CN113407833B - Recommendation method and device for competing hotels, electronic equipment and readable storage medium - Google Patents

Recommendation method and device for competing hotels, electronic equipment and readable storage medium Download PDF

Info

Publication number
CN113407833B
CN113407833B CN202110673880.9A CN202110673880A CN113407833B CN 113407833 B CN113407833 B CN 113407833B CN 202110673880 A CN202110673880 A CN 202110673880A CN 113407833 B CN113407833 B CN 113407833B
Authority
CN
China
Prior art keywords
vector
hotel
target
column
hotels
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
Application number
CN202110673880.9A
Other languages
Chinese (zh)
Other versions
CN113407833A (en
Inventor
邓丽
张钧涛
张猛
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.)
Beijing Joint Wisdom Information Technology Co ltd
Original Assignee
Beijing Joint Wisdom Information Technology Co ltd
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 Beijing Joint Wisdom Information Technology Co ltd filed Critical Beijing Joint Wisdom Information Technology Co ltd
Priority to CN202110673880.9A priority Critical patent/CN113407833B/en
Publication of CN113407833A publication Critical patent/CN113407833A/en
Application granted granted Critical
Publication of CN113407833B publication Critical patent/CN113407833B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • 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
    • G06Q50/12—Hotels or restaurants

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Business, Economics & Management (AREA)
  • Mathematical Physics (AREA)
  • Tourism & Hospitality (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Human Resources & Organizations (AREA)
  • Computing Systems (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Algebra (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Software Systems (AREA)
  • Strategic Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a recommendation method, a recommendation device, electronic equipment and a readable storage medium for competing hotels, wherein firstly, a plurality of candidate hotels with flow direction relations are determined according to historical browsed information of target hotels to be selected; secondly, calculating a target parameter matrix for determining a competing hotel corresponding to the target hotel to be selected based on the determined multiple flow direction parameter vectors of the target hotel to be selected and each candidate hotel under different flow direction dimensions and multiple attribute parameter vectors of the candidate hotels under different attribute dimensions; and finally, determining the hotel competing based on the target parameter matrix, the first relative weight and the second relative weight of the flow direction dimension or the attribute dimension corresponding to each column of feature vector in the determined target parameter matrix. Therefore, the relevant competing hotels can be accurately recommended to the user according to the association characteristics of the target hotels to be selected and the candidate hotels under different flow dimensions, so that the browsing time of the user in the network is reduced.

