CN111177559B - Text travel service recommendation method and device, electronic equipment and storage medium - Google Patents
Text travel service recommendation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111177559B CN111177559B CN201911404349.0A CN201911404349A CN111177559B CN 111177559 B CN111177559 B CN 111177559B CN 201911404349 A CN201911404349 A CN 201911404349A CN 111177559 B CN111177559 B CN 111177559B
- Authority
- CN
- China
- Prior art keywords
- information
- user
- knowledge
- target
- travel service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims description 33
- 238000000605 extraction Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 abstract description 11
- 230000008846 dynamic interplay Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 18
- 238000010586 diagram Methods 0.000 description 10
- 230000008451 emotion Effects 0.000 description 10
- 230000006399 behavior Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000003993 interaction Effects 0.000 description 6
- 238000010276 construction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013475 authorization Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Computational Linguistics (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method, a device, electronic equipment and a storage medium for recommending a travel service, wherein user characteristic information of a target user is obtained; extracting a knowledge chain group from a preset travel knowledge graph according to the user characteristic information; calculating target travel service information matched with the user characteristic information according to the knowledge chain group; the target travel service information is recommended to the target user, and compared with the original travel knowledge graph, the knowledge chain group extracted from the preset travel knowledge graph according to the user characteristic information has smaller data size and higher calculation efficiency, so that the dynamic interaction behavior in the use process of the user can be analyzed in real time and timely fed back, and the accuracy of the result of the travel service recommendation to the user is improved.
Description
Technical Field
The present invention relates to the field of big data technologies, and in particular, to a method and apparatus for recommending a travel service, an electronic device, and a storage medium.
Background
Along with the development of big data technology, the maturity of various user identification technologies provides support for personalized recommendation systems, provides personalized real-time recommendation functions according to the characteristics of users, can reduce frequent clicking and error correction behaviors of users in a human-computer interaction system, optimize user experience, improve user satisfaction, especially in intelligent travel data visualization scenes, information demand contents in different business scenes are inconsistent, how to recommend proper contents for the users based on big data information, and improve user experience in the human-computer interaction process is very necessary.
In the prior art, the traditional recommendation method for realizing the travel service by using the knowledge graph constructs the knowledge graph through priori knowledge, and because the knowledge graph has a complex structure, real-time calculation is difficult to achieve, a calculation matrix with a huge scale is constructed, and real-time analysis and timely feedback on dynamic interaction behaviors in the use process of a user are difficult to achieve, so that the problems of low calculation efficiency, inaccurate result of travel service recommendation to the user and the like are caused, and the experience of the user in the man-machine interaction process is affected.
Disclosure of Invention
The invention provides a method, a device, electronic equipment and a storage medium for recommending a travel service, which are used for solving the problem that the result of recommending the travel service to a user is inaccurate.
According to a first aspect of the disclosed embodiments, the present invention provides a method for recommending a travel service, the method comprising:
acquiring user characteristic information of a target user;
extracting a knowledge chain group from a preset travel knowledge graph according to the user characteristic information;
calculating target travel service information matched with the user characteristic information according to the knowledge chain group;
recommending the target travel service information to the target user.
Optionally, the obtaining the user characteristic information of the target user includes:
acquiring portrait information and interest information of the target user;
and determining user characteristic information of the target user according to the portrait information and the interest information.
Optionally, the acquiring the portrait information of the target user includes:
acquiring identity information of a target user;
classifying the target users according to the identity information of the target users, and determining the group category of the target users;
and determining portrait information of the target user according to the group category.
Optionally, the obtaining the interest information of the target user includes:
acquiring browsing information and comment information of the target user;
and determining interest information of the target user according to the browsing information and comment information of the target user.
Optionally, the determining the interest information of the target user according to the browsing information and comment information of the target user includes:
according to the browsing information of the target user, determining the interest field of the target user;
determining interest information of the target user according to the comment information of the target user in the interest field;
Correspondingly, the determining the user characteristic information of the target user according to the portrait information and the interest information comprises the following steps:
and determining the portrait information and the interest information as the user characteristic information.
Optionally, the knowledge graph includes a plurality of knowledge chains, the knowledge chains are used for mapping relationships between users corresponding to different user feature information and travel service information, and the extracting a knowledge chain group from a preset travel knowledge graph according to the user feature information includes:
determining a target knowledge chain related to the user characteristic information in a knowledge graph;
and extracting a preset number of target knowledge chains from the knowledge graph to generate a knowledge chain group.
Optionally, the calculating, according to the knowledge chain set, the target travel service information matched with the user feature information includes:
converting the knowledge chain set into a multidimensional feature matrix;
training a recommendation model matched with the user characteristic information by utilizing the multidimensional characteristic matrix;
and inputting the user characteristic information into the recommendation model to obtain the output target travel service information.
Optionally, the converting the knowledge chain set into a multidimensional feature matrix includes:
Extracting user characteristic information and travel service information corresponding to each knowledge chain in the knowledge chain group;
generating a plurality of first feature rectangles according to the corresponding user feature information;
generating a plurality of second feature matrixes according to the corresponding travel service information;
correspondingly combining each first characteristic rectangle and each second characteristic rectangle into a plurality of characteristic matrixes;
and combining the plurality of feature matrices into a multi-dimensional feature matrix.
Optionally, before the obtaining the user characteristic information of the target user, the method further includes:
acquiring priori knowledge of a text travel service;
and constructing a travel knowledge graph according to the travel service priori knowledge.
According to a second aspect of the embodiments of the present disclosure, the present invention provides a travel service recommendation device, including:
the user characteristic acquisition module is used for acquiring user characteristic information of a target user;
the knowledge chain set extraction module is used for extracting a knowledge chain set from a preset travel knowledge graph according to the user characteristic information;
the travel service calculation module is used for calculating target travel service information matched with the user characteristic information according to the knowledge chain group;
and the travel service recommending module is used for recommending the target travel service information to the target user.
