CN110942334A - Leisure agriculture tourism recommendation method and system, electronic equipment and storage medium - Google Patents

Leisure agriculture tourism recommendation method and system, electronic equipment and storage medium Download PDF

Info

Publication number
CN110942334A
CN110942334A CN201910968979.4A CN201910968979A CN110942334A CN 110942334 A CN110942334 A CN 110942334A CN 201910968979 A CN201910968979 A CN 201910968979A CN 110942334 A CN110942334 A CN 110942334A
Authority
CN
China
Prior art keywords
user
scenic spot
information
rating
neural network
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.)
Pending
Application number
CN201910968979.4A
Other languages
Chinese (zh)
Inventor
高万林
郭超
贾敬敦
任延昭
何东彬
时爽
刘新亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Agricultural University
Original Assignee
China Agricultural University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Agricultural University filed Critical China Agricultural University
Priority to CN201910968979.4A priority Critical patent/CN110942334A/en
Publication of CN110942334A publication Critical patent/CN110942334A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0282—Rating or review of business operators or products
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Recommending goods or services
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Agronomy & Crop Science (AREA)
  • Animal Husbandry (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Mining & Mineral Resources (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本发明提供一种休闲农业旅游推荐方法、系统、电子设备及存储介质，方法包括：根据旅游网站上用户对景点的评分信息，用聚类法将信息中的用户划分为不同的群体，把群体的中心值作为未评分项目的填充值，利用相似群体的评分信息初步预测评分；将文本信息输入预先训练的深度合作神经网络，产生景点推荐策略；再通过采集用户当前城市、具有纬度和经度的用户位置、天气等情景感知信息，综合地理距离、天气情况来确定最终推荐列表。本发明采用聚类算法对用户进行聚类，填充未评分项，改善数据稀疏性问题，又通过文本挖掘提升休闲农业旅游推荐效果，最后采用情景感知信息进一步为游客提供个性化的推荐服务。

Figure 201910968979

The invention provides a leisure agricultural tourism recommendation method, system, electronic equipment and storage medium. The method includes: according to the user's rating information on the scenic spots on the tourism website, using a clustering method to divide the users in the information into different groups, and divide the groups into different groups. The central value of the unrated items is used as the filling value of the unrated items, and the rating information of similar groups is used to preliminarily predict the rating; input the text information into the pre-trained deep cooperative neural network to generate the scenic spot recommendation strategy; then collect the user's current city, latitude and longitude User location, weather and other situational awareness information, combined with geographic distance and weather conditions to determine the final recommendation list. The invention uses a clustering algorithm to cluster users, fills unscored items, improves the data sparsity problem, improves the recommendation effect of leisure agricultural tourism through text mining, and finally uses situational awareness information to further provide personalized recommendation services for tourists.

