the travel product is determined to be personal, history, delicacies or parent and the like, or the user likes the travel product of the masses, seeks to be unique or favors hot spots, so that the recommended travel product meets the requirements of the user for the travel product.
Step 102, determining a target city journey according to travel days, a departure city, a passing city and an arrival city based on a pre-constructed travel knowledge graph.
In the implementation, based on a pre-constructed travel knowledge graph, the passing cities can be planned according to travel days, departure cities, passing cities and arrival cities, all the passing cities which can pass through are determined, and the target city journey of surrounding city play can be performed under the condition of permission of travel days.
Optionally, fig. 2 is a flowchart of a method for determining a target city trip provided in the embodiment of the present application, as shown in fig. 2, in step 102, based on a pre-constructed travel knowledge graph, the specific steps for determining the target city trip according to the travel days, the departure city, the passing city and the arrival city are as follows:
step 201, determining the shortest journey of all the passing cities as the initial city journey based on the pre-constructed travel knowledge graph.
In the implementation, after the departure city, the passing city and the arrival city input by the user are acquired, the shortest journey of all the passing cities is determined as the initial city journey according to the traffic distance among families of the cities. If the number of passing cities is less than or equal to 1, the initial city trip may be determined directly. If there is more than one transit city, for example: the departure city input by the user is Beijing, the passing cities are Tianjin, guangzhou and Shanghai, and the arrival city is Shenzhen, so that the embodiment of the application firstly determines a city which passes through all cities according to the traffic distance among the passing cities (Tianjin, guangzhou and Shanghai) and has the shortest path, and the user is prevented from consuming more time in traffic. Finally, the shortest route can be determined as Beijing-Tianjin-Shanghai-Guangzhou-Shenzhen. This shortest route of travel is determined to be the initial city route.
Step 202, determining a target city journey based on a pre-constructed travel knowledge graph according to travel days, an initial city journey, a breadth-first traversal algorithm and a preset first traversal constraint condition, wherein the target city journey at least comprises a departure city, a passing city and an arrival city.
In practice, in addition to the city entered by the user in step 201, there may be transit cities depending on the vehicles used by the user, the presence or absence of the direct, and the consideration of the travel costs of the user. Such as: if the user selects the passing city and the last city or the next city have no direct action, or the direct action scheme has higher cost, or the travel daysEnough users play around the route, the embodiment of the application determines the target city journey according to the travel days, the initial city journey, the breadth-first traversal algorithm and the preset first traversal constraint condition based on the pre-constructed travel knowledge graph, wherein the target city journey at least comprises a departure city, a passing city and an arrival city and can also comprise a transit city, and the embodiment of the application can determine whether to stay in the transit city and play according to the travel days input by the users. Specifically, breadth-first traversal algorithm may be used for analysis, for example: the travel days are D, and the departure city is S 0 Passing through City S i The number of (2) is k, respectively S 1 、S 2 、…S k Ending city as S k+1 Then can use (S 0 ，S 1 )、(S 1 ，S 2 )、...(S k ，S k+1 ) Representing the route between two adjacent cities in the initial city trip. The surrounding cities of each passing city Si are traversed in breadth to (S 0 ，S 1 ) For example, since k passing cities and 1 arrival city are cities that must stay to play in the initial city journey, the method is performed in the screening (S 0 ，S 1 ) When the city is transferred, the D-1-k degree (unit: day, indicating route time-consuming) to ensure that there are at least one day of stay in the next k transit cities and 1 arrival city. If the cities are connected by Ji degrees (unit: day), the Ji degrees at least wrap the time of the journey, and can also comprise stay time, and Ji is accumulated successively. When sum (Ji) +k-i+1>When=d, the following transit city stop is abandoned. If final sum (Ji) +k-i+1<And D, circularly selecting top (min (D-sum (Ji) -k-1, k)) most distant arrival cities to link.
Optionally, the formula corresponding to the preset first traversal constraint in step 202 may be:
sum(J i )+k-i+1<d (formula I);
wherein J is i For the current city and the last city J i-1 Degree of connectivity between them, sum (J) i ) To reach the total connectivity of the current city from the departure city, k is the via city The number i represents the serial number of the current city, and D represents the travel days.