Description

Recommendation method and device for competing hotels, electronic equipment and readable storage medium
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and apparatus for recommending a hotel in a bid, an electronic device, and a readable storage medium.
Background
With the gradual increase of the technology level, people can reserve a check-in hotel required in the process of going out through a network, and as the competition relationship between hotel industries is increasingly enhanced, hotel managers often need to analyze the competition relationship with the hotel to formulate a coping strategy and the like.
At present, an expert judgment method is needed, namely, the expert evaluates the competition relationship among hotels from a single angle through experience knowledge or a scoring mechanism according to basic attribute data such as geographic positions, star grades, room numbers and the like of the hotels, an evaluation result obtained by the evaluation mode is subjective, and when the number of the hotels is large, a great deal of time is needed to check information of each hotel, and obviously, a great deal of unnecessary time is consumed by a manager.
Disclosure of Invention
In view of the foregoing, an object of the present application is to provide a method, an apparatus, an electronic device, and a readable storage medium for recommending a bid-to-hotel, which can accurately recommend relevant bid-to-hotel to a user according to the association characteristics of a target hotel to be selected and candidate hotels in different streaming dimensions, thereby being beneficial to improving the accuracy of the recommendation result and reducing the browsing time of the user in a network.
The embodiment of the application provides a recommendation method for a hotel competing for, which comprises the following steps:
acquiring historical browsed information of a target hotel to be selected browsed by a user;
determining a plurality of candidate hotels with flow direction relations with the target hotels to be selected based on the historical browsed information;
determining a plurality of flow direction parameter vectors between the target hotel to be selected and each candidate hotel under different flow direction dimensions and a plurality of attribute parameter vectors of the candidate hotels under different attribute dimensions based on the target parameter information of the target hotel to be selected and the candidate parameter information of each candidate hotel;
calculating a target parameter matrix for determining the competing hotel corresponding to the target hotel to be selected based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors;
calculating a column vector average value of each column of feature vectors in the target parameter matrix, and determining a first relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vectors based on the column vector average value of the each column of feature vectors;
determining a second relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vector in the target parameter matrix based on the target parameter matrix and a preset orthogonal variable;
And determining the competing hotels from the candidate hotels based on the target parameter matrix and the first relative weight and the second relative weight of the flow direction dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix.
Further, the flow direction parameter vector comprises at least one of an outflow night vector, an inflow night vector, an outflow room average price vector and an inflow room average price vector; the attribute parameter vector includes at least one of a predetermined overnight vector, a predetermined room average value vector, a criticizing score vector, a hotel star level vector, a hotel distance vector, and a room number vector.
Further, the calculating, based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors, a target parameter matrix for determining a competing hotel corresponding to the target hotel to be selected includes:
determining the star level, the number of target rooms, the average price of outflow rooms and the average price of inflow rooms of the target hotel to be selected based on the target parameter information of the target hotel to be selected;
respectively calculating the difference values between the outflow room average value vector and the outflow room average value, the inflow room average value vector and the inflow room average value, the hotel star level vector and the target hotel star level, the preset room average value vector and the target room average value and the room quantity vector and the target room quantity, and obtaining calculated outflow room average value vector, inflow room average value vector, hotel star level vector, preset room average value vector and room quantity vector;
Respectively carrying out feature normalization processing on the outflow night vector, the inflow night vector, the preset night vector, the criticizing score vector, the hotel distance vector, the calculated outflow room average price vector, the inflow room average price vector, the hotel star level vector, the preset room average price vector and the room number vector to obtain normalized outflow night vector, inflow night vector, preset night vector, criticizing score vector, hotel distance vector, outflow room average price vector, inflow room average price vector, hotel star level vector, preset room average price vector and room number vector;
and based on the normalized outflow night vector, the inflow night vector, the predetermined night vector, the scoring vector, the hotel distance vector, the outflow room average price vector, the inflow room average price vector, the hotel star level vector and the predetermined room average price vector, the target parameter matrix of the target hotel to be selected is obtained by splicing.
Further, the determining, based on the historical browsed information, a plurality of candidate hotels having a flow direction relationship with the target hotels to be selected includes:
based on the historical browsed information, determining hotels with a client inflow relation and/or a client outflow relation with the target hotels to be selected as hotels to be screened;
Determining the outflow quantity of the clients from the target hotels to be selected to each hotel to be screened and the inflow quantity of the clients from each hotel to be screened to the target hotels to be selected;
and determining the hotels to be screened, of which the outflow quantity is greater than a preset outflow threshold value and/or the inflow quantity is greater than a preset inflow threshold value, as candidate hotels.
Further, the calculating a column vector average value of each column of feature vectors in the target parameter matrix, and determining a first relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vectors based on the column vector average value of the column of feature vectors includes:
calculating a column vector average value of each column of feature vectors in the target parameter matrix, comparing the column vector average value of the column of feature vectors with the column vector average value of each column of feature vectors in the target parameter matrix aiming at each column of feature vectors, and determining a comparison result between the column of feature vectors and each column of feature vectors;
and based on each determined comparison result, calculating to obtain a first relative weight of the flow direction dimension or the attribute dimension corresponding to the column of feature vectors.
Further, the determining, based on the target parameter matrix and a preset orthogonal variable, a second relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vectors in the target parameter matrix includes:
For each column of feature vectors in the target parameter matrix, determining a second relative weight of a flow direction dimension or an attribute dimension corresponding to the column of feature vectors based on the column of feature vectors and a preset orthogonal variable.
Further, the determining, based on the target parameter matrix and the first relative weight and the second relative weight of the flow direction dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix, the competing hotel from the candidate hotels includes:
for each column of feature vectors in the target parameter matrix, calculating to obtain the combination weight of the corresponding flow direction dimension or attribute dimension of the column of feature vectors based on the first relative weight and the second relative weight of the corresponding flow direction dimension or attribute dimension of the column of feature vectors;
for each candidate hotel, calculating to obtain an evaluation value of the candidate hotel based on a row feature vector corresponding to the candidate hotel in the target parameter matrix and a combination weight of a flow dimension or an attribute dimension corresponding to each feature element in the row feature vector;
and determining the competing hotel of the target hotel to be selected from the candidate hotels based on the calculated evaluation values of the candidate hotels.
Further, after determining the competing hotel from the plurality of candidate hotels based on the hotel score vector, the recommendation method further includes:
and determining a display level of each competing hotel based on the evaluation value of each competing hotel, and displaying each competing hotel to the user according to the display level.
Further, the display hierarchy for each competing hotel is determined by:
determining an evaluation difference between each two competing hotels based on the evaluation score of each competing hotel;
determining a maximum evaluation difference value from the determined plurality of evaluation difference values, and determining a secondary evaluation difference value which is the largest in the plurality of evaluation difference values except for the maximum evaluation difference value;
determining a score range for each display tier based on the maximum evaluation difference and the secondary evaluation difference;
based on the assessment score of each competing hotel, a display hierarchy to which the competing hotel belongs is determined.
The embodiment of the application also provides a recommendation device for competing hotels, which comprises:
the information acquisition module is used for acquiring historical browsed information of the target hotel to be selected browsed by the user;
the candidate hotel determining module is used for determining a plurality of candidate hotels with flow direction relations with the target hotels to be selected based on the historical browsed information;
The first vector determining module is used for determining a plurality of flow direction parameter vectors under different flow direction dimensions and a plurality of attribute parameter vectors under different attribute dimensions of the plurality of candidate hotels between the target hotels to be selected and each candidate hotel based on the target parameter information of the target hotels to be selected and the candidate parameter information of each candidate hotel;
the second vector determining module is used for calculating a target parameter matrix for determining the competing hotel corresponding to the target hotel to be selected based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors;
the first weight determining module is used for calculating the column vector average value of each column of feature vectors in the target parameter matrix and determining the first relative weight of the flow direction dimension or attribute dimension corresponding to each column of feature vectors based on the column vector average value of the feature vectors;
the second weight determining module is used for determining second relative weights of the flow direction dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix based on the target parameter matrix and the preset orthogonal variable;
and the hotel competing determination module is used for determining the hotel competing from the candidate hotels based on the target parameter matrix and the first relative weight and the second relative weight of the flow dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix.