Figure 201910968979

Description

Leisure agriculture tourism recommendation method and system, electronic equipment and storage medium
Technical Field
The invention belongs to the technical field of leisure agriculture tourism, and particularly relates to a leisure agriculture tourism recommendation method, a system, electronic equipment and a storage medium.
Background
The leisure agriculture tourism is the rising in developed countries in Europe at first, is tourism activities such as tourism, appreciation, experience, leisure, tasting, shopping and the like before tourists are attracted by utilizing rural space and agricultural landscape, is a new industry for developing tourism products on the basis of agricultural resources and providing the tourists with combined services of agriculture and tourism, and is a typical characteristic of the leisure agriculture tourism.
With the increasing income of people, travel enriches the amateur life of the people and becomes a new life style of the people. Along with the acceleration of the urbanization process in China, attention is paid to ecological environment protection, and more people desire to return to nature. Many websites related to tourism are also produced on the internet, and tourists can score scenic spots, write tourism notes and the like on the websites to share the own tourism experience. The user can conveniently search the travel information through the network, and choose and purchase travel products and services, and enjoy the convenience brought by the information technology. However, the travel information of the leisure agriculture is relatively less, the problem of serious data sparsity exists, the influence of the appearance time, weather and other factors on the user is large, and the user is often difficult to select efficiently.
Therefore, an urgent need exists for an individualized recommendation method applicable to leisure agriculture tourism, which meets diversified and individualized requirements of tourists and provides individualized information service and decision support for customers.
Disclosure of Invention
To overcome the above-mentioned existing problems or to at least partially solve the above-mentioned problems, embodiments of the present invention provide a leisure agricultural tour recommendation method, system, electronic device, and storage medium.
According to a first aspect of the embodiments of the present invention, there is provided a travel recommendation method for leisure agriculture, including:
capturing relevant information of each sight spot from a tourism website, wherein the relevant information of the sight spots comprises comment information, rating information and sight spot text information of each user on the sight spots;
clustering the users according to the grading information of the users on the scenic spots to obtain user groups of various categories;
for the same user group, determining the scoring information of the user who does not score any scenic spot according to the known scoring information of the user in the user group on any scenic spot;
inputting the comment information, the score information and the text information of each sight spot of each user into a pre-trained deep cooperation neural network, and outputting a first rating of each sight spot;
and generating a first sight recommendation list according to the first rating of each sight.
On the basis of the technical scheme, the invention can be further improved.
Further, the clustering each user according to the rating information of each user for each sight spot to obtain the user group of each category includes:
analyzing the attention of each user to different scenic spots according to the grading information of each user to each scenic spot;
and clustering the users according to the attention of each user to different scenic spots.
Further, for the same user group, determining the scoring information of the users who do not score any scenic spot by the following method:
x＝(x1+x2+....+xn)/n；
wherein n is the number of users giving scores to any scenic spot, x1，x2..xnAnd d, scoring each user for any attraction, wherein x is the score of the user who does not score any attraction.
Further, the deep cooperative neural network comprises a first neural network, a second neural network and a shared neural network, the first neural network and the second neural network are in parallel, and an output of the first neural network and an output of the second neural network are inputs of the shared neural network.
Further, the inputting the comment information, the score information and the text information of each sight spot of each user into the pre-trained deep cooperative neural network, and the outputting the first rating of each sight spot includes:
inputting comment information and scoring information of each user on each sight spot into the first neural network, and outputting user characteristics of each user;
inputting the scoring information and the sight spot text information of each sight spot of each user into the second neural network, and outputting the sight spot characteristics of each sight spot;
and inputting each user characteristic and each sight characteristic into the shared neural network, and outputting a first rating of each sight.
Further, the method also comprises the following steps:
acquiring a current position of a user and a weather condition of the current position of the user;
and adjusting the generated first scenic spot recommendation list according to the current position of the user and the weather condition to obtain an adjusted second scenic spot recommendation list.