Step 103, determining a node recommendation score corresponding to each travel node according to the travel preference type, the travel recommendation type, the travel date and the average selling proportion corresponding to the travel node associated with each city node in the target city travel based on the pre-constructed travel knowledge graph.
In implementation, after the target city trip is determined, the trip node associated with each city node in the target city trip can be determined based on a pre-constructed travel knowledge graph, but the number of the trip nodes associated with each city node is large, and the trip nodes cannot be completely recommended to the user. Therefore, the embodiment of the application can determine the node recommendation score corresponding to each travel node according to the travel preference type, the travel recommendation type, the travel date and the average selling proportion corresponding to the travel node associated with each city node in the target city travel based on the travel knowledge graph constructed in advance.
Optionally, fig. 3 is a flowchart of a method for determining a node recommendation score according to an embodiment of the present application, as shown in fig. 3, in step 103, based on a pre-constructed travel knowledge graph, according to a travel preference type, a travel recommendation type, a travel date, and an average selling ratio corresponding to a travel node associated with each city node in a target city travel, the specific steps of determining the node recommendation score corresponding to each travel node are as follows:
Step 301, inquiring travel nodes associated with each city node in the target city travel based on a pre-constructed travel knowledge graph, and forming a travel node set.
In the implementation, since each city node is already contained in the travel knowledge graph, the association relationship between the city corresponding to the city node and the travel nodes such as hotels and scenic spots in the city is established. Therefore, the embodiment of the application can query the travel nodes associated with each city node in the target city travel based on the pre-constructed travel knowledge graph and form a travel node set.
Step 302, determining a date label node corresponding to the travel date and a travel preference node corresponding to the travel preference type in a pre-constructed travel knowledge graph.
In implementation, in a pre-constructed travel knowledge graph, a date label node corresponding to a travel date and a travel preference node corresponding to a travel preference type are determined. Such as: the travel date input by the user is 5 months and 1 day, and the travel purpose is to taste the food with local characteristics. According to the information input by the user, based on a pre-constructed travel knowledge graph, it can be determined that the date label node can comprise five months, labor sections, summer and the like, and the travel preference node corresponding to the travel preference type is food.
Step 303, determining the relevance between the map node and each label node based on the pre-constructed travel knowledge map and a pre-set relevance algorithm, wherein the map node comprises label nodes and travel nodes in a travel node set, and the label nodes comprise date label nodes and travel preference nodes.
In an implementation, the graph nodes include a tag node and a travel node in the set of travel nodes, the tag node including a date tag node and a travel preference node. By usingX i Represent the firstiThe nodes of the map are connected with each other,La sequence of tag nodes is represented and,L l represent the firstlAnd a plurality of tag nodes, wherein,L 1 、L 2 …L n in order for the travel preference node to be a travel preference node,L n+1 、L n+2 …L n+p setting vectors for date tag nodesC （Xi）For representingX i And (3) withL 1 Is used for the correlation of the data in the database,X i and (3) withL 2 Is … of the correlation degree of (5)XiAnd (3) withL n+p Is a correlation of (a) and (b). By C l （X i ) Representation, the firstiIndividual graph nodesX i And the firstlPersonal tag node L l Is a correlation of (a) and (b). Nodes with a certain mapX g And a certain tag node L h For example, if the graph nodesX g Belonging to a tag node sequenceLBut is not equal to the tag node L h Then the graph nodes can be determinedX g And tag node L h Are different tag nodes. The label node comprises a date label node and a travel preference node, wherein the travel preference node can be a personally preferred node, a historical preference node or a parent-child preference node and the like, and obviously, different dates in one year have no direct relation to whether a user prefers the history or the family parent-child, so that the map node X g And tag node L h Is low or 0. Another example is: if the map nodeX g Not belonging to a sequence of tag nodesLThen the graph nodes can be determinedX g For the travel nodes in the travel node set, the map nodes can be determined according to a preset correlation algorithmX g And tag node L h Is a correlation of (a) and (b).