Optionally, the user feature acquisition module is specifically configured to:
acquiring portrait information and interest information of the target user;
and determining user characteristic information of the target user according to the portrait information and the interest information.
Optionally, the user feature acquisition module is specifically configured to, when acquiring portrait information of the target user:
acquiring identity information of a target user;
classifying the target users according to the identity information of the target users, and determining the group category of the target users;
and determining portrait information of the target user according to the group category.
Optionally, the user feature acquisition module is specifically configured to, when acquiring interest information of the target user:
acquiring browsing information and comment information of the target user;
and determining interest information of the target user according to the browsing information and comment information of the target user.
Optionally, the user feature acquisition module is specifically configured to, when determining the interest information of the target user according to the browsing information and the comment information of the target user:
according to the browsing information of the target user, determining the interest field of the target user;
Determining interest information of the target user according to the comment information of the target user in the interest field;
correspondingly, the user characteristic acquisition module is specifically used for determining the user characteristic information of the target user according to the portrait information and the interest information:
and determining the portrait information and the interest information as the user characteristic information.
Optionally, the knowledge graph includes a plurality of knowledge chains, the knowledge chains are used for mapping relationships between users corresponding to different user feature information and travel service information, and the knowledge chain group extraction module is specifically used for:
determining a target knowledge chain related to the user characteristic information in a knowledge graph;
and extracting a preset number of target knowledge chains from the knowledge graph to generate a knowledge chain group.
Optionally, the hotel services calculation module is specifically configured to:
converting the knowledge chain set into a multidimensional feature matrix;
training a recommendation model matched with the user characteristic information by utilizing the multidimensional characteristic matrix;
and inputting the user characteristic information into the recommendation model to obtain the output target travel service information.
Optionally, the travel service calculation module is specifically configured to, when converting the knowledge chain set into a multidimensional feature matrix:
Extracting user characteristic information and travel service information corresponding to each knowledge chain in the knowledge chain group;
generating a plurality of first feature rectangles according to the corresponding user feature information;
generating a plurality of second feature matrixes according to the corresponding travel service information;
correspondingly combining each first characteristic rectangle and each second characteristic rectangle into a plurality of characteristic matrixes;
and combining the plurality of feature matrices into a multi-dimensional feature matrix.
Optionally, the travel service recommending device further includes a knowledge graph construction module, configured to:
acquiring priori knowledge of a text travel service;
and constructing a travel knowledge graph according to the travel service priori knowledge.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including: a memory, a processor, and a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor as the method of travel service recommendation according to any of the first aspect of the embodiments of the present disclosure.
According to a fourth aspect of the disclosed embodiments, the present invention provides a computer-readable storage medium having stored therein computer-executable instructions, which when executed by a processor, are for implementing the method for recommending a travel service according to any of the first aspects of the disclosed embodiments.
The invention provides a travel service recommending method, a device, electronic equipment and a storage medium, wherein user characteristic information of a target user is obtained; extracting a knowledge chain group from a preset travel knowledge graph according to the user characteristic information; calculating target travel service information matched with the user characteristic information according to the knowledge chain group; and recommending the target travel service information to the target user, wherein the knowledge chain group extracted from the preset travel knowledge graph according to the user characteristic information has smaller data size and higher calculation efficiency compared with the original travel knowledge graph, so that the dynamic interaction behavior of the user in the using process can be analyzed in real time and timely fed back, and the accuracy of the result of recommending the travel service to the user is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is an application scenario diagram of a travel service recommendation method provided by an embodiment of the present invention;
FIG. 2 is a flow chart of a travel service recommendation method according to an embodiment of the present invention;
FIG. 3 is a flow chart of a travel service recommendation method according to another embodiment of the present invention;
FIG. 4 is a flowchart of step S203 in the embodiment shown in FIG. 3;
FIG. 5 is a flowchart of step S204 in the embodiment shown in FIG. 3;
FIG. 6 is a schematic diagram of the content of a knowledge chain set according to an embodiment of the present invention;
FIG. 7 is a flowchart of step S208 in the embodiment shown in FIG. 3;
FIG. 8 is a schematic diagram of a travel service recommendation device according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of a travel service recommendation device according to another embodiment of the present invention;
fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Specific embodiments of the present disclosure have been shown by way of the above drawings and will be described in more detail below. These drawings and the written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the disclosed concepts to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
First, the terms involved in the present invention will be explained:
knowledge graph: knowledge maps are structured semantic knowledge bases that are used to symbolically describe concepts and their interrelationships in the physical world. The basic composition unit is an entity-relation-entity triplet, and the entities and related attribute value pairs thereof are mutually connected through the relation to form a net-shaped knowledge structure. The basic form of a triplet mainly includes a first entity, a relationship, a second entity, and a concept, an attribute value, and the like.
The entities are the most basic elements in the knowledge graph, and different relationships exist among different entities. Concepts mainly refer to collections, categories, object types, categories of things, such as people, geographies, etc.; attributes mainly refer to attributes, features, characteristics, features and parameters that an object may have, such as nationality, birthday, etc.; the attribute value mainly refers to the value of the object-specified attribute, such as China, 1988-09-08, and the like. Each entity may be identified by a globally unique ID, each attribute-value pair (AVP) may be used to characterize the intrinsic properties of the entity, and a relationship may be used to connect two entities, characterizing the association between them.
The following describes the technical scheme of the present invention and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
The following explains the application scenario of the embodiment of the present invention:
fig. 1 is an application scenario diagram of a travel service recommendation method provided by an embodiment of the present invention, where, as shown in fig. 1, the travel service recommendation method provided by the embodiment of the present invention is operated on an electronic device, and in particular, the electronic device is a server of an a website. After the target user accesses the A website through the terminal equipment, the server of the A website acquires the user characteristic information of the target user, determines target travel service information matched with the user characteristic information according to the user characteristic information, and pushes the target travel service information to the target user, so that the target user can quickly acquire a travel service item suitable for the target user.