Further, the flow direction parameter vector comprises at least one of an outflow night vector, an inflow night vector, an outflow room average price vector and an inflow room average price vector; the attribute parameter vector includes at least one of a predetermined overnight vector, a predetermined room average value vector, a criticizing score vector, a hotel star level vector, a hotel distance vector, and a room number vector.
Further, when the second vector determining module is configured to calculate, based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors, a target parameter matrix for determining a competing hotel corresponding to the target hotel to be selected, the second vector determining module is configured to:
determining the star level, the number of target rooms, the average price of outflow rooms and the average price of inflow rooms of the target hotel to be selected based on the target parameter information of the target hotel to be selected;
respectively calculating the difference values between the outflow room average value vector and the outflow room average value, the inflow room average value vector and the inflow room average value, the hotel star level vector and the target hotel star level, the preset room average value vector and the target room average value and the room quantity vector and the target room quantity, and obtaining calculated outflow room average value vector, inflow room average value vector, hotel star level vector, preset room average value vector and room quantity vector;
Respectively carrying out feature normalization processing on the outflow night vector, the inflow night vector, the preset night vector, the criticizing score vector, the hotel distance vector, the calculated outflow room average price vector, the inflow room average price vector, the hotel star level vector, the preset room average price vector and the room number vector to obtain normalized outflow night vector, inflow night vector, preset night vector, criticizing score vector, hotel distance vector, outflow room average price vector, inflow room average price vector, hotel star level vector, preset room average price vector and room number vector;
and based on the normalized outflow night vector, the inflow night vector, the predetermined night vector, the scoring vector, the hotel distance vector, the outflow room average price vector, the inflow room average price vector, the hotel star level vector and the predetermined room average price vector, the target parameter matrix of the target hotel to be selected is obtained by splicing.
Further, when the candidate hotel determination module is configured to determine, based on the historical browsed information, that there is a plurality of candidate hotels in a flow direction relationship with the target hotel to be selected, the candidate hotel determination module is configured to:
Based on the historical browsed information, determining hotels with a client inflow relation and/or a client outflow relation with the target hotels to be selected as hotels to be screened;
determining the outflow quantity of the clients from the target hotels to be selected to each hotel to be screened and the inflow quantity of the clients from each hotel to be screened to the target hotels to be selected;
and determining the hotels to be screened, of which the outflow quantity is greater than a preset outflow threshold value and/or the inflow quantity is greater than a preset inflow threshold value, as candidate hotels.
Further, when the first weight determining module is configured to calculate a column vector average value of each column of feature vectors in the target parameter matrix, and determine a first relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vectors based on the column vector average value of the column of feature vectors, the first weight determining module is configured to:
calculating a column vector average value of each column of feature vectors in the target parameter matrix, comparing the column vector average value of the column of feature vectors with the column vector average value of each column of feature vectors in the target parameter matrix aiming at each column of feature vectors, and determining a comparison result between the column of feature vectors and each column of feature vectors;
And based on each determined comparison result, calculating to obtain a first relative weight of the flow direction dimension or the attribute dimension corresponding to the column of feature vectors. Further, when the second weight determining module is configured to determine, based on the target parameter matrix and a preset orthogonal variable, a second relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vector in the target parameter matrix, the second weight determining module is configured to:
for each column of feature vectors in the target parameter matrix, determining a second relative weight of a flow direction dimension or an attribute dimension corresponding to the column of feature vectors based on the column of feature vectors and a preset orthogonal variable.
Further, when the competing hotel determining module is configured to determine, based on the target parameter matrix and the first relative weight and the second relative weight of the flow direction dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix, a competing hotel from the candidate hotels, the competing hotel determining module is configured to:
for each column of feature vectors in the target parameter matrix, calculating to obtain the combination weight of the corresponding flow direction dimension or attribute dimension of the column of feature vectors based on the first relative weight and the second relative weight of the corresponding flow direction dimension or attribute dimension of the column of feature vectors;
For each candidate hotel, calculating to obtain an evaluation value of the candidate hotel based on a row feature vector corresponding to the candidate hotel in the target parameter matrix and a combination weight of a flow dimension or an attribute dimension corresponding to each feature element in the row feature vector;
and determining the competing hotel of the target hotel to be selected from the candidate hotels based on the calculated evaluation values of the candidate hotels.
Further, the recommending device further comprises a hierarchical display module, wherein the hierarchical display module is used for:
and determining a display level of each competing hotel based on the evaluation value of each competing hotel, and displaying each competing hotel to the user according to the display level.
Further, the hierarchy display module is configured to determine a display hierarchy for each competing hotel by:
determining an evaluation difference between each two competing hotels based on the evaluation score of each competing hotel;
determining a maximum evaluation difference value from the determined plurality of evaluation difference values, and determining a secondary evaluation difference value which is the largest in the plurality of evaluation difference values except for the maximum evaluation difference value;
determining a score range for each display tier based on the maximum evaluation difference and the secondary evaluation difference;
Based on the assessment score of each competing hotel, a display hierarchy to which the competing hotel belongs is determined.
The embodiment of the application also provides electronic equipment, which comprises: the system comprises a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, the processor and the memory are communicated through the bus when the electronic device is running, and the machine-readable instructions are executed by the processor to perform the steps of the recommended method for competing for hotels.
Embodiments of the present application also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of recommending a hotel for a hotel as described above.
The method, the device, the electronic equipment and the readable storage medium for recommending the competing hotels acquire historical browsed information of the target hotels to be selected browsed by the user; determining a plurality of candidate hotels with flow direction relations with the target hotels to be selected based on the historical browsed information; determining a plurality of flow direction parameter vectors between the target hotel to be selected and each candidate hotel under different flow direction dimensions and a plurality of attribute parameter vectors of the candidate hotels under different attribute dimensions based on the target parameter information of the target hotel to be selected and the candidate parameter information of each candidate hotel; calculating a target parameter matrix for determining the competing hotel corresponding to the target hotel to be selected based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors; calculating a column vector average value of each column of feature vectors in the target parameter matrix, and determining a first relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vectors based on the column vector average value of the each column of feature vectors; determining a second relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vector in the target parameter matrix based on the target parameter matrix and a preset orthogonal variable; and determining the competing hotels from the candidate hotels based on the target parameter matrix and the first relative weight and the second relative weight of the flow direction dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix. Therefore, the relevant competing hotels can be accurately recommended to the user according to the association characteristics of the target hotels to be selected and the candidate hotels under different flow dimensions, the accuracy of the recommendation result is improved, and the browsing time of the user in the network can be reduced.
In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for recommending a hotel for a bid according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a recommended device for competing for hotels according to an embodiment of the present application;
fig. 3 is a second schematic structural diagram of a recommendation device for a hotel competing according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as provided in the accompanying drawings, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. Based on the embodiments of the present application, every other embodiment that a person skilled in the art would obtain without making any inventive effort is within the scope of protection of the present application.
According to research, at present, an expert judgment method is needed, namely, the expert evaluates the competition relationship among hotels from a single angle through experience knowledge or scoring mechanism according to basic attribute data such as geographic positions, star grades and room numbers of the hotels, the evaluation result obtained by the evaluation mode is subjective, and when the number of the hotels is large, a large amount of time is needed to check each hotel information, and obviously, a large amount of unnecessary time is consumed by a manager.
Based on the above, the embodiment of the application provides a recommendation method for a hotel in competition, which can accurately determine the recommended hotel in competition from a plurality of candidate hotels.
Referring to fig. 1, fig. 1 is a flowchart of a method for recommending a hotel in a bid according to an embodiment of the present application. As shown in fig. 1, the method for recommending a hotel in a bid provided by the embodiment of the application includes:
s101, acquiring historical browsed information of a target hotel to be selected browsed by a user.
S102, determining a plurality of candidate hotels with flow direction relations with the target hotels to be selected based on the historical browsed information.
S103, determining a plurality of flow direction parameter vectors of the target hotel to be selected and each candidate hotel under different flow direction dimensions and a plurality of attribute parameter vectors of the candidate hotels under different attribute dimensions based on the target parameter information of the target hotel to be selected and the candidate parameter information of each candidate hotel.