Optionally, in step 303, based on the pre-constructed travel knowledge graph and a pre-set correlation algorithm, a calculation formula for determining the correlation between the graph node and each label node is:
wherein,,Xrepresenting map nodesX，C l （X）Representing map nodesXWith tag nodeL l Is used for the correlation of the data in the database,La sequence of tag nodes is represented and,L l representing tag nodes in a sequence of tag nodesL l ，aThe conversion rate parameter is represented by a number of bits,in（X）representing map nodesXA set of inflow nodes in the travel knowledge graph,Yrepresenting map nodesXIs used for the input degree node of the (1),C l （Y）inlet degree node of representationYWith tag nodeL l Is used for the correlation of the data in the database,∣out(Y)∣representing an input degree nodeYNumber of nodes in the outbound node set in the travel knowledge graph.
In practice, a map is first determinedNodeXWhether or not it belongs to a tag node sequenceLIf not, according toXNot belong toLUsing the conditions of the computational graph nodesXWith tag nodeL l Is related to the degree of correlation of (2)C l （X）. If the map node XBelonging to a tag node sequenceLFurther judging the map nodeXWhether to calculate the label node of the correlation degreeL l Similarly, if so, the correlation is 1, if not, the correlation is 0, and the iteration end condition may beC l （X）No change in the value of (2) occurs.
Step 304, determining a node recommendation score corresponding to each travel node according to the relevance of each travel node and each label node, the average selling proportion corresponding to each travel node and the travel recommendation type.
In implementation, after the relevance between each trip node and each tag node is determined, the vending data of each trip node in the trip node set can be further queried, and the average vending proportion of the trip nodes such as scenic spots, hotels and the like in the trip date range is obtained. For the trip node which can not inquire the vending data, the default average vending ratio can be preset to be 0.5. When calculating the node recommendation score corresponding to each trip node, the trip recommendation type input by the user can be considered, and the crowd trip node is taken as an example: generally, the average selling proportion of the travel nodes of the masses is low, so if the travel recommendation type input by the user is the mass travel recommendation type, the reciprocal mode of calculating the average selling proportion can be adopted to enable the travel points of the masses to obtain higher scores.
Optionally, in step 304, the trip recommendation types include a popular trip recommendation type and an audience trip recommendation type, and according to the relevance of each trip node to each tag node, the average selling ratio corresponding to each trip node, and the trip recommendation type, a formula of a node recommendation score corresponding to each trip node is determined as follows:
wherein Candidate represents a travel node set, and Z represents a travel node in the travel node set CandidateZ，S（Z）Representing travel nodesZThe corresponding node recommends a score that,P（Z）representing the average sales ratio for trip node Z, |candidate| represents the number of trip nodes in the set of trip nodes,C l （W）representing travel nodesWWith tag nodeL l Is used for the correlation of the data in the database,C l （Z）representing graph nodes Z and label nodesL l Is used for the correlation of the data in the database,nfor the number of travel preference nodes,pfor the number of date tag nodes,Qindicating the trip recommendation type.
And 104, determining a travel recommended route according to the node recommended score corresponding to each travel node based on the pre-constructed travel knowledge graph, and pushing the travel recommended route to the user.
In implementation, determining a node recommendation score corresponding to each travel node, planning a travel node with a high and feasible node recommendation score into a travel recommendation route based on a pre-constructed travel knowledge graph according to the node recommendation score, and pushing the travel recommendation route to a user.
Optionally, fig. 4 is a flowchart of a method for determining a route recommended by a trip according to an embodiment of the present application, as shown in fig. 4, in step 104, based on a pre-constructed travel knowledge graph, a route recommended by a trip is determined according to a node recommendation score corresponding to each trip node, and the specific steps of pushing the route recommended by the trip to a user are as follows:
step 401, for each city node in the target city journey, determining a journey candidate route corresponding to the city node according to a journey node, a depth-first traversal algorithm and a preset second traversal constraint condition associated with the city node based on a pre-constructed travel knowledge graph.
In implementation, the number of travel nodes associated with the city node is large, but not all the travel nodes are feasible, so that all the travel nodes can be traversed according to the preset departure time of the day based on the preset second traversal constraint condition and the depth-first traversal algorithm, and the travel nodes which are not opened, have overtime travel time and have overtime travel time are eliminated, so that feasible travel nodes which can form routes are selected, and the travel nodes are planned into a plurality of travel candidate routes.
