CN109903191B - Travel recommendation method and device based on machine learning, storage medium and terminal - Google Patents
Travel recommendation method and device based on machine learning, storage medium and terminal Download PDFInfo
- Publication number
- CN109903191B CN109903191B CN201910007983.4A CN201910007983A CN109903191B CN 109903191 B CN109903191 B CN 109903191B CN 201910007983 A CN201910007983 A CN 201910007983A CN 109903191 B CN109903191 B CN 109903191B
- Authority
- CN
- China
- Prior art keywords
- user
- travel
- destination
- travel destination
- degree
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of computers, and particularly relates to a travel recommendation method and device based on machine learning, a computer readable storage medium and a server. The method receives a travel recommendation request sent by terminal equipment and extracts an identity of a user from the travel recommendation request; inquiring user information corresponding to the user identifier, and acquiring browsing record data of the user; extracting travel destinations in the browsing record data, and respectively calculating the attention degree of the user to each travel destination according to the browsing record data; respectively constructing evaluation vectors of all the travel destinations according to the user information and the attention degree of the user to all the travel destinations; respectively inputting the evaluation vectors of all the travel destinations into a preset machine learning model for processing to obtain the association degree between the user and each travel destination; and sending the travel destination with the highest degree of association with the user to the terminal equipment as a recommended object.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a travel recommendation method and device based on machine learning, a computer readable storage medium and a server.
Background
Currently, when a travel destination is recommended to a user, an application program related to travel is generally completed by a professional customization operator of a travel agency through manual work, and firstly, the customization operator needs to know a great amount of travel information and information, so that the characteristics of various places are very known; secondly, the subscriber needs to spend a lot of time to communicate with the user and recommend a suitable travel destination for the user according to the communication result, and the method needs to spend a lot of manpower resources with very low efficiency.
Disclosure of Invention
In view of the above, the embodiments of the present invention provide a travel recommendation method, device, computer readable storage medium and server based on machine learning, so as to solve the problems of high manpower resource consumption and low efficiency of the existing travel recommendation method.
A first aspect of an embodiment of the present invention provides a travel recommendation method based on machine learning, which may include:
receiving a travel recommendation request sent by a terminal device, and extracting an identity of a user from the travel recommendation request;
inquiring user information corresponding to the user identification in a preset database, and acquiring browsing record data of the user from a server of each preset travel website according to the identification;
extracting each travel destination in the browsing record data, and respectively calculating the attention degree of the user to each travel destination according to the browsing record data;
respectively constructing evaluation vectors of all the travel destinations according to the user information and the attention degree of the user to all the travel destinations;
respectively inputting the evaluation vectors of all the travel destinations into a preset machine learning model for processing to obtain the association degree between the user and each travel destination;
and sending the travel destination with the highest degree of association with the user to the terminal equipment as a recommended object.
A second aspect of an embodiment of the present invention provides a travel recommendation device based on machine learning, which may include:
the travel recommendation request receiving module is used for receiving a travel recommendation request sent by the terminal equipment and extracting an identity of a user from the travel recommendation request;
the user data acquisition module is used for inquiring user information corresponding to the user identification in a preset database and acquiring browsing record data of the user from a preset server of each travel website according to the identity identification;
the attention degree calculation module is used for extracting each travel destination in the browsing record data and calculating the attention degree of the user on each travel destination according to the browsing record data;
the evaluation vector construction module is used for respectively constructing evaluation vectors of all the travel destinations according to the user information and the attention of the user to all the travel destinations;
the model processing module is used for respectively inputting the evaluation vectors of all the travel destinations into a preset machine learning model for processing to obtain the association degree between the user and each travel destination;
and the travel recommendation module is used for sending the travel destination with the highest association degree with the user to the terminal equipment as a recommendation object.
A third aspect of embodiments of the present invention provides a computer readable storage medium storing computer readable instructions which when executed by a processor perform the steps of:
receiving a travel recommendation request sent by a terminal device, and extracting an identity of a user from the travel recommendation request;
inquiring user information corresponding to the user identification in a preset database, and acquiring browsing record data of the user from a server of each preset travel website according to the identification;
extracting each travel destination in the browsing record data, and respectively calculating the attention degree of the user to each travel destination according to the browsing record data;
respectively constructing evaluation vectors of all the travel destinations according to the user information and the attention degree of the user to all the travel destinations;
respectively inputting the evaluation vectors of all the travel destinations into a preset machine learning model for processing to obtain the association degree between the user and each travel destination;
and sending the travel destination with the highest degree of association with the user to the terminal equipment as a recommended object.