And S104, calculating a target parameter matrix for determining the competing hotel corresponding to the target hotel to be selected based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors.
S105, calculating a column vector average value of each column of feature vectors in the target parameter matrix, and determining a first relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vectors based on the column vector average value of each column of feature vectors.
S106, determining second relative weights of the flow direction dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix based on the target parameter matrix and the preset orthogonal variables.
And S107, determining the competing hotels from the candidate hotels based on the target parameter matrix and the first relative weight and the second relative weight of the flow direction dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix.
Here, a user may refer to a staff of a hotel, and when the staff of the hotel wants to determine a competing hotel of the hotels where the staff of the hotel works, the staff of the hotel generally needs to traverse all hotels in the browsing network, so as to select other hotels having competitiveness.
The user can also refer to a hotel reservation passenger, and when the passenger wants to reserve a hotel in the journey, the passenger can determine the hotel to reserve after a large amount of browsing.
In step S101, historical browsed information of a target hotel to be selected browsed by a user is acquired.
In the step, historical browsed information of the target hotel to be selected, which is currently browsed by the user, is obtained, wherein the historical browsed information comprises browsing information of other users who browse the target hotel to be selected, and the browsing information of the other users comprises browsing or booking other hotels before browsing the target hotel to be selected, browsing or booking other hotels after browsing the target hotel to be selected, and the like.
The flow direction relation comprises a client inflow relation and a client outflow relation, wherein the client outflow relation refers to a client outflow relation between a target hotel to be selected and a candidate hotel after a user browses the target hotel to be selected and reserves the candidate hotel; the client inflow relationship refers to that after browsing the candidate hotel, a target hotel to be selected is reserved, and then the client inflow relationship exists between the target hotel to be selected and the candidate hotel.
In one embodiment, step S102 includes: based on the historical browsed information, determining hotels with a client inflow relation and/or a client outflow relation with the target hotels to be selected as hotels to be screened; determining the outflow quantity of the clients from the target hotels to be selected to each hotel to be screened and the inflow quantity of the clients from each hotel to be screened to the target hotels to be selected; and determining the hotels to be screened, of which the outflow quantity is greater than a preset outflow threshold value and/or the inflow quantity is greater than a preset inflow threshold value, as candidate hotels.
In the above step, according to the historical browsed information of the target hotel to be selected, when other users are determined to subscribe to other hotels after browsing the target hotel to be selected, the other hotels can be determined to be the hotels to be screened, wherein the client outflow relationship exists between the other hotels and the target hotel to be selected; accordingly, when it is determined that other users reserve the target hotel to be selected after browsing other hotels, the other hotels can be determined to be hotels to be screened, wherein the client inflow relationship exists between the other hotels and the target hotel to be selected, so that a plurality of hotels to be screened, which have client inflow relationship and/or client outflow relationship between the other hotels and the target hotel to be selected, are determined.
Specifically, first, for each hotel to be screened having a client outflow relationship with the target hotel to be selected, determining the outflow quantity of clients flowing from the target hotel to be selected to the clients in the hotel to be screened, that is, the quantity of clients who reserve the hotel to be screened after browsing the target hotel to be selected, and determining the hotel to be screened as a candidate hotel when the outflow quantity is greater than a preset outflow threshold.
Secondly, for each hotel to be screened, which has a client inflow relation with the target hotel to be selected, determining the inflow quantity of clients flowing into the target hotel to be selected from the hotel to be screened, namely, the quantity of clients reserving the target hotel to be selected after browsing the hotel to be screened, and determining the hotel to be screened as a candidate hotel when the inflow quantity is larger than a preset inflow threshold value.
In step S103, a plurality of flow direction parameter vectors under different flow direction dimensions between the target hotel to be selected and each candidate hotel and a plurality of attribute parameter vectors under different attribute dimensions of the plurality of candidate hotels are determined based on the target parameter information of the target hotel to be selected and the candidate parameter information of each candidate hotel.
The target parameter information may include target room average prices of all rooms of the target hotel to be selected, target room number of the target hotel to be selected, online scheduled night number of the target hotel to be selected, target hotel star level of the target hotel to be selected, location coordinates of the target hotel to be selected, and score points of the target hotel to be selected in a network platform browsed by the user.
The candidate parameter information may include a candidate room average value of all rooms of the candidate hotel, a candidate room number of the candidate hotel, an online check-in night number of the candidate hotel, a candidate hotel star level of the candidate hotel, a location coordinate of the candidate hotel, and a point score of the candidate hotel in a network platform browsed by the user.
Specifically, the flow direction parameter vector that may be determined according to the target parameter information and the candidate parameter information includes: at least one of an outflow night vector, an inflow night vector, an outflow room average price vector, and an inflow room average price vector; the attribute parameter vector includes at least one of a predetermined overnight vector, a predetermined room average value vector, a criticizing score vector, a hotel star level vector, a hotel distance vector, and a room number vector.
Night vector of outflowThe term "vector" refers to a vector of the amount of night flowing out from the target hotel to be selected to each candidate hotel, that is, a vector of the amount of night ordered in each candidate hotel after the user browses the target hotel to be selected;
the hotel night volume is also called as night number, and is a calculating unit of the room rate of the hotel in a certain time period, and the calculating formula of the hotel night volume is that the night volume=the number of the room to be checked in.
Vector of inflow nightThe term "vector" refers to a vector composed of the amount of night flowing from each candidate hotel into the target hotel to be selected, that is, a vector composed of the amount of night ordered in the target hotel to be selected after the user browses each candidate hotel;
average value vector of outflow houseThe average price of the orders flowing from the target hotel to be selected to each candidate hotel is a vector, namely, after the user browses the target hotel to be selected, the average price of the orders placed in each candidate hotel is a vector;
inflow room average price vectorThe average price of the orders flowing into the target hotel to be selected from each candidate hotel is a vector formed by average prices of the orders placed in the target hotel to be selected after the user browses each candidate hotel;
Predetermined night vectorIs a vector consisting of online scheduled night amounts of each candidate hotel;
reservation house average price vectorIs a vector consisting of average room prices of all candidate hotels;
criticizing score vectorThe system is a vector formed by point score scores of candidate hotels in a network platform browsed by a user;
hotel star level vectorIs a vector composed of star levels of each candidate hotel;
hotel distance vectorIs a vector composed of distances between each candidate hotel and the target hotel to be selected;
room number vectorIs a vector consisting of the total number of rooms for each candidate hotel.
In step S104, a target parameter matrix for determining a competing hotel corresponding to the target hotel to be selected is calculated based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors.
In one embodiment, step S104 further includes: and determining the star level of the target hotel, the number of target rooms, the average price of the outflow rooms and the average price of the inflow rooms of the target hotel to be selected based on the target parameter information of the target hotel to be selected.
The outflow room average price refers to the average price of the rooms of the same type reserved in the candidate hotels after the clients browse the rooms of the target hotels to be selected; the inflow room average price refers to the average price of the rooms of the same type reserved in the target hotel to be selected after the clients browse the rooms of the candidate hotels.
Respectively calculating the difference values between the outflow room average price vector and the outflow room average price, the inflow room average price vector and the inflow room average price, the hotel star level vector and the target hotel star level, the preset room average price vector and the target room average price, and the room quantity vector and the target room quantity, so as to obtain a calculated outflow room average price vectorInflow house average price vector->Hotel star vector->Reservation house average price vectorRoom number vector->
For the outflow night vectors respectivelyThe inflow night vector->The predetermined night vector->The comment score vector->The hotel distance vector->Calculated streamRoom-leaving average price vector->Inflow house average price vector->Hotel star vector->Reservation of the house average vector->Room number vector->And carrying out feature normalization processing to obtain normalized outflow night vectors, inflow night vectors, preset night vectors, comment score vectors, hotel distance vectors, outflow room average price vectors, inflow room average price vectors, hotel star level vectors, preset room average price vectors and room quantity vectors.
Here, the purpose of normalizing the vectors is to normalize the normalized overnight outflow vector Inflow night vector->Criticizing score vector->Room number vector->Inversely proportional to the original value, and the normalized other vector is directly proportional to the original value.
And based on the normalized outflow night vector, the inflow night vector, the predetermined night vector, the scoring vector, the hotel distance vector, the outflow room average price vector, the inflow room average price vector, the hotel star level vector and the predetermined room average price vector, the target parameter matrix of the target hotel to be selected is obtained by splicing.
Here, the column feature vector in the spliced target parameter matrix is a feature value corresponding to each candidate hotel in a certain flow direction dimension or attribute dimension, and the row feature vector is a feature value corresponding to a certain candidate hotel in all flow direction dimensions or attribute dimensions.
In one embodiment, step S105 includes: calculating a column vector average value of each column of feature vectors in the target parameter matrix, comparing the column vector average value of the column of feature vectors with the column vector average value of each column of feature vectors in the target parameter matrix aiming at each column of feature vectors, and determining a comparison result between the column of feature vectors and each column of feature vectors; and based on each determined comparison result, calculating to obtain a first relative weight of the flow direction dimension or the attribute dimension corresponding to the column of feature vectors.