Alternatively, if the number of travel nodes associated with the city node is excessive, such as some travel popular cities or first-line cities, resulting in an excessively large result set being screened, only the travel nodes with the highest recommended scores of the nodes may be reserved, and a depth-first traversal algorithm may be performed on the travel nodes.
Optionally, the formula corresponding to the preset second traversal constraint in step 401 may be:
wherein,,t end for a preset end-of-travel time,tfor the preset current time period to be set,pfor a preset starting trip node for the day,cis a preset termination journey node for the current day,s 1 for the 1 st trip node to play on the day,s i for playing on the same dayiThe number of travel nodes is one,T(p, s 1 )from p tos 1 Is time-consuming in the driving course of the vehicle,T(s j , c)is the slaves j The trip to c is time consuming,T(s i , s i+1 )is the slaves i To the point ofs i+1 Is time-consuming in driving process, w%s 1 ) Is a journey nodes 1 Recommended play time, w #s i ) Is a journey nodes i Recommended play time, w #s j ) Is a journey nodes j Is a recommended play time for (a).
In practice, from a preset starting trip node of the daypStarting according to the current timetTermination of a preset dayJourney nodecEstimating the end-of-travel timet end The method specifically can be to accumulate the time consumption of the journey between the adjacent journey nodes and the recommended playing time of each journey node by using the current time t, and the accumulated result is the journey end time t end . If the travel end time is presett end The number of trip nodes in the route and the trip time between adjacent trip nodes can be controlled or constrained. For the trip planning of a certain city node on the first day, the initial trip node input by the user can be obtained as the initial trip node of the current daypIf the initial travel node input by the user cannot be acquired, selecting to directly check in a nearby travel node (hotel), ending one-day travel, setting the current time as the departure time of the next day, setting the current place as the hotel location, and repeating the travel planning of the next day.
Step 402, determining, for each route candidate route, a route recommendation score of the route candidate route according to the number of route nodes in the route candidate route, the node recommendation score corresponding to each route node, and driving time between two adjacent route nodes.
In implementation, after determining the route candidate route, the route recommendation score of the route candidate route may be determined according to the number of route nodes in the route candidate route, the node recommendation score corresponding to each route node, and driving time between two adjacent route nodes.
Optionally, in step 402, for each route candidate route, according to the number of route nodes in the route candidate route, the node recommendation score corresponding to each route node, and the driving time between two preset adjacent route nodes, a formula for determining the route recommendation score of the route candidate route is as follows:
Wherein,,Tas a route candidate for the journey,S(T)a route recommendation score for the route candidate route of the route,S(X i )candidate routes for journeyTMiddle (f)iThe nodes of the individual trip nodes recommend scores,scandidate routes for journeyTIs a function of the number of travel nodes in the network,t(X i ， X i-1 )for a predetermined travel nodeXiWith adjacent travel nodesX i-1 Is time-consuming in minutes.
Step 403, determining the route candidate route with the highest first preset number of route recommendation scores as a route recommendation route according to the sequence from high to low, and pushing the route recommendation route to the user.
In implementation, the route candidates may be ranked in order of high-to-low route recommendation scores, and the route candidate route having the highest route recommendation score of the first preset number may be determined as the route recommendation route, and the route recommendation route may be pushed to the user.
Optionally, the route recommended by the journey pushed to the user is editable, so that the user can edit and adjust the route recommended by the journey, and the route recommended by the journey after editing and adjusting is saved in the travel knowledge graph for future planning recommendation in response to a saving instruction of the user for the route recommended by the journey after editing and adjusting.
As an alternative implementation, fig. 5 is a flowchart of another method for recommending travel itineraries provided in the embodiment of the present application, as shown in fig. 5: the method comprises the following specific steps:
Step 501, adding month label nodes and holiday label nodes in an initial travel knowledge graph, establishing a two-way relationship between adjacent month label nodes, and establishing a two-way relationship between the month label nodes and the holiday label nodes.
In the implementation, month label nodes such as one month to twelve months and the like, and festival holiday label nodes such as a primordial denier, a spring festival, a Qing Ming festival, a labor festival, an end noon festival, a mid-autumn festival, a national celebration festival, a cold holiday, a summer holiday and the like are added in the initial travel knowledge graph, and a bidirectional relation is established between adjacent months. A two-way relationship is established between primordial denier and month, spring festival and month of february, qing festival and month of april, labor festival and month of june, midautumn festival and month of september, national festival and month of october.