A fourth aspect of the embodiments of the present invention provides a server comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, the processor executing the computer readable instructions to perform the steps of:
receiving a travel recommendation request sent by a terminal device, and extracting an identity of a user from the travel recommendation request;
inquiring user information corresponding to the user identification in a preset database, and acquiring browsing record data of the user from a server of each preset travel website according to the identification;
extracting each travel destination in the browsing record data, and respectively calculating the attention degree of the user to each travel destination according to the browsing record data;
respectively constructing evaluation vectors of all the travel destinations according to the user information and the attention degree of the user to all the travel destinations;
respectively inputting the evaluation vectors of all the travel destinations into a preset machine learning model for processing to obtain the association degree between the user and each travel destination;
and sending the travel destination with the highest degree of association with the user to the terminal equipment as a recommended object.
Compared with the prior art, the embodiment of the invention has the beneficial effects that: after a travel recommendation request sent by a user through a terminal device is received, user information corresponding to the user identification is automatically queried in a preset database according to an identification mark extracted from the travel recommendation request, browsing record data of the user are obtained from a server of each preset travel website according to the identification mark, each travel destination in the browsing record data is extracted, the attention degree of the user to each travel destination is calculated according to the browsing record data, evaluation vectors of each travel destination are respectively constructed according to the user information and the attention degree of the user to each travel destination, the evaluation vectors of each travel destination are respectively input into a preset machine learning model for processing, the association degree between the user and each travel destination is obtained, and finally the travel destination with the highest association degree with the user is used as a recommendation object to be sent to the terminal device. According to the embodiment of the invention, the collection of the information related to the user is completed in an automatic mode, and the information is intelligently analyzed through the machine learning model, so that a proper travel destination is recommended for the user, the consumption of human resources is reduced, and the efficiency is greatly improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of one embodiment of a machine learning based travel recommendation method in accordance with an embodiment of the present invention;
FIG. 2 is a schematic flow chart of acquiring browsing record data of a user from a preset server of each travel website according to an identity;
FIG. 3 is a block diagram of one embodiment of a travel recommendation device in accordance with an embodiment of the present invention;
fig. 4 is a schematic block diagram of a server according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more comprehensible, the technical solutions in the embodiments of the present invention are described in detail below with reference to the accompanying drawings, and it is apparent that the embodiments described below are only some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an embodiment of a travel recommendation method based on machine learning according to an embodiment of the present invention may include:
step S101, a travel recommendation request sent by a terminal device is received, and an identity of a user is extracted from the travel recommendation request.
In this embodiment, the terminal device of the user monitors the operation behavior of the user in real time, and when it is monitored that the user performs an operation related to travel, it is determined that the user may have an intention of traveling, and the terminal device sends a travel recommendation request to a designated server for managing travel. The travel-related operations include, but are not limited to: searching for travel related web pages, browsing travel related web pages or pushing information, opening travel related applications, and the like.
The travel recommendation request includes an identity of the user, including but not limited to an identification of the user that may uniquely characterize the user, an identification of the user, a social security number, a mobile phone number, and the like. And after receiving the travel recommendation request, the travel management server can extract the identity of the user from the travel recommendation request.
Step S102, inquiring user information corresponding to the user identification in a preset database, and acquiring browsing record data of the user from a preset server of each travel website according to the identity identification.
The travel management server may query the database for user information corresponding to the user identification including, but not limited to, personal base data of the user's age, gender, occupation, educational level, income level, health status, and the like.
The travel management server can also acquire the browsing record data of the user from the preset servers of all the travel websites according to the identity. The travel websites can be set according to actual conditions, for example, a plurality of travel websites with higher awareness degree can be selected as analysis objects, the number of the selected travel websites is denoted as WN, and the travel websites are numbered according to serial numbers of 1, 2, 3, …, WN, … and WN, wherein, the number of the travel websites is equal to or more than 1 and equal to or less than WN.
As shown in fig. 2, the process of acquiring browsing record data of the user from a preset server of each travel website may specifically include:
step S1021, a data authorization request is sent to the terminal equipment.
The data authorization request includes an identification of the wnth travel website, where the identification of the travel website includes, but is not limited to, a uniform resource locator (Uniform Resource Locator, URL) of the travel website, a chinese name (including full name or abbreviation), an english name (including full name or abbreviation), and so on.
Step S1022, receiving feedback information of the terminal device.