After a target parameter matrix of the target hotel to be selected is obtained, calculating a column vector average value avg_f of each column of feature vectors in the target parameter matrix i i∈[1，l]And l is the column number of the target parameter matrix, the column vector average value of every two column feature vectors is respectively compared, and the comparison result between every column feature vector and every column feature vector in the target parameter matrix is determined, wherein every column feature vector in the target parameter matrix comprises the column feature vector, and when the column feature vector is compared with the column feature vector in the comparison process, the column vector average value between every column feature vector and the column feature vector is considered to be equal, so that one l is the comparison result vector can be determinedWherein, the elements on the diagonal line in the comparison result vector are the comparison result of each column of feature vector and the element; specifically, when the column vector average value of the column feature vectors is greater than the column vector average value of the column feature vectors in the target parameter matrix, the determined comparison result is 1; conversely, when the column vector average value of the column feature vector is smaller than each of the target parameter vectors in the target parameter matrixWhen the vector is the average value, the determined comparison result is 0; when the column vector average value of the column feature vector is equal to the vector average value of each target parameter vector in the target parameter matrix, the determined comparison result is 0.5.
Thus, a contrast result matrix obtained through comparison of the vector meansThe method comprises the following steps:
wherein,avg_f for comparing the elements of the ith row and jth column in the result matrix i Avg_f is the column vector average of the ith column feature vector j And (3) comparing the column vector average value of the jth column feature vector with the column vector average value of the ith column feature vector, wherein l is the column number of the target parameter matrix.
Further, a first relative weight of the flow direction dimension or the attribute dimension corresponding to each column of feature vectors is calculated by the following formula:
wherein q i For the first relative weight of the flow dimension or attribute dimension corresponding to the ith column of feature vectors,for comparing elements of the ith row and jth column of the result matrix.
In one embodiment, step S106 includes: for each column of feature vectors in the target parameter matrix, determining a second relative weight of a flow direction dimension or an attribute dimension corresponding to the column of feature vectors based on the column of feature vectors and a preset orthogonal variable.
Obtaining preset orthogonal variable Z k Establishing each target parameter vector and orthogonal variable Z k Association relation between:
f i ＝α i1 *Z 1 +α i2 *Z 2 +…+α ik *Z k ；
wherein f i For the ith column of eigenvectors in the target parameter matrix, the orthogonal variable Z is used for k Fitting the ith column feature vector alpha i1 Is f i With respect to orthogonal variable Z 1 Fitting coefficient alpha of (a) i2 Is f i With respect to orthogonal variable Z 2 Fitting coefficient alpha of (a) ik Is f i In relation to orthogonal variable Z k Is used for the fitting coefficients of (a).
Further, in determining the ith column feature vector f i After the fitting coefficient of each orthogonal variable Z, based on the fitting coefficients, a second relative weight of the flow direction dimension or the attribute dimension corresponding to the column of feature vectors is calculated by the following formula:
wherein ε i For the second relative weight, alpha, of the flow dimension or attribute dimension corresponding to the ith column of feature vectors in For the ith column feature vector about the orthogonal variable Z n K is the number of orthogonal variables.
Therefore, the method and the device avoid the weight analysis from being out of balance through the combination weight, ensure the neutrality of subjective and objective analysis and improve the scientific reliability of the evaluation result.
In one embodiment, step S107 includes: for each column of feature vectors in the target parameter matrix, calculating to obtain the combination weight of the corresponding flow direction dimension or attribute dimension of the column of feature vectors based on the first relative weight and the second relative weight of the corresponding flow direction dimension or attribute dimension of the column of feature vectors; for each candidate hotel, calculating to obtain an evaluation value of the candidate hotel based on a row feature vector corresponding to the candidate hotel in the target parameter matrix and a combination weight of a flow dimension or an attribute dimension corresponding to each feature element in the row feature vector; and determining the competing hotel of the target hotel to be selected from the candidate hotels based on the calculated evaluation values of the candidate hotels.
In this step, when each target parameter vector f is determined i Is the first relative weight q of (2) i And a second relative weight epsilon i Then, the target parameter vector f is calculated by the following formula i Is a combination weight of (1):
wherein omega i For the ith column feature vector f i Combining weights of corresponding flow dimension or attribute dimension, q i For the ith column feature vector f i First relative weight of corresponding flow dimension or attribute dimension, ε i For the ith column feature vector f i A second relative weight of the corresponding flow dimension or attribute dimension.
As an example, the features represented by the flow dimension or attribute dimension corresponding to the column feature vector may be ranked according to the combining weights, as shown in table 1, table 1 is a feature importance schematic table:
TABLE 1 schematic table of feature importance
Further, the evaluation value of each candidate hotel is calculated by the following formula:
S n ＝g n *W i ；
wherein S is n Assessment score for nth candidate hotel, g n For the target parameter matrix f i Row feature vector corresponding to nth candidate hotel, W i G is g n The combination weight omega corresponding to each element in the list i Is a set of (3).
Finally, determining the competing hotel of the target hotel to be selected from a plurality of candidate hotels based on the calculated evaluation value of each candidate hotel; specifically, candidate hotels with evaluation scores greater than a preset evaluation threshold can be determined as competing hotels of the target hotels to be selected; or, arranging a plurality of candidate hotels in a descending order according to the evaluation values of the candidate hotels, and determining the candidate hotels with the preset number of digits as competing hotels of the target hotels to be selected.
In one embodiment, after the determining a competing hotel from the plurality of candidate hotels based on the hotel score vector, the recommendation method further comprises: and determining a display level of each competing hotel based on the evaluation value of each competing hotel, and displaying each competing hotel to the user according to the display level.
When a display instruction issued by a user is received, determining a display level of each competing hotel according to the evaluation value of each competing hotel, and further displaying each competing hotel to the user one by one according to the display level. Here, the evaluation score of the competing hotel refers to the evaluation score of the candidate hotel corresponding to the competing hotel, where the display level may be preset, specifically, a score range corresponding to each level may be set, and when the evaluation score of the competing hotel falls within the score range corresponding to the level, the level is determined as the display level of the competing hotel.
In one embodiment, the display hierarchy for each competing hotel is determined by: determining an evaluation difference between each two competing hotels based on the evaluation score of each competing hotel; determining a maximum evaluation difference value from the determined plurality of evaluation difference values, and determining a secondary evaluation difference value which is the largest in the plurality of evaluation difference values except for the maximum evaluation difference value; determining a score range for each display tier based on the maximum evaluation difference and the secondary evaluation difference; based on the assessment score of each competing hotel, a display hierarchy to which the competing hotel belongs is determined.
Here, in determining the display hierarchy of each competing hotel, first, the evaluation difference between each two competing hotels is determined separately; secondly, determining the maximum evaluation difference value and the maximum secondary evaluation difference value except the maximum evaluation difference value in the plurality of evaluation difference values from the plurality of determined evaluation difference values; then, determining a score range covered by each display level according to the maximum evaluation difference value and the secondary evaluation difference value; finally, when the evaluation score of a competing hotel is within the score range of the display hierarchy, the competing hotel is displayed in the display hierarchy.
By way of example, suppose, C 1 ，C 2 ，...，C n For n competing hotels ranked by score from high to low, there is a maximum assessment difference absolute value of C Sp (Hotel score difference for location p and Hotel score difference for location p-1), with secondary assessment difference absolute value of C Sq (scoring the difference between the hotel at location q and the hotel at location q-1), where p, q.epsilon.1, n]Grouping the hotels according to the ordering sequence numbers, and then:
the first layer competing hotel is C 1 ，C 2 ，…C min(p，q)-1
The second layer competing hotel is C min(p，q) ，…C max(p，q)-1
The third layer competing hotel is C max(p，q) ，…C n
It should be noted that if only one hotel is competing for the hotel, only 1 layer is displayed; if only two competing hotels exist, the first layer displays one and the second layer displays one.
According to the recommendation method for the competing hotels, historical browsed information of the target hotels to be selected, browsed by the user, is obtained; determining a plurality of candidate hotels with flow direction relations with the target hotels to be selected based on the historical browsed information; determining a plurality of flow direction parameter vectors between the target hotel to be selected and each candidate hotel under different flow direction dimensions and a plurality of attribute parameter vectors of the candidate hotels under different attribute dimensions based on the target parameter information of the target hotel to be selected and the candidate parameter information of each candidate hotel; calculating a target parameter matrix for determining the competing hotel corresponding to the target hotel to be selected based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors; calculating a column vector average value of each column of feature vectors in the target parameter matrix, and determining a first relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vectors based on the column vector average value of the each column of feature vectors; determining a second relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vector in the target parameter matrix based on the target parameter matrix and a preset orthogonal variable; and determining the competing hotels from the candidate hotels based on the target parameter matrix and the first relative weight and the second relative weight of the flow direction dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix. Therefore, the relevant competing hotels can be accurately recommended to the user according to the association characteristics of the target hotels to be selected and the candidate hotels under different flow dimensions, the accuracy of the recommendation result is improved, and the browsing time of the user in the network can be reduced.