Step 502, adding travel preference nodes in the initial travel knowledge graph.
In practice, travel preference nodes, such as people, history, delicacies, parents, etc., are added to the initial travel knowledge graph.
In step 503, city nodes and city attribute information are added to the initial travel knowledge graph.
In implementation, city nodes are added in the initial travel knowledge graph, and the longitude and latitude of the central position of the city are used as city attribute information of the city.
And step 504, adding travel nodes and travel attribute information into the initial travel knowledge graph, and establishing association relations between city nodes and travel nodes.
In the implementation, travel nodes such as scenic spots and hotels are added in the initial travel knowledge graph, position information such as longitude and latitude, travel attribute information such as opening time and the like are input into the knowledge graph, and an association relationship between the city nodes and the travel nodes is established.
In step 505, in the initial travel knowledge graph, for each trip route corresponding to each city node in each historical trip of the user, taking the city node as a starting point, sequentially obtaining each trip node in the trip route, establishing an association relationship of adjacent trip nodes, and adding a historical trip number and a trip time for the association relationship.
In practice, in the initial travel knowledge graph, for each historical trip of the user, data t, assuming that the historical trip is for m days, t ij For the jth journey of the ith day of a certain city in the historical journey, taking the city as a starting point, sequentially acquiring each journey node, and sequentially taking t as the starting point i1 、t i2 (i=1, 2, m), an association is established between adjacent travel nodes, and adding a history journey number t and journey time for the association relation.
Step 506, in the initial travel knowledge graph, establishing an association relationship between each historical travel and the travel preference node, and establishing an association relationship between the first travel corresponding to the daily travel in each historical travel and the travel preference node.
In practice, for each of the historically available trip data t in the initial travel knowledge graph, its trip preference node (humane, history, food, parent, noted L (t, 1), L (t, 2), L (t, L)) and the first trip node per day ti1 are associated in the knowledge graph (i=1, 2.
Step 507, in the initial travel knowledge graph, for each trip route of each city node in each historical trip of the user, obtaining a visited date of each trip node in the trip route, and establishing an association relationship between the month label node corresponding to the visited date and the holiday label node and the trip node.
In implementation, in the initial travel knowledge graph, for each historical travel data t of a user, the visit date of each travel node is obtained in the initial travel knowledge graph, and the association relationship between the month label node corresponding to the visit date and the holiday label node and the travel node is established.
Step 508, in the initial travel knowledge graph, for each historical trip of the user, if the number of passing cities in the historical trip is greater than 1, establishing an association relationship between the historical trip and the passing cities in the historical trip.
In practice, for each historical trip data t of a user in the initial travel knowledge graph, if there is more than one passing city in the historical trip, then the passing cities are associated in the initial travel knowledge graph.
The embodiment of the application provides a travel route recommending method, which comprises the following steps: and acquiring travel dates, travel days, departure cities, passing cities, arrival cities, travel recommendation types and travel preference types which are input by the user. And determining a target city journey according to travel days, departure cities, passing cities and arrival cities based on a pre-constructed travel knowledge graph. And determining a node recommendation score corresponding to each travel node according to the travel preference type, the travel recommendation type, the travel date and the average selling proportion corresponding to the travel node associated with each city node in the target city travel based on the pre-constructed travel knowledge graph. And determining a travel recommended route according to the node recommended score corresponding to each travel node based on the pre-constructed travel knowledge graph, and pushing the travel recommended route to the user. The travel recommendation method provided by the application can establish correlation among the user, the travel and the travel products based on the travel knowledge graph, automatically analyze the choice of travel nodes associated with each city node for the user, judge whether the playing season, date, time and line of each travel node are reasonable, connect the traffic of each travel section and the like, and provide a depth customized travel product for the user.
It should be understood that, although the steps in the flowcharts of fig. 1 to 5 are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a portion of the steps of fig. 1-5 may include steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily occur sequentially, but may be performed alternately or alternately with other steps or at least a portion of the steps or stages in other steps.