Further, the adjusting the generated first sight spot recommendation list according to the current position of the user and the weather condition to obtain an adjusted second sight spot recommendation list includes:
according to the weather condition of the current position of the user, reducing or increasing a first preset value for the first rating of each scenic spot to obtain a second rating of each scenic spot;
according to the distance between the current position of the user and each sight spot in the first sight spot recommendation list, reducing or increasing a second preset value for the second rating of each sight spot to obtain a third rating of each sight spot;
and generating a second sight spot recommendation list according to the third rating of each sight spot.
According to a second aspect of the embodiments of the present invention, there is provided a travel recommendation system for leisure agriculture, including:
the system comprises a capturing module, a processing module and a display module, wherein the capturing module is used for capturing relevant information of each scenic spot from a tourism website, and the relevant information of the scenic spots comprises comment information, score information and scenic spot text information of each user on the scenic spot;
the clustering module is used for clustering the users according to the grading information of the users on the scenic spots to obtain user groups of various categories;
the determining module is used for determining the scoring information of the unscored users of any scenic spot according to the known scoring information of the users of any scenic spot in the user group for the same user group;
the output module is used for inputting the comment information, the score information and the text information of each scenic spot of each user into a pre-trained deep cooperative neural network and outputting a first rating of each scenic spot;
and the generating module is used for generating a first scenic spot recommendation list according to the first rating of each scenic spot.
According to a third aspect of the embodiments of the present invention, there is also provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor invokes the program instructions to perform the method for recommending a travel for a recreational agriculture provided in any one of the various possible implementations of the first aspect.
According to a fourth aspect of embodiments of the present invention, there is also provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method for recommending a leisure agricultural tour provided in any one of the various possible implementations of the first aspect.
The embodiment of the invention provides a leisure agriculture tourism recommendation method, a leisure agriculture tourism recommendation system, electronic equipment and a storage medium.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic overall flow chart of a travel recommendation method for leisure agriculture according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an overall structure of a deep cooperative neural network according to an embodiment of the present invention;
FIG. 3 is a flowchart of obtaining a first rating of each attraction using a deep cooperative neural network according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for generating a second scenic spot recommendation list according to an embodiment of the present invention;
FIG. 5 is a connection block diagram of a leisure agricultural tour recommendation system according to an embodiment of the invention;
fig. 6 is a schematic view of an overall structure of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
In an embodiment of the present invention, a method for recommending leisure agriculture tourism is provided, and fig. 1 is a schematic overall flow chart of the method for recommending leisure agriculture tourism provided in the embodiment of the present invention, where the method includes:
capturing relevant information of each sight spot from a tourism website, wherein the relevant information of the sight spots comprises comment information, rating information and sight spot text information of each user on the sight spots;
clustering the users according to the grading information of the users on the scenic spots to obtain user groups of various categories;
for the same user group, determining the scoring information of the user who does not score any scenic spot according to the known scoring information of the user in the user group on any scenic spot;
inputting the comment information, the score information and the text information of each sight spot of each user into a pre-trained deep cooperation neural network, and outputting a first rating of each sight spot;
and generating a first sight recommendation list according to the first rating of each sight.