Fig. 2 is a flowchart of a travel service recommendation method according to an embodiment of the present invention, as shown in fig. 2, where the travel service recommendation method according to the embodiment includes the following steps:
Step S101, obtaining user characteristic information of a target user.
The user characteristic information is information for describing characteristics possessed by the user, and by using the user characteristic information, different users can be classified and distinguished. The user characteristic information may be simple single-element information, such as sex characteristics, for acquiring user characteristic information of the target user, i.e., acquiring the sex of the target user. The user characteristic information can also be complex multi-element information, for example, the interest characteristic, the age characteristic and the crowd characteristic of the user are integrated as the user characteristic information, the user characteristic information of the target user is obtained, that is, a plurality of characteristic elements such as the interest characteristic, the age characteristic and the crowd characteristic of the target user are obtained as the user characteristic information, and it can be understood that the more the characteristic elements in the user characteristic information, the more accurate the user is distinguished.
Further, the user characteristic information may include objective characteristics possessed by the user itself, such as gender characteristics, age characteristics of the user. Subjective features that the user has after classifying the user as desired, e.g., high consumption features, young group features, may also be included. Therefore, the content of the user characteristic information can be adjusted according to specific scenes and needs, and the content of the user characteristic information is not specifically limited herein.
Step S102, extracting a knowledge chain group from a preset travel knowledge graph according to the user characteristic information.
The travel knowledge graph is a knowledge graph of the user and specific travel activity content for describing the characteristic information of different users in the travel activity, and according to the travel index graph, the mapping relationship between the user and the travel activity content of the different user characteristic information can be determined.
However, the content contained in the preset travel knowledge graph is huge, the mapping relation is extremely complex, and the problem of low calculation efficiency is caused by directly processing or calculating the preset travel knowledge graph.
For the user characteristic information, only a small amount of information is contained, and according to the user characteristic information, the content matched with the user characteristic information of the target user is found from the preset travel knowledge graph to form a plurality of groups of knowledge chains, so that useless information in the preset travel knowledge graph can be filtered, which is equivalent to dimension reduction, the data volume of subsequent data processing can be effectively reduced, and the data processing efficiency is improved.
For example, the user feature information includes two feature elements, namely "interest feature" and "gender feature", and the knowledge chains related to the "interest feature" and the "gender feature" in the preset travel knowledge graph are extracted according to the user feature information, and the rest knowledge chains not related to the "interest feature" and the "gender feature" are omitted, so that the purpose of improving the data processing efficiency is achieved without processing in subsequent calculation.
Step S103, calculating target travel service information matched with the user characteristic information according to the knowledge chain group.
After the knowledge chain group is determined, the knowledge chain group comprises a plurality of knowledge chains, a set of strategies for recommending the travel service for the target user according to different user characteristic information of the target user can be formed according to the relation elements in each knowledge chain, and at the moment, the target travel service information matched with the user characteristic information is calculated by utilizing the strategies for recommending the travel service according to the specific user characteristic information of the user.
Step S104, recommending the target travel service information to the target user.
After the target travel service information is obtained, the information is recommended to the target user through different channels, so that the target user can obtain the travel service recommendation information matched with the user characteristic information and meeting the user requirements, and further, the target user can quickly obtain the travel service project suitable for the target user.
In this embodiment, the user characteristic information of the target user is obtained. And extracting a knowledge chain group from a preset travel knowledge graph according to the user characteristic information. And calculating target travel service information matched with the user characteristic information according to the knowledge chain group. The target travel service information is recommended to the target user, and compared with the original travel knowledge graph, the knowledge chain group extracted from the preset travel knowledge graph according to the user characteristic information has smaller data size and higher calculation efficiency, so that the dynamic interaction behavior in the use process of the user can be analyzed in real time and timely fed back, and the accuracy of the result of the travel service recommendation to the user is improved.
Fig. 3 is a flowchart of a travel service recommendation method according to another embodiment of the present invention, as shown in fig. 3, where, based on the travel service recommendation method according to the embodiment shown in fig. 2, steps S101 to S103 are further refined, and a step of building a travel knowledge graph is added before step S101, the travel service recommendation method according to the present embodiment includes the following steps:
step S201, obtaining priori knowledge of the travel service.
The travel service a priori knowledge refers to data that can be used to describe the relationship between different users and the travel service. The data can be used as a learning sample for studying the relationship between different users and the travel service. The form and content of the travel service a priori knowledge is varied, for example, as a record of the travel service that is actively or passively accepted by different users. As another example, the prior knowledge of the travel service is obtained by evaluating, clicking amount and other data of different users on different travel services on the website. The acquisition mode of the priori knowledge of the travel service is various, and the form, the content and the acquisition mode of the priori knowledge of the travel service are not particularly limited.
Step S202, constructing a travel knowledge graph according to the prior knowledge of the travel service.
According to the acquired priori knowledge of the travel service, analysis and feature extraction can be performed as sample data, and a travel knowledge graph is constructed. The construction of the knowledge graph is divided into a bottom-up mode and a top-down mode, wherein a certain rule is extracted from the prior knowledge of the existing travel service, information with higher confidence is found according to the rule and added into the knowledge graph, the top-down mode is a process of finding entities and relation information from a high-quality website and adding the entities and relation information into the knowledge graph, or the entities are extracted and induced in a combined mode, for example, a natural language processing mode is firstly utilized from the behavior and comment data of a user, and then verification expansion is carried out from information such as a user portrait and the like in a top-down mode, and the two methods are combined alternately to ensure that the travel user entity library with higher confidence is extracted. And finally, representing the processed data through a uniform resource descriptor and storing the uniform resource descriptor into the graph data to form a travel knowledge graph.