Referring to fig. 2 and 3, fig. 2 is a schematic structural diagram of a recommended device for competing with hotels according to an embodiment of the present application, and fig. 3 is a schematic structural diagram of a recommended device for competing with hotels according to an embodiment of the present application. As shown in fig. 2, the recommending apparatus 200 includes:
an information obtaining module 210, configured to obtain historical browsed information of a target hotel to be selected browsed by a user;
a candidate hotel determination module 220, configured to determine, based on the historical browsed information, a plurality of candidate hotels having a flow direction relationship with the target hotels to be selected;
a first vector determining module 230, configured to determine, based on the target parameter information of the target hotel to be selected and the candidate parameter information of each candidate hotel, a plurality of flow direction parameter vectors between the target hotel to be selected and each candidate hotel in different flow direction dimensions and a plurality of attribute parameter vectors of the plurality of candidate hotels in different attribute dimensions;
a second vector determining module 240, configured to calculate, based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors, a target parameter matrix for determining a competing hotel corresponding to the target hotel to be selected;
A first weight determining module 250, configured to calculate a column vector average value of each column of feature vectors in the target parameter matrix, and determine a first relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vectors based on the column vector average value of the column of feature vectors;
a second weight determining module 260, configured to determine, based on the target parameter matrix and a preset orthogonal variable, a second relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vector in the target parameter matrix;
the competing hotel determination module 270 is configured to determine a competing hotel from the candidate hotels based on the target parameter matrix and the first relative weight and the second relative weight of the flow dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix.
Further, as shown in fig. 3, the recommendation device 200 further includes a hierarchical display module 280, where the hierarchical display module 280 is configured to:
and determining a display level of each competing hotel based on the evaluation value of each competing hotel, and displaying each competing hotel to the user according to the display level.
Further, the flow direction parameter vector comprises at least one of an outflow night vector, an inflow night vector, an outflow room average price vector and an inflow room average price vector; the attribute parameter vector includes at least one of a predetermined overnight vector, a predetermined room average value vector, a criticizing score vector, a hotel star level vector, a hotel distance vector, and a room number vector.
Further, when the second vector determining module 240 is configured to calculate, based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors, a target parameter matrix for determining a bid-to-hotel corresponding to the target hotel to be selected, the second vector determining module 240 is configured to:
determining the star level, the number of target rooms, the average price of outflow rooms and the average price of inflow rooms of the target hotel to be selected based on the target parameter information of the target hotel to be selected;
respectively calculating the difference values between the outflow room average value vector and the outflow room average value, the inflow room average value vector and the inflow room average value, the hotel star level vector and the target hotel star level, the preset room average value vector and the target room average value and the room quantity vector and the target room quantity, and obtaining calculated outflow room average value vector, inflow room average value vector, hotel star level vector, preset room average value vector and room quantity vector;
respectively carrying out feature normalization processing on the outflow night vector, the inflow night vector, the preset night vector, the criticizing score vector, the hotel distance vector, the calculated outflow room average price vector, the inflow room average price vector, the hotel star level vector, the preset room average price vector and the room number vector to obtain normalized outflow night vector, inflow night vector, preset night vector, criticizing score vector, hotel distance vector, outflow room average price vector, inflow room average price vector, hotel star level vector, preset room average price vector and room number vector;
And based on the normalized outflow night vector, the inflow night vector, the predetermined night vector, the scoring vector, the hotel distance vector, the outflow room average price vector, the inflow room average price vector, the hotel star level vector and the predetermined room average price vector, the target parameter matrix of the target hotel to be selected is obtained by splicing.
Further, when the candidate hotel determination module 220 is configured to determine, based on the historical browsed information, that there is a plurality of candidate hotels in a flow relationship with the target hotel to be selected, the candidate hotel determination module 220 is configured to:
based on the historical browsed information, determining hotels with a client inflow relation and/or a client outflow relation with the target hotels to be selected as hotels to be screened;
determining the outflow quantity of the clients from the target hotels to be selected to each hotel to be screened and the inflow quantity of the clients from each hotel to be screened to the target hotels to be selected;
and determining the hotels to be screened, of which the outflow quantity is greater than a preset outflow threshold value and/or the inflow quantity is greater than a preset inflow threshold value, as candidate hotels.
Further, when the first weight determining module 250 is configured to calculate a column vector average value of each column of feature vectors in the target parameter matrix, and determine, based on the column vector average value of each column of feature vectors, a first relative weight of a flow direction dimension or an attribute dimension corresponding to the column of feature vectors, the first weight determining module 250 is configured to:
Calculating a column vector average value of each column of feature vectors in the target parameter matrix, comparing the column vector average value of the column of feature vectors with the column vector average value of each column of feature vectors in the target parameter matrix aiming at each column of feature vectors, and determining a comparison result between the column of feature vectors and each column of feature vectors;
and based on each determined comparison result, calculating to obtain a first relative weight of the flow direction dimension or the attribute dimension corresponding to the column of feature vectors.
Further, when the second weight determining module 260 is configured to determine, based on the target parameter matrix and a preset orthogonal variable, a second relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vectors in the target parameter matrix, the second weight determining module 260 is configured to:
for each column of feature vectors in the target parameter matrix, determining a second relative weight of a flow direction dimension or an attribute dimension corresponding to the column of feature vectors based on the column of feature vectors and a preset orthogonal variable.
Further, when the competing hotel determining module 270 is configured to determine, based on the target parameter matrix and the first relative weight and the second relative weight of the flow dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix, a competing hotel from the candidate hotels, the competing hotel determining module 270 is configured to:
For each column of feature vectors in the target parameter matrix, calculating to obtain the combination weight of the corresponding flow direction dimension or attribute dimension of the column of feature vectors based on the first relative weight and the second relative weight of the corresponding flow direction dimension or attribute dimension of the column of feature vectors;
for each candidate hotel, calculating to obtain an evaluation value of the candidate hotel based on a row feature vector corresponding to the candidate hotel in the target parameter matrix and a combination weight of a flow dimension or an attribute dimension corresponding to each feature element in the row feature vector;
and determining the competing hotel of the target hotel to be selected from the candidate hotels based on the calculated evaluation values of the candidate hotels.
Further, the hierarchy display module 280 is configured to determine a display hierarchy of each competing hotel by:
determining an evaluation difference between each two competing hotels based on the evaluation score of each competing hotel;
determining a maximum evaluation difference value from the determined plurality of evaluation difference values, and determining a secondary evaluation difference value which is the largest in the plurality of evaluation difference values except for the maximum evaluation difference value;
determining a score range for each display tier based on the maximum evaluation difference and the secondary evaluation difference;
Based on the assessment score of each competing hotel, a display hierarchy to which the competing hotel belongs is determined.
The recommendation device for the competing hotels acquires historical browsed information of the target hotels to be selected browsed by the user; determining a plurality of candidate hotels with flow direction relations with the target hotels to be selected based on the historical browsed information; determining a plurality of flow direction parameter vectors between the target hotel to be selected and each candidate hotel under different flow direction dimensions and a plurality of attribute parameter vectors of the candidate hotels under different attribute dimensions based on the target parameter information of the target hotel to be selected and the candidate parameter information of each candidate hotel; calculating a target parameter matrix for determining the competing hotel corresponding to the target hotel to be selected based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors; calculating a column vector average value of each column of feature vectors in the target parameter matrix, and determining a first relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vectors based on the column vector average value of the each column of feature vectors; determining a second relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vector in the target parameter matrix based on the target parameter matrix and a preset orthogonal variable; and determining the competing hotels from the candidate hotels based on the target parameter matrix and the first relative weight and the second relative weight of the flow direction dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix. Therefore, the relevant competing hotels can be accurately recommended to the user according to the association characteristics of the target hotels to be selected and the candidate hotels under different flow dimensions, the accuracy of the recommendation result is improved, and the browsing time of the user in the network can be reduced.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 4, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.
The memory 420 stores machine-readable instructions executable by the processor 410, when the electronic device 400 is running, the processor 410 communicates with the memory 420 through the bus 430, and when the machine-readable instructions are executed by the processor 410, the steps of the method for recommending a hotel for a hotel in the method embodiment shown in fig. 1 can be executed, and the specific implementation is referred to the method embodiment and will not be described herein.