It can be appreciated that a crawler technology is utilized to crawl a plurality of travel website information, and leisure agricultural information published by agricultural rural areas is used as a supplement to establish an available leisure agricultural travel data set. In the embodiment of the invention, the related information of each sight spot captured from the tourism website comprises comment information, score information and sight spot text information of each user on the sight spot. Because not every user scores scenic spots, the captured data has sparsity, the users are clustered according to the interests of the users in all the scenic spots, and the scores of the user groups in the same category to all the scenic spots are roughly considered to be different. Therefore, after the users are clustered, for the same user group, the rating information of the users who have not rated any scenic spot is determined according to the known rating information of the users to any scenic spot in the user group, so that the rating information of each user to each scenic spot can be obtained. Finally, inputting the comment information, the score information and the text information of each sight spot of each user into a pre-trained deep cooperation neural network, and outputting a first rating of each sight spot; and generating a first sight recommendation list according to the first rating of each sight.
On the basis of the above embodiment, in the embodiment of the present invention, the clustering the users according to the rating information of each user for each scenic spot to obtain the user groups of each category includes:
analyzing the attention of each user to different scenic spots according to the grading information of each user to each scenic spot;
and clustering the users according to the attention of each user to different scenic spots.
It can be understood that when clustering is performed on users, the attention of each user to different scenic spots is analyzed according to the scoring information of each user to each scenic spot; and clustering the users according to the attention of each user to different scenic spots. For example, user A, user B, user C, and user D are all interested in sights 1, 2, 3, and 4, then user A, user B, user C, and user D may be grouped into one category. In the embodiment of the invention, a K-mean clustering algorithm is adopted to cluster each user.
On the basis of the above embodiment, in the embodiment of the present invention, for the same user group, the scoring information of the user who has not scored any scenic spot is determined in the following manner:
x＝(x1+x2+....+xn)/n；
wherein n is the number of users giving scores to any scenic spot, x1，x2..xnAnd d, scoring each user for any attraction, wherein x is the score of the user who does not score any attraction.
It can be understood that, for the same user group, such as the user a, the user B, the user C, and the user D, for example, the user a, the user B, and the user C all give a score to a certain attraction, and the user D does not give a score to the attraction, the score of the user D to the attraction may be determined according to the scores of the user a, the user B, and the user C, for example, an average value of the scores of the user a, the user B, and the user C to the attraction is used as the score of the user D to the attraction. In the embodiment of the present invention, the score of each user for the scenic spots is set to 1, 2, 3, 4, and 5.
Referring to fig. 2, on the basis of the above embodiment, in the embodiment of the present invention, the deep cooperative neural network includes a first neural network, a second neural network, and a shared neural network, the first neural network and the second neural network are in parallel, and an output of the first neural network and an output of the second neural network are inputs of the shared neural network.
Referring to fig. 3, on the basis of the above embodiments, in the embodiment of the present invention, inputting the comment information, the score information, and the text information of each sight spot of each user into the depth cooperation neural network trained in advance, and outputting the first rating of each sight spot includes:
inputting comment information and scoring information of each user on each sight spot into the first neural network, and outputting user characteristics of each user;
inputting the scoring information and the sight spot text information of each sight spot of each user into the second neural network, and outputting the sight spot characteristics of each sight spot;
each user feature and each sight feature are input into a shared neural network, and a first rating of each sight is output.
It will be appreciated that embodiments of the present invention utilize a deep cooperative neural network to rank attractions accordingly, wherein the deep cooperative neural network comprises a first neural network (which may be referred to as a user network) and a second neural network (which may be referred to as a project network or an attraction network) in parallel and a shared neural network.
Specifically, a first neural network and a second neural network can be trained respectively by adopting a training sample set, then comment information and scoring information of each user on each scenic spot are input into the first neural network, and user characteristics of each user are output; and inputting the scoring information and the sight text information of each sight of each user into the second neural network, and outputting the sight characteristics of each sight. Finally, each user characteristic and each sight feature are input into the shared neural network, and a first rating of each sight is output.