Step S203, portrait information of the target user is acquired.
The portrayal information is information describing characteristics and requirements of users, and users having different characteristics can be classified into different types according to the portrayal information. Such as young age groups, high consumer groups, price sensitive groups, and the like.
Optionally, as shown in fig. 4, the step S203 of acquiring the portrait information of the target user includes three specific implementation steps of steps S2031, S2032 and S2033:
step S2031, obtaining identity information of a target user.
Specifically, the identity information is information related to the true identity of the user, and the identity information is obtained through registration information of the user. For example, sex information, age information, etc. registered by the user. Of course, the identity information of the user may also be obtained by means of a third party authorization, for example, the user is a member of the a website, and the identity information is registered in the a website. And B, the website obtains the identity information of the user through the authorization of the website A. Here, the specific manner of acquiring the identity information of the target user is not limited.
Step S2032, classifying the target users according to the identity information of the target users, and determining the group category of the target users.
The different user identity information generally causes different behavior habits and consumption habits of users. Therefore, after classifying the target users according to the identity information of the target users, the users with different user identities are in the corresponding group categories, so that the follow-up recommendation of the matched text and travel service information according to the different group categories is facilitated.
Alternatively, the relationship information between the target user and other users may be determined according to the identity information of the target user, for example, the target user a and the user B are in a friend relationship. The target user and other users having a specific relationship therewith, such as friends, classmates, relatives, may be determined as a group category. Because the behavior habit and the characteristics of the user are often influenced by friends and relatives in the social network, the target user and other users with specific relations are determined to be a group class, the actual demands of the user can be better determined, and the accuracy of determining the characteristic information of the user is improved.
Step S2033, determining portrait information of the target user according to the group category.
Because the specific group categories have relatively obvious differences and characteristics in behavioral habits and consumption habits, the portrait information corresponding to the users in different group categories can be determined according to the differences and characteristics. For example, for younger age groups, some popular metropolitan, hotter scenic spots tend to be the destination of the travel activity when engaged in the travel activity. While some older middle-aged and old people tend to take some points of interest and scenic spots with beautiful nature as destinations of the travel activities when participating in the travel activities. For another example, young people consume higher when they are engaged in a travel activity, and middle-aged and elderly people consume lower when they are engaged in a travel activity. Therefore, the portrait information of the young group users and the portrait information of the middle-aged and elderly group users can be determined accordingly.
In the steps of the embodiment, different portrait information is generated for the user through the identity information of the target user of the user, so that the purpose of quickly classifying the user is achieved, the identity information is obtained in a simple mode, and the content is accurate, so that the processing efficiency and accuracy of the portrait information of the user can be improved.
Step S204, obtaining interest information of the target user.
In particular, the interest information refers to the interest point information of the user, and in the travel activities, the user tends to easily accept the travel service matching the interest point. Such as the country, region of interest. The interesting activity content, such as food and sports, belongs to the category of interest information.
Alternatively, the browsing information and comment information of the user on the website may represent the content of interest of the user, and thus, the interest information of the target user may be determined according to the browsing information and comment information of the target user.
Optionally, as shown in fig. 5, the step S204 of obtaining the interest information of the target user includes three specific implementation steps of steps S2041, S2042 and S2043:
in step S2041, browsing information and comment information of the target user are acquired.
In particular, browsing information and comment information of a user at a website are often direct expressions in which the user is interested in the content thereof. The browsing information comprises the content and duration of the web pages browsed by the user in a period of time.
Comment information is comment content posted by a user for specific content in a period of time, including non-real-time messages and real-time messages, such as video bullets and the like.
Step S2042, according to the browsing information of the target user, determining the interest field of the target user.
Alternatively, if the target user browses the content of the specific domain for a long time or multiple times, the user may be determined to be interested in the domain comparison, that is, the domain of interest of the target user may be determined. For example, the target user browses the content and information related to "Xinjiang tour" on the website multiple times, and can determine that the target user is interested in the "Xinjiang tour", namely, "Xinjiang tour" can be used as the interest field of the target user. For another example, the target user browses the content and information related to "self-driving tour" on the website for multiple times, and can determine that the target user is interested in the comparison of the "self-driving tour", namely, the "self-driving tour" can be used as the interest field of the target user.
Step S2043, determining interest information of the target user according to the comment information of the target user in the interest area.
While the user is interested in a certain area, the user's emotion in that area of interest may be positive or negative, e.g., the user searches for "Xinjiang tour" multiple times, in fact because the user has already attended the travel activity associated with "Xinjiang tour", but has a poor experience, browsing the content multiple times for complaints and expressions of the travel activity that is not full of "Xinjiang tour".
Therefore, on the basis of determining the interest field, the emotion tendency of the user is determined according to the comment information of the target user in the interest field, and further the interest information of the target user is accurately determined.
In the step of the embodiment, the interest information of the user is determined from the interest field and the emotion tendency of the user by acquiring the browsing information and the comment information of the user, so that misjudgment on the true interest intention of the user is avoided, and the accuracy of evaluating the interest information of the user is improved.
Optionally, when the target user does not comment in the interest field, the emotion tendency of the target user to the interest field can be judged through the specific content in the interest field browsed by the target user, so that the interest information of the target user can be accurately determined.
Optionally, the interest information includes browsing information and comment information itself.
Optionally, the method for determining the emotion tendencies of the user from the comment information of the target user and the method for judging the emotion tendencies of the target user in the interest field browsed by the target user may adopt a mode of performing natural language processing on the specific content and the comment content and obtaining semantic information and emotion information, so that the judgment of the emotion tendencies of the target user is realized, and the specific implementation method is the prior art in the field and is not repeated herein.