After receiving the data authorization request sent by the travel management server, the terminal equipment can inquire whether to carry out data authorization on the travel management server for the user through a specified man-machine interaction interface, if the user confirms, confirmation authorization information is sent to the travel management server, the confirmation authorization information carries the digital signature of the user, and if the user refuses, refuses authorization information is sent to the travel management server.
After receiving the feedback information of the terminal device, the travel management server first judges whether the feedback information is confirmation authorization information or rejection authorization information, if the feedback information is rejection authorization information, the travel management server does not acquire the browsing record data of the user from the server of the wnth travel website any more, and if the feedback information is confirmation authorization information, step S1023 and subsequent steps are executed.
Step S1023, sending a data query request to a server of the wnth travel website.
The data query request comprises the confirmation authorization information so as to inform the server of the wnth travel website that the data query request is authorized by the user.
And step S1024, receiving browsing record data of the user on the down-th travel website, which is sent by the server of the down-th travel website.
And after receiving the data query request, the server of the wnth travel website extracts the digital signature of the user from the confirmation authorization information and verifies the digital signature. And if the verification is successful, transmitting browsing record data of the user on the wnth travel website to the travel management server.
Through the process shown in fig. 2, the travel management server may acquire the browsing record data of the user from the servers of the respective travel websites, respectively.
And step 103, extracting each travel destination in the browsing record data, and respectively calculating the attention degree of the user to each travel destination according to the browsing record data.
In the specific process of calculating the attention degree of the user to each travel destination, the travel management server may first count the browsing times and browsing time duration of each travel destination of the user according to the browsing record data, and then calculate the attention degree of the user to each travel destination according to the following formula:
wherein dn is the serial number of each travel destination, dn is 1-1 DesNum, desNum is the number of travel destinations extracted from the browsing record data, BN is the serial number of each browsing action of the user, and BN is 1-BN wn,dn ，BN wn,dn Browsing time for the number of views of the dn's travel destination on the wnth travel website by the user wn,dn,bn WebWeight for the length of browsing the user on the wnth travel website for the bn th travel destination wn FocDeg is the weighting coefficient of the wnth travel website dn And (5) focusing on the dn-th travel destination for the user.
The setting process of the weight coefficient specifically comprises the following steps: firstly, respectively acquiring the registered user quantity and daily access quantity of each travel website, and then calculating the weight coefficient of each travel website according to the following formula:
wherein, userNum wn VisNumPerday for the amount of registered users of the wnth travel website wn For the daily access quantity of the wnth travel website, lambda is a preset coefficient, lambda is more than or equal to 0 and less than or equal to 1, and the specific value of lambda can be set according to the actual situation, for example, 0.2, 0.3, 0.5, 0.8 or other values can be set.
And step S104, respectively constructing evaluation vectors of all the travel destinations according to the user information and the attention degree of the user to all the travel destinations.
Each travel destination corresponds to an evaluation vector, and the evaluation vector comprises the user information and the attention degree of the user to the travel destination.
Step 105, the evaluation vectors of the travel destinations are respectively input into a preset machine learning model for processing, and the association degree between the user and each travel destination is obtained.
The machine learning model is a model which is trained by a large number of samples in advance and has the accuracy reaching the expected requirement, and the specific training process can comprise the following steps:
(1) And constructing a sample library according to the statistical data of the historical users.
Each sample includes two parts, one part is an evaluation vector of the historical user, namely, the input of the model, the specific construction process of the evaluation vector is similar to that described above, and the other part is the degree of association between the historical user and a certain travel destination, namely, the expected output of the model (note that the expected output is not the actual output).
The degree of association between a historical user and a travel destination may be expressed in terms of the number of times the user actually goes to the travel destination within a certain statistical period (e.g., 3 years, 5 years, 8 years, etc.).
After the sample library is constructed, the samples in the sample library can be further segmented into two sets, namely a training sample set and a test sample set.
(2) And (5) machine learning modeling.
The modeling can be performed based on various existing machine learning algorithms in this embodiment, and the parameters of the model are trained using samples in the training sample set.
The machine learning algorithm used in this embodiment includes, but is not limited to, decision trees, SVMs, KNNs, etc. specific algorithms.
(3) And (5) evaluating model accuracy.
The machine learning model is used for further processing the characteristic data in the test sample set, expected output values and actual output values of all samples in the test sample set are compared, if the expected output values and the actual output values are close to each other, the accuracy of the model is higher, otherwise, the accuracy of the model is lower.