In the embodiment of the invention, the comment information of each user for each sight spot is represented as word embedding, and the word vector matrix is created by using the word embedding. The user comment information and the scenery spot text information respectively represent word embedding matrixes, a first neural network and a second neural network which are trained in advance are input to capture semantic information in the comment text, and a user feature u and a scenery spot feature i are output respectively, but the user feature u and the scenery spot feature i can be in different feature spaces and have no comparability. In order to map them to the same feature space, a shared neural network is introduced on top of the first and second neural networks, combining the user network and the item network. And connecting u and i into a vector z (u, i). Modeling all nested variable interactions in z, applying a factorization machine algorithm (FM) as an estimator of the corresponding rank, generating a predicted rating for each sight, hereinafter referred to as the first rating.
On the basis of the above embodiments, the embodiments of the present invention further include:
acquiring a current position of a user and a weather condition of the current position of the user;
and adjusting the generated first scenic spot recommendation list according to the current position of the user and the weather condition to obtain an adjusted second scenic spot recommendation list.
Referring to fig. 4, on the basis of the foregoing embodiments, in the embodiments of the present invention, the adjusting the generated first sight spot recommendation list according to the current location of the user and the weather condition to obtain an adjusted second sight spot recommendation list includes:
according to the weather condition of the current position of the user, reducing or increasing a first preset value for the first rating of each scenic spot to obtain a second rating of each scenic spot;
according to the distance between the current position of the user and each sight spot in the first sight spot recommendation list, reducing or increasing a second preset value for the second rating of each sight spot to obtain a third rating of each sight spot;
and generating a second sight spot recommendation list according to the third rating of each sight spot.
It can be understood that, when recommending scenic spots for each user, the actual situation and weather situation of each user need to be considered, the HTML5 API is used to obtain the current user location, and the weather situation of the current user location is obtained by calling the weather API. Setting four grades of sunny, cloudy, rainy and snowy, and respectively carrying out +3, 0, -4 and-5 on the basis of the first grade of each scenic spot to form a second grade of each scenic spot. And by utilizing a Goodpastel API, setting the acquired current position of the user as a starting point, setting each sight spot in the previously generated first sight spot recommendation list as an end point, calculating the distance between the current position of the user and each sight spot, setting five levels of <30km, 30-60km, 60-90km, 90-120km and >120km, respectively forming a third rating of each sight spot on the basis of the second rating of each current sight spot, and sequentially sequencing all sight spots from high to low according to the third rating of each sight spot to generate a second sight spot recommendation list.
In another embodiment of the invention, a leisure agricultural tour recommendation system is provided for implementing the methods of the foregoing embodiments. Therefore, the descriptions and definitions in the embodiments of the leisure agriculture tour recommendation method can be used for understanding the execution modules in the embodiments of the present invention. Fig. 5 is a schematic diagram of the overall structure of the leisure agriculture tourism recommendation system provided by the embodiment of the present invention, and the system includes a grabbing module 51, a clustering module 52, a determining module 53, an output module 54, and a generating module 55.
The capturing module 51 is configured to capture relevant information of each scenic spot from a travel website, where the relevant information of the scenic spot includes comment information, score information, and scenic spot text information of each user about the scenic spot;
the clustering module 52 is configured to cluster the users according to the rating information of each user on each scenic spot, so as to obtain user groups of each category;
the determining module 53 is configured to determine, for the same user group, scoring information of a user who has not scored any attraction according to known scoring information of the user in the user group for any attraction;
the output module 54 is configured to input the comment information, the score information, and the text information of each sight spot of each user into a pre-trained deep cooperative neural network, and output a first rating of each sight spot;
and the generating module 55 is configured to generate a first sight spot recommendation list according to the first rating of each sight spot.
It can be understood that the leisure agricultural travel recommendation system provided by the embodiment of the present invention corresponds to the leisure travel recommendation methods provided by the embodiments, and the relevant technical features of the leisure agricultural travel recommendation system provided by the embodiment of the present invention can refer to the relevant technical features of the leisure travel recommendation methods provided by the embodiments, and are not described herein again.