It should be understood that the same/similar parts of the embodiments of the method described above in this specification may be referred to each other, and each embodiment focuses on differences from other embodiments, and references to descriptions of other method embodiments are only needed.
In one embodiment, a computer device is provided, as shown in fig. 6, comprising a memory and a processor, the memory having stored thereon a computer program executable on the processor, the processor executing the computer program to perform the recommended method steps of travel itinerary described above.
In one embodiment, a computer readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the method of travel itinerary recommendation described above.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
It should be noted that, user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for presentation, analyzed data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (7)
1. A method of recommending travel itineraries, the method comprising:
acquiring travel dates, travel days, departure cities, passing cities, arrival cities, travel recommendation types and travel preference types input by a user;
determining a target city journey according to the travel days, the departure city, the passing city and the arrival city based on a pre-constructed travel knowledge graph;
determining a node recommendation score corresponding to each travel node according to the travel preference type, the travel recommendation type, the travel date and the average selling proportion corresponding to the travel node associated with each city node in the target city travel based on the pre-constructed travel knowledge graph;
determining a travel recommended route according to the node recommended score corresponding to each travel node based on the pre-constructed travel knowledge graph, and pushing the travel recommended route to the user;
the determining, based on the pre-constructed travel knowledge graph, a node recommendation score corresponding to each travel node according to the travel preference type, the travel recommendation type, the travel date, and an average selling ratio corresponding to a travel node associated with each city node in the target city travel, includes:
Inquiring travel nodes associated with each city node in the target city travel based on the pre-constructed travel knowledge graph, and forming a travel node set;
determining a date label node corresponding to the travel date and a travel preference node corresponding to the travel preference type in the pre-constructed travel knowledge graph;
determining the relevance of map nodes and all label nodes based on the pre-constructed travel knowledge map and a pre-set relevance algorithm, wherein the map nodes comprise the label nodes and the travel nodes in the travel node set, and the label nodes comprise date label nodes and travel preference nodes;
determining a node recommendation score corresponding to each travel node according to the relevance of each travel node and each label node, the average selling proportion corresponding to each travel node and the travel recommendation type;
the calculation formula for determining the relevance between the map node and each label node based on the pre-constructed travel knowledge map and a preset relevance algorithm is as follows:
wherein,,Xrepresenting map nodesX，C l （X）Representing map nodesXWith tag nodeL l Is used for the correlation of the data in the database,La sequence of tag nodes is represented and, L l Representing tag nodes in a sequence of tag nodesL l ，aThe conversion rate parameter is represented by a number of bits,in（X）representing map nodesXA set of inflow nodes in the travel knowledge graph,Yrepresenting map nodesXIs used for the input degree node of the (1),C l （Y）inlet degree node of representationYWith tag nodeL l Is used for the correlation of the data in the database,∣out(Y)∣representing an input degree nodeYThe number of nodes in the outbound node set in the travel knowledge graph;
the trip recommendation type comprises a hot trip recommendation type and a minor trip recommendation type, and the formula for determining the node recommendation score corresponding to each trip node according to the relevance of each trip node to each tag node, the average selling proportion corresponding to each trip node and the trip recommendation type is as follows:
wherein Candidate represents a travel node set, and Z represents a travel node in the travel node set CandidateZ，S （Z）Representing travel nodesZThe corresponding node recommends a score that,P（Z）representing the average sales ratio for trip node Z, |candidate| represents the number of trip nodes in the set of trip nodes,C l （W）representing travel nodesWWith tag nodeL l Is used for the correlation of the data in the database,C l （Z）representing map nodesZAND markSignature nodeL l Is used for the correlation of the data in the database,nfor the number of travel preference nodes,pfor the number of date tag nodes, QIndicating the trip recommendation type.
2. The method of claim 1, wherein the determining a target city trip based on the travel days, the departure city, the approach city, and the arrival city based on the pre-constructed travel knowledge graph comprises:
determining the shortest journey of all the passing cities as an initial city journey based on the pre-constructed travel knowledge graph;
and determining a target city journey based on the pre-constructed travel knowledge graph according to the travel days, the initial city journey, the breadth-first traversal algorithm and a preset first traversal constraint condition, wherein the target city journey at least comprises a departure city, a passing city and an arrival city.