If the accuracy of the model is greater than a preset threshold, the model can be considered to have the use condition, the current user can be evaluated by using the model, and if the accuracy of the model is less than the threshold, the subsequent adjustment process is further executed.
(4) And (5) model adjustment.
When the accuracy of the model is lower, the parameters of the model can be properly adjusted until the accuracy reaches the standard, and if the calculated result still has great difference with the result on the test set after the model parameters are adjusted for many times, the screening of the characteristic data can be tried again, and the model can be re-used until the accuracy reaches the standard.
After the machine learning model is built, the evaluation vectors of the travel destinations can be respectively input into a preset machine learning model for processing, so that the association degree between the user and each travel destination is obtained.
And step S106, the travel destination with the highest degree of association with the user is sent to the terminal equipment as a recommended object.
Further, the present embodiment may also take into account the user's social networking data on the basis of the process shown in fig. 1. Specifically, after obtaining the association degree between the user and each travel destination, the travel management server may obtain network social data of the user, and extract each friend of the user from the network social data, where the friend is another user who has interacted with the user.
Then, the travel management server may respectively count interaction frequencies between the user and each friend according to the network social data, and respectively calculate influence weights of each friend on the user according to the following formula:
wherein FN is the serial number of each friend, FN is more than or equal to 1 and less than or equal to FN, FN is the number of friends of the user, and ContactNum fn FriendWeight is the frequency of interaction between the user and the fn-th friend fn And the influence weight of the fn-th friend on the user is given.
Finally, the travel management server may adjust the degree of association between the user and each travel destination according to the following equation:
wherein, friendAsso fn,dn As for the association degree between the fn-th friend and the dn-th travel destination of the user, the specific calculation method of the association degree is the same as the foregoing process, and the foregoing may be referred to for specific details, which are not repeated herein. Association of dn For the association degree between the user and the dn't travel destination, ω is a preset coefficient, and 0 is equal to or less than ω is equal to or less than 1, and the specific value thereof may be set according to the actual situation, for example, may be set to 0.2, 0.3, 0.5, 0.8 or other values. EditedAsso dn For the adjusted degree of association between the user and the dn't travel destination. In this case, the travel management server will follow the callAnd selecting a recommended object according to the whole association degree, namely sending the travel destination with the highest association degree after adjustment with the user to the terminal equipment as the recommended object.
Further, considering that the structure of the whole database is very complex under the condition that the number of users, the tourist destinations and the friend relations are large, if the traditional relational database, the key-value nosql database and the like are used for processing, the processing efficiency is very low, so that the problem of the application scene is solved by using the graph database with stronger relation as the storage based on the background. The graph database is a database service that can store billions of relationships and can perform graph queries and stores with millisecond delays. The highly interconnected data sets can be easily constructed and run, supporting real-time updates to large graphics data, while supporting queries.
The graph databases also have flexible schema modification, users can continuously add or delete new vertexes, edges and attributes, and expand or shrink data models, which is particularly convenient for managing continuously changing object types, and most graph databases can modify schema online, simultaneously continue to provide queries, nodes can be updated independently and in real time, and the overall operation of the system is prevented from being influenced. For example, when a certain travel business is changed to cause deviation of user behavior data, the model can be retrained by independently extracting the data of the corresponding vertexes, and the accuracy of the overall calculation cannot be affected. In addition, an inherent index data structure is provided so that it does not need to load or contact irrelevant data for a query for a given condition.
In summary, after receiving a travel recommendation request sent by a user through a terminal device, the embodiment of the invention automatically queries user information corresponding to the user identifier in a preset database according to the identity identifier extracted from the travel recommendation request, acquires browsing record data of the user from a server of each preset travel website according to the identity identifier, extracts each travel destination in the browsing record data, calculates attention of the user to each travel destination according to the browsing record data, respectively constructs evaluation vectors of each travel destination according to the user information and the attention of the user to each travel destination, respectively inputs the evaluation vectors of each travel destination into a preset machine learning model for processing, obtains the association degree between the user and each travel destination, and finally sends the travel destination with the highest association degree with the user as a recommendation object to the terminal device. According to the embodiment of the invention, the collection of the information related to the user is completed in an automatic mode, and the information is intelligently analyzed through the machine learning model, so that a proper travel destination is recommended for the user, the consumption of human resources is reduced, and the efficiency is greatly improved.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
Corresponding to the travel recommendation method based on machine learning described in the above embodiments, fig. 3 shows a block diagram of an embodiment of a travel recommendation device according to an embodiment of the present invention.