Step S205, user characteristic information of the target user is determined according to the portrait information and the interest information.
The portrait information of the user and the interest information of the user describe the feature information of the user from two dimensions. Portrayal information is a general classification of a user population, while interest information is used to rescreen a user population having specific interest features based on a specific user population. Therefore, the user characteristic information of the target user is determined according to two dimensions of the portrait information and the interest information, the effect of accurately evaluating the user characteristic information is achieved, and the accuracy of user characteristic evaluation is improved. Specifically, an alternative implementation is to determine portrait information and interest information as user feature information.
Optionally, the knowledge graph includes a plurality of knowledge chains, and the knowledge chains are used for mapping relationships between users corresponding to different user characteristic information and travel service information.
Step S206, determining a target knowledge chain related to the user characteristic information in the knowledge graph.
The user characteristic information is less than the knowledge graph information, a large number of redundant knowledge chains in the knowledge graph are irrelevant to the user characteristic information, and the knowledge chains relevant to the knowledge graph are determined according to the user characteristic information, so that the subsequent data processing efficiency can be effectively improved.
For example, the user characteristic information includes the age characteristic and the interest characteristic of the user a, and a knowledge chain with the attribute related to the age characteristic and the interest characteristic in the knowledge graph is determined as a target knowledge chain. Other attributes in the knowledge graph are not related to the knowledge chain, such as a knowledge chain for representing the relationship between the record of the last travel activity of the user and the recommended travel service, and the knowledge chain is not determined to be a target knowledge chain.
Step S207, extracting a preset number of target knowledge chains from the knowledge graph to generate a knowledge chain group.
Optionally, the knowledge chain group includes a plurality of knowledge chains, where the number of knowledge chains is a preset number, and the number of knowledge chains may be set according to the number of target knowledge chains and specific requirements, which is not limited herein specifically.
Fig. 6 is a schematic diagram of the content of the knowledge chain set according to an embodiment of the present invention. As shown in fig. 6, the portrait information in the user feature information includes several feature elements of "professional information" and "friend information" of the user. The interest information in the user characteristic information comprises a plurality of characteristic elements including browsing information and comment information, ten knowledge chains related to the user characteristic information are extracted from the knowledge graph to form a knowledge chain group, wherein a first entity is a user 1, namely a target user. The second entity is service 2, namely the target travel service, and the relations in the knowledge chains one to ten are respectively:
The first knowledge chain determines the service 2 by the evaluation content of the user 1.
And a second knowledge chain, determining a friend user 2 through portrait information of the user 1, and determining a service 2 through browsing content of the user 2.
And a third knowledge chain, determining the service 1 through the browse content of the user 1. By co-browsing the users 2 of the service 1, the service 2 is determined.
And a knowledge chain IV, wherein the service 1 is determined through browsing of the user 1, the company 1 is determined through attribution of the service 1, and the travel service which belongs to the company 2 is determined as the service 2.
And fifthly, determining the service 1 through browsing of the user 1, determining the site 1 according to the position of the service 1, and determining the travel service at the same site as the service 2.
And a knowledge chain six, determining the service 1 through browsing of the user 1, determining the consumption 1 according to the consumption condition of the service 1, and determining the travel service with similar consumption condition as the service 2.
And a knowledge chain seven, determining that the user occupation is occupation 1 through the portrait information of the user 1, determining the user 2 with the same occupation according to the occupation 1, and determining the service 2 according to the browsing content of the user 2.
Knowledge chain eight, through positive emotion in rating 1 that user 1 composes, confirm service 1, according to rating 2 that also has positive emotion, confirm user 2 that composes rating 2, according to user's 2 browse content, confirm service 2.
Knowledge chain nine, through the content in rating 1 written by user 1, determines the mentioned product 1, determines user 2 who is writing rating 2 from rating 2 which is also referring to product 1, and determines service 2 from the browsed content of user 2.
Knowledge chain ten, service 1 and product are determined by the ratings and the mentioned content in rating 1 written by user 1. Based on the rating 2 having similar ratings and content references to service 1 and the product, user 2 composing rating 2 is determined, and service 2 is determined based on the browsed content of user 2.
Step S208, converting the knowledge chain group into a multidimensional feature matrix.
And determining a target recommended travel service according to the knowledge chain group, and calculating after matrixing the knowledge chain group.
Optionally, as shown in fig. 7, the step S208 of converting the knowledge chain set into the multidimensional feature matrix includes five specific implementation steps of steps S2081, S2082, S2083, S2084 and S2085:
step S2081, extracting user characteristic information and travel service information corresponding to each knowledge chain in the knowledge chain group.
The knowledge chain group comprises a plurality of groups of knowledge chains, each knowledge chain is equivalent to a group of 'user-service' pairs, and a first entity and a second entity at two ends of the knowledge chain respectively serve as user characteristic information and travel service information. And extracting the first entity and the second entity at the two ends of the knowledge chain to obtain the user characteristic information and the travel service information.
Step S2082, a plurality of first feature rectangles are generated according to the corresponding user feature information.
Step S2083, a plurality of second feature matrices are generated according to the corresponding travel service information.
Step S2084, each first feature rectangle and each second feature rectangle are correspondingly combined into a plurality of feature matrixes.
Step S2085, combining the feature matrices into a multi-dimensional feature matrix.
Specifically, the user characteristic information and the travel service information are respectively matrixed, wherein the user characteristic information is represented by u, the travel service information is represented by b, and the ith user characteristic information is u i Travel service information b i . Combining the user characteristic information and the travel service information to obtain L groups of characteristics, wherein L is the number of knowledge chains in a preset knowledge chain group, as shown in formula 1:
where F is the rank of the matrix, u i (l) And b j (l) Representing user characteristic information and travel service information extracted from the first knowledge chain, respectively. Different fromThe rank of the feature matrix is different, and the feature matrix is fixed to the same value in this embodiment. X is x n Representing the feature vector of the nth sample after combination. Each user-service pair may be represented by an L x F dimensional feature matrix.