Fig. 6 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 6: the system comprises a processor (processor)01, a communication Interface (Communications Interface)02, a memory (memory)03 and a communication bus 04, wherein the processor 01, the communication Interface 02 and the memory 03 complete mutual communication through the communication bus 04. Processor 01 may call logic instructions in memory 03 to perform the following method: capturing relevant information of each sight spot from a tourism website, wherein the relevant information of the sight spots comprises comment information, rating information and sight spot text information of each user on the sight spots; clustering the users according to the grading information of the users on the scenic spots to obtain user groups of various categories; for the same user group, determining the scoring information of the user who does not score any scenic spot according to the known scoring information of the user in the user group on any scenic spot; inputting the comment information, the score information and the text information of each sight spot of each user into a pre-trained deep cooperation neural network, and outputting a first rating of each sight spot; and generating a first sight recommendation list according to the first rating of each sight.
In addition, the logic instructions in the memory 03 can be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The present embodiments provide a non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the methods provided by the above method embodiments, for example, including: capturing relevant information of each sight spot from a tourism website, wherein the relevant information of the sight spots comprises comment information, rating information and sight spot text information of each user on the sight spots; clustering the users according to the grading information of the users on the scenic spots to obtain user groups of various categories; for the same user group, determining the scoring information of the user who does not score any scenic spot according to the known scoring information of the user in the user group on any scenic spot; inputting the comment information, the score information and the text information of each sight spot of each user into a pre-trained deep cooperation neural network, and outputting a first rating of each sight spot; and generating a first sight recommendation list according to the first rating of each sight.
According to the leisure agriculture tourism recommendation method, the system, the electronic equipment and the storage medium, users are clustered through a clustering algorithm, the scores of the users who are not scored are determined according to the scores of the scored users, the problem of data sparsity is solved, a deep cooperative neural network model is used for predicting and rating each scenic spot, finally, the primarily determined rating of each scenic spot is adjusted by considering the distance between the current position of the user and each recommended scenic spot, a final recommendation list is determined by combining scene perception information, and the scenic spot personalized recommendation of different users is achieved.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1.一种休闲农业旅游推荐方法，其特征在于，包括：1. a leisure agricultural tourism recommendation method, is characterized in that, comprises: 从旅游网站抓取各景点相关信息，其中，所述景点相关信息包括各用户对各景点的评论信息、评分信息和景点文本信息；Capture relevant information of each scenic spot from a travel website, wherein the scenic spot-related information includes comment information, rating information and scenic spot text information of each user on each scenic spot; 根据各用户对各景点的评分信息，对各用户进行聚类，得到各类别的用户群体；According to each user's rating information for each scenic spot, each user is clustered to obtain various user groups; 对于同一个用户群体，根据所述用户群体内用户对任一景点的已知评分信息确定对所述任一景点未评分的用户的评分信息；For the same user group, determine the rating information of the user who has not rated any scenic spot according to the known rating information of the user in the user group for any scenic spot; 将每个用户对每个景点的评论信息、评分信息和每个景点文本信息输入预先训练后的深度合作神经网络，输出每个景点的第一评级；Input each user's comment information, rating information and text information of each scenic spot into the pre-trained deep cooperative neural network, and output the first rating of each scenic spot; 根据每个景点的第一评级，生成第一景点推荐列表。According to the first rating of each scenic spot, a first scenic spot recommendation list is generated. 2.根据权利要求1所述的休闲农业旅游推荐方法，其特征在于，所述根据各用户对各景点的评论信息和评分信息，对各用户进行聚类，得到各类别的用户群体包括：2. The method for recommending leisure agricultural tourism according to claim 1, characterized in that, according to each user's comment information and rating information on each scenic spot, each user is clustered to obtain various user groups including: 根据各用户对各景点的评分信息，分析每一个用户对不同景点的关注度；According to each user's rating information for each scenic spot, analyze each user's attention to different scenic spots; 根据每一个用户对不同景点的关注度，对各用户进行聚类。According to each user's attention to different scenic spots, each user is clustered. 3.根据权利要求1所述的休闲农业旅游推荐方法，其特征在于，对于同一个用户群体，通过如下方式确定对所述任一景点未评分的用户的评分信息：3. The method for recommending leisure agricultural tourism according to claim 1, wherein, for the same user group, the rating information of the user who has not rated any of the scenic spots is determined as follows: x＝(x1+x2+....+xn)/n；x=(x 1 +x 2 +....+x n )/n; 其中，n为对所述任一景点给出了评分的用户的数量，x1，x2..xn为每一个用户对所述任一景点的评分，x为对所述任一景点未评分的用户的评分。Among them, n is the number of users who have given ratings to the any scenic spot, x 1 , x 2 .. x n is the score of each user to the any scenic spot, and x is the unreviewed score for the any scenic spot. The rating of the user who rated it. 4.根据权利要求1所述的休闲农业旅游推荐方法，其特征在于，所述深度合作神经网络包括第一神经网络、第二神经网络和共享神经网络，所述第一神经网络和所述第二神经网络并行，且所述第一神经网络的输出和所述第二神经网络的输出均为所述共享神经网络的输入。