In this embodiment, a travel recommendation device may include:
a travel recommendation request receiving module 301, configured to receive a travel recommendation request sent by a terminal device, and extract an identity of a user from the travel recommendation request;
the user data acquisition module 302 is configured to query a preset database for user information corresponding to the user identifier, and acquire browsing record data of the user from a preset server of each travel website according to the identity identifier;
a degree of interest calculation module 303, configured to extract each travel destination in the browsing record data, and calculate the degree of interest of the user on each travel destination according to the browsing record data;
an evaluation vector construction module 304, configured to construct an evaluation vector of each travel destination according to the user information and the attention of the user to each travel destination;
the model processing module 305 is configured to input the evaluation vectors of the travel destinations into a preset machine learning model for processing, so as to obtain a degree of association between the user and each travel destination;
and the travel recommendation module 306 is configured to send a travel destination with the highest association degree with the user to the terminal device as a recommendation object.
Further, the user data acquisition module may include:
a data authorization request sending unit, configured to send a data authorization request to the terminal device, where the data authorization request includes an identifier of a wnth travel website, WN is greater than or equal to 1 and less than or equal to WN, and WN is the number of travel websites;
the feedback information receiving unit is used for receiving feedback information of the terminal equipment;
the data query request sending unit is used for sending a data query request to a server of a down-th travel website if the feedback information is confirmation authorization information, wherein the data query request comprises the confirmation authorization information;
and the browse record data receiving unit is used for receiving the browse record data of the user on the down-th travel website, which is sent by the server of the down-th travel website.
Further, the attention calculating module may include:
the browsing data statistics unit is used for respectively counting the browsing times of the user to each travel destination and the browsing duration of each time according to the browsing record data;
a degree of interest calculation unit configured to calculate the degree of interest of the user for each travel destination, respectively, according to the following formula:
wherein dn is the serial number of each travel destination, and dn is more than or equal to 1 and less than or equal to DesNum, desNum is the number of travel destinations extracted from the browsing record data, BN is the sequence number of each browsing action of the user, 1.ltoreq.bn.ltoreq.BN wn,dn ，BN wn,dn Browsing time for the number of views of the dn's travel destination on the wnth travel website by the user wn,dn,bn WebWeight for the length of browsing the user on the wnth travel website for the bn th travel destination wn FocDeg is the weighting coefficient of the wnth travel website dn And (5) focusing on the dn-th travel destination for the user.
Further, the travel recommendation device may further include:
the website data acquisition module is used for respectively acquiring the registered user quantity and daily access quantity of each travel website;
the weight coefficient calculation module is used for calculating the weight coefficient of each travel website according to the following formula:
wherein, userNum wn VisNumPerday for the amount of registered users of the wnth travel website wn And lambda is a preset coefficient for the daily visit amount of the wnth travel website, and lambda is more than or equal to 0 and less than or equal to 1.
Further, the travel recommendation device may further include:
the network social data acquisition module is used for acquiring network social data of the user and extracting all friends of the user from the network social data, wherein the friends are other users interacted with the user;
the interaction frequency statistics module is used for respectively counting the interaction frequency between the user and each friend according to the network social data;
the influence weight calculation module is used for calculating the influence weight of each friend on the user according to the following formula:
wherein FN is the serial number of each friend, FN is more than or equal to 1 and less than or equal to FN, FN is the number of friends of the user, and ContactNum fn FriendWeight is the frequency of interaction between the user and the fn-th friend fn The influence weight of the fn-th friend on the user is given;
the association degree adjusting module is used for adjusting the association degree between the user and each travel destination according to the following formula:
wherein, friendAsso fn,dn Association for Association between the user's fn-th friend and dn-th travel destination dn For the relevance between the user and the dn't travel destination, omega is a preset coefficient, and 0.ltoreq.ω.ltoreq.1, editedasso dn For the adjusted degree of association between the user and the dn't travel destination.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described apparatus, modules and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Fig. 4 shows a schematic block diagram of a server according to an embodiment of the present invention, and for convenience of explanation, only a portion related to the embodiment of the present invention is shown.
In this embodiment, the server 4 is the travel management server in the above embodiment of the method, and the server may include: a processor 40, a memory 41, and computer readable instructions 42 stored in the memory 41 and executable on the processor 40, such as computer readable instructions for performing the trip recommendation method described above. The processor 40, when executing the computer readable instructions 42, implements the steps of the various travel recommendation method embodiments described above, such as steps S101 through S106 shown in fig. 1. Alternatively, the processor 40, when executing the computer readable instructions 42, performs the functions of the modules/units of the apparatus embodiments described above, such as the functions of modules 301 through 306 shown in fig. 3.