The embodiment of the present application further provides a computer readable storage medium, where a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the steps of the method for recommending a hotel for a race in the method embodiment shown in fig. 1 may be executed, and a specific implementation manner may refer to the method embodiment and will not be described herein.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units 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 through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown 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 units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the foregoing examples are merely specific embodiments of the present application, and are not intended to limit the scope of the present application, but the present application is not limited thereto, and those skilled in the art will appreciate that while the foregoing examples are described in detail, the present application is not limited thereto. Any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or make equivalent substitutions for some of the technical features within the technical scope of the disclosure of the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. A recommendation method for a hotel in competition, the recommendation method comprising:
acquiring historical browsed information of a target hotel to be selected browsed by a user;
determining a plurality of candidate hotels with flow direction relations with the target hotels to be selected based on the historical browsed information;
determining a plurality of flow direction parameter vectors between the target hotel to be selected and each candidate hotel under different flow direction dimensions and a plurality of attribute parameter vectors of the candidate hotels under different attribute dimensions based on the target parameter information of the target hotel to be selected and the candidate parameter information of each candidate hotel;
calculating a target parameter matrix for determining the competing hotel corresponding to the target hotel to be selected based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors;
calculating a column vector average value of each column of feature vectors in the target parameter matrix, and determining a first relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vectors based on the column vector average value of the each column of feature vectors;
determining a second relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vector in the target parameter matrix based on the target parameter matrix and a preset orthogonal variable;
And determining the competing hotels from the candidate hotels based on the target parameter matrix and the first relative weight and the second relative weight of the flow direction dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix.
2. The recommendation method according to claim 1, wherein the flow direction parameter vector comprises at least one of an outflow night vector, an inflow night vector, an outflow room average price vector, and an inflow room average price vector; the attribute parameter vector includes at least one of a predetermined overnight vector, a predetermined room average value vector, a criticizing score vector, a hotel star level vector, a hotel distance vector, and a room number vector.
3. The recommendation method according to claim 2, wherein the calculating, based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors, a target parameter matrix for determining a bid-to-hotel corresponding to the target hotel to be selected includes:
determining the star level, the number of target rooms, the average price of outflow rooms and the average price of inflow rooms of the target hotel to be selected based on the target parameter information of the target hotel to be selected;
Respectively calculating the difference values between the outflow room average value vector and the outflow room average value, the inflow room average value vector and the inflow room average value, the hotel star level vector and the target hotel star level, the preset room average value vector and the target room average value and the room quantity vector and the target room quantity, and obtaining calculated outflow room average value vector, inflow room average value vector, hotel star level vector, preset room average value vector and room quantity vector;
respectively carrying out feature normalization processing on the outflow night vector, the inflow night vector, the preset night vector, the criticizing score vector, the hotel distance vector, the calculated outflow room average price vector, the inflow room average price vector, the hotel star level vector, the preset room average price vector and the room number vector to obtain normalized outflow night vector, inflow night vector, preset night vector, criticizing score vector, hotel distance vector, outflow room average price vector, inflow room average price vector, hotel star level vector, preset room average price vector and room number vector;
and based on the normalized outflow night vector, the inflow night vector, the predetermined night vector, the scoring vector, the hotel distance vector, the outflow room average price vector, the inflow room average price vector, the hotel star level vector and the predetermined room average price vector, the target parameter matrix of the target hotel to be selected is obtained by splicing.
4. The recommendation method according to claim 1, wherein said determining, based on said historical browsed information, a plurality of candidate hotels in a flow direction relationship with said target hotel to be selected comprises:
based on the historical browsed information, determining hotels with a client inflow relation and/or a client outflow relation with the target hotels to be selected as hotels to be screened;
determining the outflow quantity of the clients from the target hotels to be selected to each hotel to be screened and the inflow quantity of the clients from each hotel to be screened to the target hotels to be selected;
and determining the hotels to be screened, of which the outflow quantity is greater than a preset outflow threshold value and/or the inflow quantity is greater than a preset inflow threshold value, as candidate hotels.
5. The recommendation method according to claim 1, wherein calculating a column vector average value of each column of feature vectors in the target parameter matrix, and determining a first relative weight of a flow direction dimension or an attribute dimension corresponding to each column of feature vectors based on the column vector average value of the column of feature vectors, comprises:
calculating a column vector average value of each column of feature vectors in the target parameter matrix, comparing the column vector average value of the column of feature vectors with the column vector average value of each column of feature vectors in the target parameter matrix aiming at each column of feature vectors, and determining a comparison result between the column of feature vectors and each column of feature vectors;
And based on each determined comparison result, calculating to obtain a first relative weight of the flow direction dimension or the attribute dimension corresponding to the column of feature vectors.
6. The recommendation method according to claim 1, wherein determining a competing hotel from the plurality of candidate hotels based on the target parameter matrix, the first relative weight and the second relative weight of the flow direction dimension or the attribute dimension corresponding to each column of feature vectors in the target parameter matrix, comprises:
for each column of feature vectors in the target parameter matrix, calculating to obtain the combination weight of the corresponding flow direction dimension or attribute dimension of the column of feature vectors based on the first relative weight and the second relative weight of the corresponding flow direction dimension or attribute dimension of the column of feature vectors;
for each candidate hotel, calculating to obtain an evaluation value of the candidate hotel based on a row feature vector corresponding to the candidate hotel in the target parameter matrix and a combination weight of a flow dimension or an attribute dimension corresponding to each feature element in the row feature vector;
and determining the competing hotel of the target hotel to be selected from the candidate hotels based on the calculated evaluation values of the candidate hotels.
7. The recommendation method according to claim 6, wherein after determining the competing hotel of the target hotel to be selected from the plurality of candidate hotels based on the calculated evaluation scores of the plurality of candidate hotels, the recommendation method further comprises:
and determining a display level of each competing hotel based on the evaluation value of each competing hotel, and displaying each competing hotel to the user according to the display level.
8. A recommendation device for competing hotels, the recommendation device comprising:
the information acquisition module is used for acquiring historical browsed information of the target hotel to be selected browsed by the user;
the candidate hotel determining module is used for determining a plurality of candidate hotels with flow direction relations with the target hotels to be selected based on the historical browsed information;
the first vector determining module is used for determining a plurality of flow direction parameter vectors under different flow direction dimensions and a plurality of attribute parameter vectors under different attribute dimensions of the plurality of candidate hotels between the target hotels to be selected and each candidate hotel based on the target parameter information of the target hotels to be selected and the candidate parameter information of each candidate hotel;
The second vector determining module is used for calculating a target parameter matrix for determining the competing hotel corresponding to the target hotel to be selected based on the plurality of flow direction parameter vectors and the plurality of attribute parameter vectors;
the first weight determining module is used for calculating the column vector average value of each column of feature vectors in the target parameter matrix and determining the first relative weight of the flow direction dimension or attribute dimension corresponding to each column of feature vectors based on the column vector average value of the feature vectors;
the second weight determining module is used for determining second relative weights of the flow direction dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix based on the target parameter matrix and the preset orthogonal variable;
and the hotel competing determination module is used for determining the hotel competing from the candidate hotels based on the target parameter matrix and the first relative weight and the second relative weight of the flow dimension or the attribute dimension corresponding to each column of feature vector in the target parameter matrix.
9. An electronic device, comprising: a processor, a memory and a bus, said memory storing machine readable instructions executable by said processor, said processor and said memory communicating via said bus when the electronic device is running, said machine readable instructions when executed by said processor performing the steps of the recommended method of competing for hotels according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, performs the steps of the method of recommending a hotel for a race according to any of claims 1 to 7.
CN202110673880.9A 2021-06-17 2021-06-17 Recommendation method and device for competing hotels, electronic equipment and readable storage medium Active CN113407833B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110673880.9A CN113407833B (en) 2021-06-17 2021-06-17 Recommendation method and device for competing hotels, electronic equipment and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110673880.9A CN113407833B (en) 2021-06-17 2021-06-17 Recommendation method and device for competing hotels, electronic equipment and readable storage medium