4. The method for recommending leisure agricultural tourism according to claim 1, wherein the deep cooperative neural network comprises a first neural network, a second neural network and a shared neural network, the first neural network and the first neural network The two neural networks are parallel, and the output of the first neural network and the output of the second neural network are both inputs of the shared neural network. 5.根据权利要求4所述的休闲农业旅游推荐方法，其特征在于，所述将每个用户对每个景点的评论信息、评分信息和每个景点文本信息输入预先训练后的深度合作神经网络，输出每个景点的第一评级包括：5 . The method for recommending leisure agricultural tourism according to claim 4 , wherein the comment information, rating information and text information of each scenic spot of each user on each scenic spot are input into the pre-trained deep cooperative neural network. 6 . , the output of the first rating for each attraction includes: 将每一个用户对每一个景点的评论信息和评分信息输入所述第一神经网络，输出每一个用户的用户特征；Input each user's comment information and rating information for each scenic spot into the first neural network, and output the user characteristics of each user; 将每一个用户对每一个景点的评分信息和景点文本信息输入所述第二神经网络，输出每一个景点的景点特征；Input each user's rating information and scenic spot text information for each scenic spot into the second neural network, and output the scenic spot feature of each scenic spot; 将每一个用户特征和每一个景点特征输入所述共享神经网络，输出每一个景点的第一评级。Each user feature and each scenic spot feature are input into the shared neural network, and the first rating of each scenic spot is output. 6.根据权利要求1所述的休闲农业旅游推荐方法，其特征在于，还包括：6. The leisure agricultural tourism recommendation method according to claim 1, characterized in that, further comprising: 获取用户当前位置和所述用户当前位置的天气情况；Obtain the user's current location and the weather conditions of the user's current location; 根据所述用户当前位置和所述天气情况，对生成的所述第一景点推荐列表进行调整，得到调整后的第二景点推荐列表。According to the current location of the user and the weather condition, the generated first recommended list of scenic spots is adjusted to obtain an adjusted second recommended list of scenic spots. 7.根据权利要求6所述的休闲农业旅游推荐方法，其特征在于，其特征在于，所述根据所述用户当前位置和所述天气情况，对生成的所述第一景点推荐列表进行调整，得到调整后的第二景点推荐列表包括：7 . The method for recommending leisure agricultural tourism according to claim 6 , wherein, according to the current location of the user and the weather condition, the generated first scenic spot recommendation list is adjusted, 8 . The adjusted list of recommended second attractions includes: 根据所述用户当前位置的天气情况，对每一个景点的第一评级减小或增加第一预设值，得到每一个景点的第二评级；Decrease or increase the first preset value for the first rating of each scenic spot according to the weather conditions of the current location of the user, and obtain the second rating of each scenic spot; 根据所述用户当前位置与所述第一景点推荐列表中的每一个景点的距离，对每一个景点的第二评级减小或增加第二预设值，得到每一个景点的第三评级；According to the distance between the user's current location and each scenic spot in the first scenic spot recommendation list, the second rating of each scenic spot is decreased or increased by a second preset value, and the third rating of each scenic spot is obtained; 根据每一个景点的第三评级，生成第二景点推荐列表。According to the third rating of each scenic spot, a second scenic spot recommendation list is generated. 8.一种休闲农业旅游推荐系统，其特征在于，包括：8. A leisure agricultural tourism recommendation system, comprising: 抓取模块，用于从旅游网站抓取各景点相关信息，其中，所述景点相关信息包括各用户对景点的评论信息、评分信息和景点文本信息；a crawling module, used for crawling the relevant information of each scenic spot from the tourism website, wherein the relevant information of the scenic spot includes the comment information, rating information and scenic spot text information of each user on the scenic spot; 聚类模块，用于根据各用户对各景点的评分信息，对各用户进行聚类，得到各类别的用户群体；The clustering module is used to cluster each user according to the rating information of each user on each scenic spot to obtain various user groups; 确定模块，用于对于同一个用户群体，根据所述用户群体内用户对任一景点的已知评分信息确定对所述任一景点未评分的用户的评分信息；A determination module, configured to, for the same user group, determine the rating information of the user who has not rated any scenic spot according to the known rating information of the user in the user group for any scenic spot; 输出模块，用于将每个用户对每个景点的评论信息、评分信息和每个景点文本信息输入预先训练后的深度合作神经网络，输出每个景点的第一评级；The output module is used to input each user's comment information, rating information and text information of each scenic spot into the pre-trained deep cooperative neural network, and output the first rating of each scenic spot; 生成模块，用于根据每个景点的第一评级，生成第一景点推荐列表。The generating module is used for generating a first recommendation list of scenic spots according to the first rating of each scenic spot. 9.一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其特征在于，所述处理器执行所述程序时实现如权利要求1至7任一项所述休闲农业旅游推荐方法的步骤。9. An electronic device, comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor implements any one of claims 1 to 7 when the processor executes the program The steps of the recommended method for leisure agricultural tourism described in item. 10.一种非暂态计算机可读存储介质，其上存储有计算机程序，其特征在于，该计算机程序被处理器执行时实现如权利要求1至7任一项所述休闲农业旅游推荐方法的步骤。10. A non-transitory computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the method for implementing the method for recommending leisure agricultural tourism according to any one of claims 1 to 7 is implemented. step.
CN201910968979.4A 2019-10-12 2019-10-12 Leisure agriculture tourism recommendation method and system, electronic equipment and storage medium Pending CN110942334A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910968979.4A CN110942334A (en) 2019-10-12 2019-10-12 Leisure agriculture tourism recommendation method and system, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910968979.4A CN110942334A (en) 2019-10-12 2019-10-12 Leisure agriculture tourism recommendation method and system, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN110942334A true CN110942334A (en) 2020-03-31