Step S209, training a recommendation model matched with the user characteristic information by utilizing the multidimensional characteristic matrix.
After the multidimensional feature matrix is generated, modeling is carried out on the second-order relation among features, and the low-rank decomposition of the second-order parameters is shown as a formula (2):
wherein w is 0 Is a bias, d=2lf represents all features of the matrix consisting of L and knowledge chain, w e R d Represents a first order parameter, v= [ V ] i ]∈R d×k Representing the second order parameter of cross-point multiplication of different parameters, v i Represents the ith row, x of matrix V i n Is x n I-th feature of (a). The parameters are learned by minimizing the mean square loss function as shown in equation (3):
in which y n Obtained from the nth sample, N is the total number of samples.
Optionally, some implicit features between the user and the service are constructed by a knowledge chain mode, in order to prevent the training result from being overfitted, the embodiment can solve the problem of feature combination under the sparse matrix by utilizing a decomposition factor machine mode, eliminate useless knowledge chains, discard feature groups useless for similarity calculation, optimize an objective function to be a non-convex and non-smooth problem, and the regularized second-order relationship is shown as a formula (4):
phi in v And phi w The first-order parameter and the second-order parameter are regularized respectively, and finally iterative computation is carried out through a near-end gradient method. And obtaining first-order and second-order parameters through iterative training, when a new user is input, putting knowledge bands formed by the user and the commodity into a model to obtain user-service similarity, and finally outputting the association probability of the user and the service, wherein the larger the probability is, the tighter the description relationship is, the sorting is carried out according to the probability, and the recommendation is carried out with the ranking being top.
Step S210, inputting the user characteristic information into a recommendation model to obtain the output target travel service information.
After the recommendation model is obtained, specific user characteristic information is input into the recommendation model, and the target travel service matched with the requirements of the target user is obtained.
In the embodiment, feature extraction is performed on the portrait information and the user operation of the user in the interaction process, the user group features and the interest information are collected, and a knowledge chain is constructed by combining a knowledge graph algorithm, so that in the continuous interaction process of the system and the user, data are collected in real time, processed, analyzed and inferred, recommended content is fed back in time according to user bias, content quality is optimized, system content which is more matched with the cognitive requirements of the user is provided, the man-machine interaction process is more intelligent, user satisfaction is improved, and user experience is optimized.
Fig. 8 is a schematic structural diagram of a travel service recommendation device according to an embodiment of the present invention, and as shown in fig. 8, the travel service recommendation device 3 according to the present embodiment includes:
the user characteristic obtaining module 31 is configured to obtain user characteristic information of the target user.
The knowledge chain set extraction module 32 is configured to extract a knowledge chain set from a preset travel knowledge graph according to the user feature information.
The travel service calculation module 33 is configured to calculate, according to the knowledge chain set, target travel service information matched with the user feature information.
The travel service recommendation module 34 recommends the target travel service information to the target user.
The user feature acquisition module 31, the knowledge chain set extraction module 32, the travel service calculation module 33 and the travel service recommendation module 34 are sequentially connected. The travel service recommending device 3 provided in this embodiment may execute the technical scheme of the method embodiment shown in fig. 2, and its implementation principle and technical effect are similar, and will not be described herein again.
Fig. 9 is a schematic structural diagram of a travel service recommendation device according to another embodiment of the present invention, as shown in fig. 9, where the travel service recommendation device 4 according to this embodiment further includes a knowledge graph construction module 41 for:
acquiring priori knowledge of the travel service.
And constructing a travel knowledge graph according to the prior knowledge of the travel service.
Optionally, the user feature acquisition module 31 is specifically configured to:
and obtaining portrait information and interest information of the target user.
User characteristic information of the target user is determined according to the portrait information and the interest information.
Optionally, the user feature acquisition module 31 is specifically configured to, when acquiring portrait information of a target user:
and acquiring the identity information of the target user.
And classifying the target users according to the identity information of the target users, and determining the group category of the target users.
And determining portrait information of the target user according to the group category.
Optionally, the user feature acquisition module 31 is specifically configured to, when acquiring interest information of the target user:
and acquiring browsing information and comment information of the target user.
And determining interest information of the target user according to the browsing information and comment information of the target user.
Alternatively, the user feature acquisition module 31 is specifically configured to, when determining the interest information of the target user according to the browsing information and the comment information of the target user:
and determining the interest field of the target user according to the browsing information of the target user.
And determining interest information of the target user according to the comment information of the target user in the interest field.
Accordingly, the user feature acquisition module 31 is specifically configured to, when determining the user feature information of the target user according to the portrait information and the interest information:
the portrait information and the interest information are determined as user feature information.
Optionally, the knowledge graph includes a plurality of knowledge chains, the knowledge chains are used for mapping relationships between users corresponding to different user feature information and travel service information, and the knowledge chain group extraction module 32 is specifically configured to:
and determining a target knowledge chain related to the user characteristic information in the knowledge graph.
And extracting a preset number of target knowledge chains from the knowledge graph to generate a knowledge chain group.
Optionally, the hotel services calculation module 33 is specifically configured to:
and converting the knowledge chain group into a multidimensional feature matrix.
And training a recommendation model matched with the user characteristic information by utilizing the multidimensional characteristic matrix.
And inputting the user characteristic information into a recommendation model to obtain the output target travel service information.
Optionally, the hotel services computing module 33 is specifically configured to, when converting the knowledge chain set into the multidimensional feature matrix:
and extracting user characteristic information and travel service information corresponding to each knowledge chain in the knowledge chain group.
And generating a plurality of first feature rectangles according to the corresponding user feature information.
And generating a plurality of second feature matrixes according to the corresponding travel service information.