3. The method of claim 2, wherein the predetermined first traversal constraint corresponds to a formula:
sum(J i )+k-i+1<D；
wherein J is i For the current city and the last city J i-1 Degree of connectivity between them, sum (J) i ) In order to reach the total connectivity of the current city from the departure city, k is the number of passing cities, i represents the serial number of the current city, and D is the travel days.
4. The method of claim 1, wherein determining a trip recommended route based on the pre-constructed travel knowledge graph according to a node recommendation score corresponding to each of the trip nodes, and pushing the trip recommended route to the user, comprises:
Determining a travel candidate route corresponding to each city node in the target city travel based on the pre-constructed travel knowledge graph according to the travel node, the depth-first traversal algorithm and a preset second traversal constraint condition associated with the city node;
for each route candidate route, determining a route recommendation score of the route candidate route according to the number of route nodes in the route candidate route, the node recommendation score corresponding to each route node and driving time consumption between two adjacent route nodes;
and determining the route candidate route with the highest first preset number of route recommendation scores as the route recommendation route according to the sequence from high to low, and pushing the route recommendation route to the user.
5. The method of claim 4, wherein the predetermined second traversal constraint corresponds to a formula:
wherein,,t end for a preset end-of-travel time,tfor the preset current time period to be set,pfor a preset starting trip node for the day,cis a preset termination journey node for the current day,s 1 for the 1 st trip node to play on the day, s i For playing on the same dayiThe number of travel nodes is one,T(p, s 1 )from p tos 1 Is time-consuming in the driving course of the vehicle,T(s j , c)is the slaves j The trip to c is time consuming,T(s i , s i+1 )is the slaves i To the point ofs i+1 Is time-consuming in driving process, w%s 1 ) Is a journey nodes 1 Recommended play time, w #s i ) Is a journey nodes i Recommended play time, w #s j ) Is a journey nodes j Is a recommended play time for (a).
6. The method according to claim 4, wherein, for each route candidate, the formula for determining the route recommendation score of the route candidate route according to the number of route nodes in the route candidate route, the node recommendation score corresponding to each route node, and the driving time between two preset adjacent route nodes is:
wherein,,Tas a route candidate for the journey,S(T)a route recommendation score for the route candidate route of the route,S(X i )candidate routes for journeyTMiddle (f)iThe nodes of the individual trip nodes recommend scores,scandidate routes for journeyTIs a function of the number of travel nodes in the network,t(X i ，X i-1 )for a predetermined travel nodeXiWith adjacent travel nodesX i-1 Is time-consuming in minutes.
7. The method according to claim 1, wherein the method further comprises:
adding month label nodes and holiday label nodes in an initial travel knowledge graph, establishing a two-way relation between adjacent month label nodes, and establishing a two-way relation between the month label nodes and the holiday label nodes;
Adding travel preference nodes into the initial travel knowledge graph;
adding city nodes and city attribute information into the initial travel knowledge graph;
adding travel nodes and travel attribute information into the initial travel knowledge graph, and establishing an association relationship between city nodes and travel nodes;
in the initial travel knowledge graph, aiming at each travel route corresponding to each city node in each history travel of a user, taking the city node as a starting point, sequentially acquiring each travel node in the travel route, establishing an association relationship of adjacent travel nodes, and adding a history travel number and a travel time for the association relationship;
in the initial travel knowledge graph, establishing an association relationship between each historical travel and travel preference nodes, and establishing an association relationship between a first travel corresponding to each daily travel in each historical travel and travel preference nodes;
in the initial travel knowledge graph, acquiring the visit date of each travel node in a travel route aiming at each travel route of each city node in each history travel of a user, and establishing the association relationship between a month label node and a holiday label node corresponding to the visit date and the travel node;