Family

ID=69906104

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910968979.4A Pending CN110942334A (en) 2019-10-12 2019-10-12 Leisure agriculture tourism recommendation method and system, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN110942334A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110320462A1 (en) * 2010-06-29 2011-12-29 International Business Machines Corporation Method and apparatus for recommending information to users within a social network
CN106599092A (en) * 2016-11-24 2017-04-26 宇龙计算机通信科技(深圳)有限公司 Method and device for recommending tourist attractions
CN108537624A (en) * 2018-03-09 2018-09-14 西北大学 A kind of tourist service recommendation method based on deep learning
CN109284443A (en) * 2018-11-28 2019-01-29 四川亨通网智科技有限公司 A kind of tourism recommended method and system based on crawler technology

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110320462A1 (en) * 2010-06-29 2011-12-29 International Business Machines Corporation Method and apparatus for recommending information to users within a social network
CN106599092A (en) * 2016-11-24 2017-04-26 宇龙计算机通信科技(深圳)有限公司 Method and device for recommending tourist attractions
CN108537624A (en) * 2018-03-09 2018-09-14 西北大学 A kind of tourist service recommendation method based on deep learning
CN109284443A (en) * 2018-11-28 2019-01-29 四川亨通网智科技有限公司 A kind of tourism recommended method and system based on crawler technology

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
程鹏等: "基于多维特征聚类和用户评分的景点推荐算法", 《计算机工程与设计》 *
黄文明等: "基于注意力机制与评论文本深度模型的推荐方法", 《计算机工程》 *

Similar Documents

Publication Publication Date Title
EP3779841A1 (en) Method, apparatus and system for sending information, and computer-readable storage medium
US8515828B1 (en) Providing product recommendations through keyword extraction from negative reviews
CN113742567B (en) Recommendation method and device for multimedia resources, electronic equipment and storage medium
CN107291888B (en) Machine learning statistical model-based living recommendation system method near living hotel
CN107424043A (en) A kind of Products Show method and device, electronic equipment
CN110097412A (en) Item recommendation method, device, equipment and storage medium
CN106354856B (en) Deep neural network enhanced search method and device based on artificial intelligence
CN105045916A (en) Mobile game recommendation system and recommendation method thereof
CN104008184A (en) Method and device for pushing information
CN117217872A (en) Method for intelligently generating scenic spot playing scheme based on tourist portrait
CN111722766A (en) Method and device for displaying multimedia resources
CN103455537A (en) Information processing apparatus, information processing method, and program
CN114358807B (en) User profiling method and system based on predictable user characteristic attributes
CN113343127A (en) Tourism route recommendation method, system, server and storage medium
CN108806355B (en) An interactive education system for calligraphy and painting art
CN111882224A (en) Method and apparatus for classifying consumption scenarios
WO2023087933A1 (en) Content recommendation method and apparatus, device, storage medium, and program product
CN119311949A (en) A regional cultural tourism intelligent recommendation method, system, device and storage medium
JP7473723B1 (en) Information processing device, information processing method, and program
CN104463633A (en) User segmentation method based on geographic position and interest point information
JP2025522587A (en) Display method, device, electronic device, and computer-readable medium
CN119850273B (en) Advertisement visual element intelligent collocation system and method based on big data
US20200073925A1 (en) Method and system for generating a website from collected content
CN113688299B (en) Land plot selection method, device, electronic device and storage medium
CN113742614B (en) Method for generating and displaying recommended information, electronic device and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20200331