And correspondingly combining each first characteristic rectangle and each second characteristic rectangle into a plurality of characteristic matrixes.
The plurality of feature matrices are combined into a multi-dimensional feature matrix.
The knowledge graph construction module 41, the user feature acquisition module 31, the knowledge link set extraction module 32, the travel service calculation module 33 and the travel service recommendation module 34 are sequentially connected. The travel service recommending device 4 provided in this embodiment may execute the technical scheme of the method embodiment shown in fig. 3 to 7, and its implementation principle and technical effect are similar, and will not be described herein again.
Fig. 10 is a schematic diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 10, where the electronic device provided in the embodiment includes: memory 51, processor 52 and computer program.
Wherein a computer program is stored in the memory 51 and configured to be executed by the processor 52 to implement the method for recommending a travel service provided by any of the embodiments of the present invention corresponding to fig. 2-7.
Wherein the memory 51 and the processor 52 are connected by a bus 53.
The description may be understood correspondingly with reference to the description and effects corresponding to the steps of fig. 2 to fig. 7, which are not repeated here.
An embodiment of the present invention provides a computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method for recommending a travel service according to any of the embodiments corresponding to fig. 2-7 of the present invention.
The computer readable storage medium may be, among other things, ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It is to be understood that the invention is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. A method of travel service recommendation, the method comprising:
acquiring user characteristic information of a target user;
extracting a knowledge chain group from a preset travel knowledge graph according to the user characteristic information;
calculating target travel service information matched with the user characteristic information according to the knowledge chain group;
recommending the target travel service information to the target user;
and calculating target travel service information matched with the user characteristic information according to the knowledge chain group, wherein the target travel service information comprises the following steps:
converting the knowledge chain set into a multidimensional feature matrix;
training a recommendation model matched with the user characteristic information by utilizing the multidimensional characteristic matrix;
inputting the user characteristic information into the recommendation model to obtain output target travel service information;
the converting the knowledge chain group into a multidimensional feature matrix comprises the following steps:
extracting user characteristic information and travel service information corresponding to each knowledge chain in the knowledge chain group;
Generating a plurality of first feature rectangles according to the corresponding user feature information;
generating a plurality of second feature matrixes according to the corresponding travel service information;
correspondingly combining each first characteristic rectangle and each second characteristic rectangle into a plurality of characteristic matrixes;
and combining the plurality of feature matrices into a multi-dimensional feature matrix.
2. The method of claim 1, wherein the obtaining user characteristic information of the target user comprises:
acquiring portrait information and interest information of the target user;
and determining user characteristic information of the target user according to the portrait information and the interest information.
3. The method of claim 2, wherein the obtaining portrait information of the target user includes:
acquiring identity information of a target user;
classifying the target users according to the identity information of the target users, and determining the group category of the target users;
and determining portrait information of the target user according to the group category.
4. A method according to claim 3, wherein said obtaining interest information of said target user comprises:
acquiring browsing information and comment information of the target user;
And determining interest information of the target user according to the browsing information and comment information of the target user.
5. The method of claim 4, wherein the determining interest information of the target user based on the browsing information and comment information of the target user comprises:
according to the browsing information of the target user, determining the interest field of the target user;
determining interest information of the target user according to the comment information of the target user in the interest field;
correspondingly, the determining the user characteristic information of the target user according to the portrait information and the interest information comprises the following steps:
and determining the portrait information and the interest information as the user characteristic information.
6. The method according to claim 1, wherein the knowledge graph includes a plurality of knowledge chains, the knowledge chains are used for mapping relationships between users corresponding to different user feature information and travel service information, and the extracting a knowledge chain group from a preset travel knowledge graph according to the user feature information includes:
determining a target knowledge chain related to the user characteristic information in a knowledge graph;
And extracting a preset number of target knowledge chains from the knowledge graph to generate a knowledge chain group.
7. The method of claim 1, further comprising, prior to said obtaining user characteristic information of the target user:
acquiring priori knowledge of a text travel service;
and constructing a travel knowledge graph according to the travel service priori knowledge.
8. A travel service recommendation device, the device comprising:
the user characteristic acquisition module is used for acquiring user characteristic information of a target user;
the knowledge chain set extraction module is used for extracting a knowledge chain set from a preset travel knowledge graph according to the user characteristic information;
the travel service calculation module is used for calculating target travel service information matched with the user characteristic information according to the knowledge chain group;
the travel service recommending module is used for recommending the target travel service information to the target user;
the travel service calculation module is specifically used for converting the knowledge chain group into a multidimensional feature matrix;
training a recommendation model matched with the user characteristic information by utilizing the multidimensional characteristic matrix;
inputting the user characteristic information into the recommendation model to obtain output target travel service information;
The travel service calculation module is specifically configured to, when converting the knowledge chain set into a multidimensional feature matrix:
extracting user characteristic information and travel service information corresponding to each knowledge chain in the knowledge chain group;
generating a plurality of first feature rectangles according to the corresponding user feature information;
generating a plurality of second feature matrixes according to the corresponding travel service information;
correspondingly combining each first characteristic rectangle and each second characteristic rectangle into a plurality of characteristic matrixes;
and combining the plurality of feature matrices into a multi-dimensional feature matrix.