Illustratively, the computer readable instructions 42 may be partitioned into one or more modules/units that are stored in the memory 41 and executed by the processor 40 to complete the present invention. The one or more modules/units may be a series of computer readable instructions capable of performing a particular function describing the execution of the computer readable instructions 42 in the server 4.
The processor 40 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), field programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 41 may be an internal storage unit of the server 4, such as a hard disk or a memory of the server 4. The memory 41 may be an external storage device of the server 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the server 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the server 4. The memory 41 is used to store the computer readable instructions as well as other instructions and data required by the server 4. The memory 41 may also be used for temporarily storing data that has been output or is to be output.
The functional units in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution contributing to the prior art or in the form of a software product stored in a storage medium, comprising a number of computer readable instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing computer readable instructions.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A machine learning based travel recommendation method, comprising:
receiving a travel recommendation request sent by a terminal device, and extracting an identity of a user from the travel recommendation request;
inquiring user information corresponding to the user identification in a preset database, and acquiring browsing record data of the user from a server of each preset travel website according to the identification;
extracting each travel destination in the browsing record data, and respectively calculating the attention degree of the user to each travel destination according to the browsing record data;
respectively constructing evaluation vectors of all the travel destinations according to the user information and the attention degree of the user to all the travel destinations;
respectively inputting the evaluation vectors of all the travel destinations into a preset machine learning model for processing to obtain the association degree between the user and each travel destination;
acquiring network social data of the user, and extracting all friends of the user from the network social data, wherein the friends are other users interacted with the user; respectively counting interaction frequencies between the user and each friend according to the network social data; according to the interaction frequency between the user and each friend, influence weights of each friend on the user are calculated respectively; the degree of association between the user and each travel destination is adjusted according to the following formula:
wherein dn is the serial number of each travel destination, FN is the serial number of each friend, FN is more than or equal to 1 and less than or equal to FN, FN is the friend number of the user, and FriendWeight fn The FriendAsso is the influence weight of the fn-th friend on the user fn,dn Association for Association between the user's fn-th friend and dn-th travel destination dn For the relevance between the user and the dn't travel destination, omega is a preset coefficient, and 0.ltoreq.ω.ltoreq.1, editedasso dn For the adjusted degree of association between the user and the dn't travel destination;
and sending the travel destination with the highest degree of association with the user to the terminal equipment as a recommended object.
2. The travel recommendation method according to claim 1, wherein the obtaining, according to the identity, the browsing record data of the user from a server of each preset travel website includes:
transmitting a data authorization request to the terminal equipment, wherein the data authorization request comprises the identification of the wnth travel website, WN is more than or equal to 1 and less than or equal to WN, and WN is the number of the travel websites;
receiving feedback information of the terminal equipment, and if the feedback information is confirmation authorization information, sending a data query request to a server of a wnth travel website, wherein the data query request comprises the confirmation authorization information;
and receiving browsing record data of the user on the down-th travel website, which is sent by the server of the down-th travel website.
3. The travel recommendation method according to claim 1, wherein the calculating the user's degree of attention to each travel destination from the browsing record data includes:
respectively counting the browsing times of the user to each travel destination according to the browsing record data;
and respectively calculating the attention degree of the user to each travel destination according to the following formula:
wherein dn is more than or equal to 1 and is less than or equal to DesNum, desNum is the number of travel destinations extracted from the browsing record data, BN is the serial number of each browsing action of the user, and BN is more than or equal to 1 and is less than or equal to BN wn,dn ，BN wn,dn Browsing time for the number of views of the dn's travel destination on the wnth travel website by the user wn,dn,bn Browsing the dn' th travel destination on the wnth travel website for the userDuration, webWeight wn FocDeg is the weighting coefficient of the wnth travel website dn And (5) focusing on the dn-th travel destination for the user.
4. The travel recommendation method according to claim 3, wherein the setting process of the weight coefficient comprises:
the method comprises the steps of respectively obtaining registered user quantity and daily access quantity of each travel website;
calculating the weight coefficient of each travel website according to the following formula:
wherein, userNum wn VisNumPerday for the amount of registered users of the wnth travel website wn And lambda is a preset coefficient for the daily visit amount of the wnth travel website, and lambda is more than or equal to 0 and less than or equal to 1.