Publications (2)

Publication Number Publication Date
CN113407833A CN113407833A (en) 2021-09-17
CN113407833B true CN113407833B (en) 2024-02-27

Family

ID=77685058

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110673880.9A Active CN113407833B (en) 2021-06-17 2021-06-17 Recommendation method and device for competing hotels, electronic equipment and readable storage medium

Country Status (1)

Country Link
CN (1) CN113407833B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101589405A (en) * 2006-02-02 2009-11-25 微软公司 Ad targeting and/or pricing based on customer behavior
CN106030626A (en) * 2013-12-11 2016-10-12 天巡有限公司 Method and system for providing fare availabilities, such as air fare availabilities
CN107194774A (en) * 2017-05-22 2017-09-22 携程旅游网络技术（上海）有限公司 Personalized hotel's commending system and method in OTA websites
CN107368907A (en) * 2017-07-25 2017-11-21 携程计算机技术（上海）有限公司 Hotel information methods of exhibiting and device, electronic equipment, storage medium
JP2019032575A (en) * 2017-08-04 2019-02-28 株式会社オークローンマーケティング Aptitude evaluation apparatus of candidate property, aptitude evaluation method, computer program and storage medium for storing computer program

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6397704B2 (en) * 2014-09-19 2018-09-26 株式会社東芝 Information processing apparatus, information processing system, information processing method, and program
EP3758817A4 (en) * 2018-02-27 2021-10-06 Draftkings, Inc. System and methods for prioritizing content packets based on a dynamically updated list of profile attributes

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101589405A (en) * 2006-02-02 2009-11-25 微软公司 Ad targeting and/or pricing based on customer behavior
CN106030626A (en) * 2013-12-11 2016-10-12 天巡有限公司 Method and system for providing fare availabilities, such as air fare availabilities
CN107194774A (en) * 2017-05-22 2017-09-22 携程旅游网络技术（上海）有限公司 Personalized hotel's commending system and method in OTA websites
CN107368907A (en) * 2017-07-25 2017-11-21 携程计算机技术（上海）有限公司 Hotel information methods of exhibiting and device, electronic equipment, storage medium
JP2019032575A (en) * 2017-08-04 2019-02-28 株式会社オークローンマーケティング Aptitude evaluation apparatus of candidate property, aptitude evaluation method, computer program and storage medium for storing computer program

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于改进聚类和矩阵分解的协同过滤推荐算法;王永贵;宋真真;肖成龙;;计算机应用;20180410(04);全文 *

Also Published As

Publication number Publication date
CN113407833A (en) 2021-09-17

Similar Documents

Publication Publication Date Title
US8832115B2 (en) Ranking real estate based on its value and other factors
US20140089020A1 (en) Systems and methods for optimizing markets for temporary living space
US11188852B2 (en) Automated ticket comparison and substitution recommendation system
US10936610B2 (en) Executing and processing corporate travel search results
KR20170065600A (en) Determining host preferences for accommodation listings
US20020032645A1 (en) System and method for score calculation
US9794268B2 (en) Privacy policy management method for a user device
CN108038730A (en) Product similarity determination methods, device and server cluster
CN107871276A (en) Inquiry unit, method and the computer-readable recording medium of loan product
US20040049440A1 (en) Real estate appraisal auxiliary system, a storage medium with a computer software program stored therein for use by a computer system to assist in appraising real estate, and a real estate appraisal auxiliary method
CN112287244A (en) Product recommendation method and device based on federal learning, computer equipment and medium
US20210174407A1 (en) Crowdsourcing seat quality in a venue
CN106097020A (en) For the method and apparatus providing pricing strategy information
US20210142430A1 (en) Systems and methods for searching property listings
US20150193799A1 (en) Interactive user interface for receiving and displaying market information
KR102131799B1 (en) System and method for products recommendation service, and apparatus applied to the same
EP2469427A1 (en) A method and a system for managing a website using profile key patterns
US20210326957A1 (en) Systems and methods for determining and leveraging geography-dependent relative desirability of products
US20130226665A1 (en) Methods and systems for conducting surveys and processing survey data to generate a collective outcome
CN108921309A (en) Meeting room subscribes optimization method, system, readable storage medium storing program for executing and computer equipment
JP5809176B2 (en) Information processing system, information processing method, and program
US20150142482A1 (en) Search engine for identifying business travel proposals
CN113407833B (en) Recommendation method and device for competing hotels, electronic equipment and readable storage medium
KR101835736B1 (en) Talent trading system and method
EP2541483A1 (en) Method and system for revenue management system based on market pricing

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