9. An electronic device, comprising: a memory, a processor, and a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the travel service recommendation method of any one of claims 1-7.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are for implementing the travel service recommendation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911404349.0A CN111177559B (en) | 2019-12-30 | 2019-12-30 | Text travel service recommendation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911404349.0A CN111177559B (en) | 2019-12-30 | 2019-12-30 | Text travel service recommendation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111177559A CN111177559A (en) | 2020-05-19 |
| CN111177559B true CN111177559B (en) | 2023-05-30 |
Family
ID=70655879
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911404349.0A Active CN111177559B (en) | 2019-12-30 | 2019-12-30 | Text travel service recommendation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111177559B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738414B (en) * | 2020-06-11 | 2023-04-07 | 北京百度网讯科技有限公司 | Recommendation model generation method, content recommendation method, device, equipment and medium |
| CN112348638B (en) * | 2020-11-09 | 2024-02-20 | 上海秒针网络科技有限公司 | Activity document recommending method and device, electronic equipment and storage medium |
| CN113837846B (en) * | 2021-10-27 | 2023-09-22 | 武汉卓尔数字传媒科技有限公司 | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium |
| CN114817737B (en) * | 2022-05-13 | 2024-01-02 | 北京世纪超星信息技术发展有限责任公司 | Cultural relic hot spot pushing method and system based on knowledge graph |
| CN115018474B (en) * | 2022-08-03 | 2022-11-08 | 山东美丽乡村云计算有限公司 | Text and travel consumption heat degree analysis method based on big data |
| CN117891352B (en) * | 2024-03-14 | 2024-05-31 | 南京市文化投资控股集团有限责任公司 | Meta universe-based travel content recommendation system and method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794232A (en) * | 2015-05-04 | 2015-07-22 | 百度在线网络技术（北京）有限公司 | Recommendation method and device for search results |
| CN107729444A (en) * | 2017-09-30 | 2018-02-23 | 桂林电子科技大学 | Recommend method in a kind of personalized tourist attractions of knowledge based collection of illustrative plates |
| WO2018072071A1 (en) * | 2016-10-18 | 2018-04-26 | 浙江核新同花顺网络信息股份有限公司 | Knowledge map building system and method |
| CN109977283A (en) * | 2019-03-14 | 2019-07-05 | 中国人民大学 | A kind of the tourism recommended method and system of knowledge based map and user's footprint |
| CN110188248A (en) * | 2019-05-28 | 2019-08-30 | 新华网股份有限公司 | Data processing method, device and electronic equipment based on news question and answer interactive system |
| CN110287336A (en) * | 2019-06-19 | 2019-09-27 | 桂林电子科技大学 | A kind of tourist's portrait construction method recommended towards tourist attractions |
| CN110473521A (en) * | 2019-02-26 | 2019-11-19 | 北京蓦然认知科技有限公司 | A kind of training method of task model, device, equipment |
-
2019
- 2019-12-30 CN CN201911404349.0A patent/CN111177559B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794232A (en) * | 2015-05-04 | 2015-07-22 | 百度在线网络技术（北京）有限公司 | Recommendation method and device for search results |
| WO2018072071A1 (en) * | 2016-10-18 | 2018-04-26 | 浙江核新同花顺网络信息股份有限公司 | Knowledge map building system and method |
| CN107729444A (en) * | 2017-09-30 | 2018-02-23 | 桂林电子科技大学 | Recommend method in a kind of personalized tourist attractions of knowledge based collection of illustrative plates |
| CN110473521A (en) * | 2019-02-26 | 2019-11-19 | 北京蓦然认知科技有限公司 | A kind of training method of task model, device, equipment |
| CN109977283A (en) * | 2019-03-14 | 2019-07-05 | 中国人民大学 | A kind of the tourism recommended method and system of knowledge based map and user's footprint |
| CN110188248A (en) * | 2019-05-28 | 2019-08-30 | 新华网股份有限公司 | Data processing method, device and electronic equipment based on news question and answer interactive system |
| CN110287336A (en) * | 2019-06-19 | 2019-09-27 | 桂林电子科技大学 | A kind of tourist's portrait construction method recommended towards tourist attractions |
Non-Patent Citations (1)
| Title |
|---|
| 基于知识图谱和用户长短期偏好的个性化景点推荐;贾中浩;《智能***学报》;20190906;第990-997页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111177559A (en) | 2020-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111177559B (en) | Text travel service recommendation method and device, electronic equipment and storage medium | |
| US20210271975A1 (en) | User tag generation method and apparatus, storage medium, and computer device | |
| CN111553754B (en) | Updating method and device of behavior prediction system | |
| US9785888B2 (en) | Information processing apparatus, information processing method, and program for prediction model generated based on evaluation information | |
| Merialdo | Clustering for collaborative filtering applications | |
| Chen et al. | General functional matrix factorization using gradient boosting | |
| CN111177538B (en) | User interest label construction method based on unsupervised weight calculation | |
| CN112765480B (en) | Information pushing method and device and computer readable storage medium | |
| Sen et al. | A total error framework for digital traces of humans | |
| CN111898031A (en) | Method and device for obtaining user portrait | |
| CN110474944B (en) | Network information processing method, device and storage medium | |
| Hong-Xia | An improved collaborative filtering recommendation algorithm | |
| CN111858972A (en) | Movie recommendation method based on family knowledge graph | |
| CN112733035A (en) | Knowledge point recommendation method and device based on knowledge graph, storage medium and electronic device | |
| Guo et al. | Calibration of voting-based helpfulness measurement for online reviews: an iterative bayesian probability approach | |
| Grivolla et al. | A hybrid recommender combining user, item and interaction data | |
| CN104572915A (en) | User event relevance calculation method based on content environment enhancement | |
| CN110633410A (en) | Information processing method and device, storage medium, and electronic device | |
| Salehi et al. | Attribute-based recommender system for learning resource by learner preference tree | |
| CN111882224A (en) | Method and device for classifying consumption scenes | |
| CN116823410A (en) | Data processing method, object processing method, recommending method and computing device | |
| CN101655853A (en) | Device and method for building model | |
| CN114707510A (en) | Resource recommendation information pushing method and device, computer equipment and storage medium | |
| CN114491296A (en) | Proposal affiliate recommendation method, system, computer device and readable storage medium | |
| CN115186173A (en) | Multimedia resource pushing and intelligent agent network generating method and device |
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 |