5. The travel recommendation method according to claim 1, wherein the calculating the influence weights of the friends on the user according to the interaction frequency between the user and the friends respectively comprises:
and respectively calculating the influence weights of the friends on the user according to the following steps:
wherein, contactNum fn And the interaction frequency between the user and the fn-th friend is the interaction frequency.
6. A travel recommendation device, comprising:
the travel recommendation request receiving module is used for receiving a travel recommendation request sent by the terminal equipment and extracting an identity of a user from the travel recommendation request;
the user data acquisition module is used for inquiring user information corresponding to the user identification in a preset database and acquiring browsing record data of the user from a preset server of each travel website according to the identity identification;
the attention degree calculation module is used for extracting each travel destination in the browsing record data and calculating the attention degree of the user on each travel destination according to the browsing record data;
the evaluation vector construction module is used for respectively constructing evaluation vectors of all the travel destinations according to the user information and the attention of the user to all the travel destinations;
the model processing module is used for respectively inputting the evaluation vectors of all the travel destinations into a preset machine learning model for processing to obtain the association degree between the user and each travel destination;
the network social data acquisition module is used for acquiring network social data of the user and extracting all friends of the user from the network social data, wherein the friends are other users interacted with the user;
the interaction frequency statistics module is used for respectively counting the interaction frequency between the user and each friend according to the network social data;
the influence weight calculation module is used for calculating the influence weight of each friend on the user according to the interaction frequency between the user and each friend;
the association degree adjusting module is used for adjusting the association degree between the user and each travel destination according to the following formula:
wherein dn is the serial number of each travel destination, FN is the serial number of each friend, FN is more than or equal to 1 and less than or equal to FN, FN is the friend number of the user, and FriendWeight fn The FriendAsso is the influence weight of the fn-th friend on the user fn,dn Is saidAssociation between the user's fn-th friend and dn-th travel destination dn For the relevance between the user and the dn't travel destination, omega is a preset coefficient, and 0.ltoreq.ω.ltoreq.1, editedasso dn For the adjusted degree of association between the user and the dn't travel destination;
and the travel recommendation module is used for sending the travel destination with the highest association degree with the user to the terminal equipment as a recommendation object.
7. The travel recommendation device of claim 6, wherein the attention calculation module comprises:
the browsing data statistics unit is used for respectively counting the browsing times of the user to each travel destination and the browsing duration of each time according to the browsing record data;
a degree of interest calculation unit configured to calculate the degree of interest of the user for each travel destination, respectively, according to the following formula:
wherein dn is more than or equal to 1 and is less than or equal to DesNum, desNum is the number of travel destinations extracted from the browsing record data, BN is the serial number of each browsing action of the user, and BN is more than or equal to 1 and is less than or equal to BN wn,dn ，BN wn,dn Browsing time for the number of views of the dn's travel destination on the wnth travel website by the user wn,dn,bn WebWeight for the length of browsing the user on the wnth travel website for the bn th travel destination wn FocDeg is the weighting coefficient of the wnth travel website dn And (5) focusing on the dn-th travel destination for the user.
8. The travel recommendation device according to claim 6 or 7, wherein the impact weight calculation module is configured to calculate the impact weight of each friend on the user according to the following formula:
wherein, contactNum fn And the interaction frequency between the user and the fn-th friend is the interaction frequency.
9. A computer readable storage medium storing computer readable instructions which, when executed by a processor, implement the steps of the travel recommendation method of any one of claims 1 to 5.