In the initial travel knowledge graph, for each history journey of the user, if the number of passing cities in the history journey is greater than 1, establishing an association relationship between the history journey and the passing cities in the history journey.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310361854.1A CN116089730B (en) | 2023-04-07 | 2023-04-07 | Travel route recommending method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310361854.1A CN116089730B (en) | 2023-04-07 | 2023-04-07 | Travel route recommending method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116089730A CN116089730A (en) | 2023-05-09 |
| CN116089730B true CN116089730B (en) | 2023-06-30 |
Family
ID=86210488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310361854.1A Active CN116089730B (en) | 2023-04-07 | 2023-04-07 | Travel route recommending method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116089730B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955535A (en) * | 2014-05-14 | 2014-07-30 | 南京大学镇江高新技术研究院 | Individualized recommending method and system based on element path |
| WO2017222585A1 (en) * | 2016-06-22 | 2017-12-28 | Google Llc | Systems and methods for providing contextual information |
| CN109977283A (en) * | 2019-03-14 | 2019-07-05 | 中国人民大学 | A kind of the tourism recommended method and system of knowledge based map and user's footprint |
| CN113886605A (en) * | 2021-10-25 | 2022-01-04 | 支付宝(杭州)信息技术有限公司 | Knowledge graph processing method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170124497A1 (en) * | 2015-10-28 | 2017-05-04 | Fractal Industries, Inc. | System for automated capture and analysis of business information for reliable business venture outcome prediction |
-
2023
- 2023-04-07 CN CN202310361854.1A patent/CN116089730B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955535A (en) * | 2014-05-14 | 2014-07-30 | 南京大学镇江高新技术研究院 | Individualized recommending method and system based on element path |
| WO2017222585A1 (en) * | 2016-06-22 | 2017-12-28 | Google Llc | Systems and methods for providing contextual information |
| CN109977283A (en) * | 2019-03-14 | 2019-07-05 | 中国人民大学 | A kind of the tourism recommended method and system of knowledge based map and user's footprint |
| CN113886605A (en) * | 2021-10-25 | 2022-01-04 | 支付宝(杭州)信息技术有限公司 | Knowledge graph processing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116089730A (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rodríguez et al. | Interactive design of personalised tourism routes | |
| Campos-Soria et al. | Understanding tourists' economizing strategies during the global economic crisis | |
| JP7264357B2 (en) | Method and Apparatus for Searching or Comparing Sites Using Routes or Route Distances Between Sites and Locations in a Transportation System | |
| Guizzardi et al. | Big data from dynamic pricing: A smart approach to tourism demand forecasting | |
| Bosurgi et al. | A model based on artificial neural networks and genetic algorithms for pavement maintenance management | |
| CN104391853A (en) | POI (point of interest) recommending method, POI information processing method and server | |
| Dogan et al. | Urbano: A tool to promote active mobility modeling and amenity analysis in urban design | |
| CN111539764B (en) | Big data multiple access selection method based on submodular function | |
| JP7144818B2 (en) | Method and Apparatus for Searching or Comparing Sites Using Routes or Route Distances Between Sites and Locations in a Transportation System | |
| CN109509039A (en) | Method for building up and system, the Method of Commodity Recommendation and system of price expectation model | |
| US20200012972A1 (en) | System and method for determining validity of web content | |
| Kim et al. | Determinants of housing prices in Hong Kong: A Box-Cox quantile regression approach | |
| Abildtrup et al. | Combining RP and SP data while accounting for large choice sets and travel mode–an application to forest recreation | |
| KR20210073819A (en) | Method and server for recommending personalized real estate information using the consumer choice model | |
| Wang et al. | Combined multinomial logit modal split and paired combinatorial logit traffic assignment model | |
| Hadiwijaya et al. | The decision model for selection of tourism site using analytic network process method | |
| Bera et al. | Estimation of spatial association between housing price and local environmental amenities in Kolkata, India Using Hedonic Local Regression | |
| CN112488419A (en) | Passenger flow distribution prediction method, device, equipment and storage medium based on OD analysis | |
| Hortas-Rico et al. | Expansionary zoning and the strategic behaviour of local governments | |
| CN116089730B (en) | Travel route recommending method | |
| TW201729154A (en) | Method and apparatus for identifying a target geographic area | |
| Kryvobokov | Is it worth identifying service employment (sub) centres when modelling apartment prices? | |
| CN115640756A (en) | Parking demand prediction model and method based on multi-source data and application thereof | |
| Montero-Lorenzo et al. | Space-time approach to commercial property prices valuation | |
| Foti | A behavioral framework for measuring walkability and its impact on home values and residential location choices |
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 |