10. A server comprising a memory, a processor and computer readable instructions stored in the memory and executable on the processor, wherein the processor, when executing the computer readable instructions, implements the steps of the travel recommendation method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910007983.4A CN109903191B (en) | 2019-01-04 | 2019-01-04 | Travel recommendation method and device based on machine learning, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910007983.4A CN109903191B (en) | 2019-01-04 | 2019-01-04 | Travel recommendation method and device based on machine learning, storage medium and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109903191A CN109903191A (en) | 2019-06-18 |
| CN109903191B true CN109903191B (en) | 2023-09-19 |
Family
ID=66943543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910007983.4A Active CN109903191B (en) | 2019-01-04 | 2019-01-04 | Travel recommendation method and device based on machine learning, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109903191B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751395B (en) * | 2019-10-21 | 2023-07-04 | 中国民航信息网络股份有限公司 | Passenger journey state determining method, device and server |
| CN111159545A (en) * | 2019-12-24 | 2020-05-15 | 贝壳技术有限公司 | Recommended house source determining method and device and house source recommending method and device |
| CN111274331A (en) * | 2020-01-15 | 2020-06-12 | 中国建设银行股份有限公司 | Relational data management maintenance system and method |
| CN111523944A (en) * | 2020-04-26 | 2020-08-11 | 北京深演智能科技股份有限公司 | Browsing data processing method and device, nonvolatile storage medium and processing |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385601A (en) * | 2010-09-03 | 2012-03-21 | 阿里巴巴集团控股有限公司 | Product information recommendation method and system |
| KR20130083703A (en) * | 2012-01-13 | 2013-07-23 | 경북대학교 산학협력단 | Apparatus and method for searching personalized contents of a traver destination based on user position log of a mobile terminal |
| KR101451153B1 (en) * | 2013-08-02 | 2014-10-16 | 충북대학교 산학협력단 | Location recommendation system and method for mobile users by moving trajectory analysis of companions |
| KR20170014464A (en) * | 2015-07-30 | 2017-02-08 | 주식회사 케이티 | Method, system and computer program for recommending travel site considering user's preference |
| KR20170107865A (en) * | 2016-03-16 | 2017-09-26 | 김진섭 | Personalized Tour Information System based on Big-data Technology |
| KR101871747B1 (en) * | 2017-04-07 | 2018-06-27 | 주식회사 화성 | Similarity tendency based user-sightseeing recommendation system and method thereof |
-
2019
- 2019-01-04 CN CN201910007983.4A patent/CN109903191B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385601A (en) * | 2010-09-03 | 2012-03-21 | 阿里巴巴集团控股有限公司 | Product information recommendation method and system |
| KR20130083703A (en) * | 2012-01-13 | 2013-07-23 | 경북대학교 산학협력단 | Apparatus and method for searching personalized contents of a traver destination based on user position log of a mobile terminal |
| KR101451153B1 (en) * | 2013-08-02 | 2014-10-16 | 충북대학교 산학협력단 | Location recommendation system and method for mobile users by moving trajectory analysis of companions |
| KR20170014464A (en) * | 2015-07-30 | 2017-02-08 | 주식회사 케이티 | Method, system and computer program for recommending travel site considering user's preference |
| KR20170107865A (en) * | 2016-03-16 | 2017-09-26 | 김진섭 | Personalized Tour Information System based on Big-data Technology |
| KR101871747B1 (en) * | 2017-04-07 | 2018-06-27 | 주식회사 화성 | Similarity tendency based user-sightseeing recommendation system and method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109903191A (en) | 2019-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109903191B (en) | Travel recommendation method and device based on machine learning, storage medium and terminal | |
| US20210329094A1 (en) | Discovering signature of electronic social networks | |
| US20170236073A1 (en) | Machine learned candidate selection on inverted indices | |
| CN105608179B (en) | The method and apparatus for determining the relevance of user identifier | |
| CN107862022B (en) | Culture resource recommendation system | |
| CN107784066A (en) | Information recommendation method, device, server and storage medium | |
| CN108399180B (en) | Knowledge graph construction method and device and server | |
| García-Escudero et al. | Avoiding spurious local maximizers in mixture modeling | |
| JP2010204966A (en) | Sampling device, sampling method, sampling program, class distinction device and class distinction system | |
| US11729286B2 (en) | Feature-based network embedding | |
| WO2016045567A1 (en) | Webpage data analysis method and device | |
| KR101450453B1 (en) | Method and apparatus for recommending contents | |
| CN107679239A (en) | Recommend method in a kind of personalized community based on user behavior | |
| CN113157922A (en) | Network entity behavior evaluation and visualization method based on graph | |
| WO2015165230A1 (en) | Social contact message monitoring method and device | |
| CN112269937B (en) | Method, system and device for calculating user similarity | |
| WO2023045378A1 (en) | Method and device for recommending item information to user, storage medium, and program product | |
| US9536199B1 (en) | Recommendations based on device usage | |
| CN103645889B (en) | Dynamic software self-adaption generating method | |
| CN114840742A (en) | User portrait construction device, method and computer readable medium | |
| Kpiebaareh et al. | User-connection behaviour analysis in service management using bipartite labelled property graph | |
| CN111191117A (en) | Accurate user interest detection method and system for government map service | |
| Wang et al. | Group behavior time series anomaly detection in specific network space based on separation degree | |
| KR20200036173A (en) | Method and apparatus for recommending user grouping and groupwise preferred machine learning analysis algorithms | |
| Xie | Research on Weibo user behavior system for subjective perception and big data mining technology |
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 |