CN113590937B - Hotel searching and information management method and device, electronic equipment and storage medium - Google Patents
Hotel searching and information management method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113590937B CN113590937B CN202110757970.6A CN202110757970A CN113590937B CN 113590937 B CN113590937 B CN 113590937B CN 202110757970 A CN202110757970 A CN 202110757970A CN 113590937 B CN113590937 B CN 113590937B
- Authority
- CN
- China
- Prior art keywords
- hotel
- low
- image
- determining
- frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 23
- 238000012163 sequencing technique Methods 0.000 claims abstract description 79
- 230000004424 eye movement Effects 0.000 claims description 32
- 238000000034 method Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 22
- 230000001815 facial effect Effects 0.000 claims description 20
- 238000001914 filtration Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 16
- 230000002146 bilateral effect Effects 0.000 claims description 12
- 238000012790 confirmation Methods 0.000 claims description 11
- 210000002569 neuron Anatomy 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 5
- 238000005315 distribution function Methods 0.000 claims description 5
- 238000007499 fusion processing Methods 0.000 claims description 5
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 5
- 229910052737 gold Inorganic materials 0.000 claims description 5
- 239000010931 gold Substances 0.000 claims description 5
- 230000005484 gravity Effects 0.000 claims description 5
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 claims description 4
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 claims description 4
- 229910052802 copper Inorganic materials 0.000 claims description 4
- 239000010949 copper Substances 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 229910052709 silver Inorganic materials 0.000 claims description 4
- 239000004332 silver Substances 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003139 buffering effect Effects 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 230000010076 replication Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- 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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9562—Bookmark management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- 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)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a hotel searching and information management method, a device, an electronic device and a storage medium, comprising the following steps: determining a target city input by a user; loading a cod is cache according to the target city, and acquiring a hotel sequencing list in the target city; hotels in the hotel sequencing list all comprise corresponding hotel labels; acquiring basic information and historical order information of a user; extracting key labels of the users according to the basic information and the historical order information; matching the key labels with hotel labels included in hotels in the hotel sequencing list respectively, determining a plurality of matched hotels in sequence, and determining the matched hotel sequencing list for the hotels according to the sequence of matching; and determining the target hotel required by the user according to the matched hotel ranking table. The user can intuitively determine the required hotel, time and labor are saved, and great convenience is brought to the user for selecting the hotel before going out.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a hotel searching and information management method and device, electronic equipment and a storage medium.
Background
At present, with the continuous development of internet technology, people search and book hotels on the internet before traveling, in the prior art, the sequence of hotels searched by users on the internet is disordered, the users cannot visually determine the required hotels, time and labor are wasted, and great inconvenience is brought to the selection of the hotels by the users.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the art described above. Therefore, the first purpose of the invention is to provide a hotel searching and information management method, so that a user can visually determine a required hotel, time and labor are saved, and great convenience is brought to the user for selecting the hotel before going out.
The second purpose of the invention is to provide a hotel searching and information managing device.
A third object of the invention is to propose an electronic device.
A fourth object of the invention is to propose a computer storage medium.
In order to achieve the above object, an embodiment of a first aspect of the present invention provides a hotel searching and information management method, including:
determining a target city input by a user;
loading a code cache according to the target city, and acquiring a hotel sequencing list in the target city; hotels in the hotel sequencing list all comprise corresponding hotel labels;
acquiring basic information and historical order information of a user;
extracting key labels of the users according to the basic information and the historical order information;
matching the key labels with hotel labels included in hotels in the hotel sequencing list respectively, determining a plurality of matched hotels in sequence, and determining the matched hotel sequencing list for the hotels according to the sequence of matching;
and determining the target hotel required by the user according to the matched hotel ranking table.
According to some embodiments of the invention, the method for determining the hotel ranking list comprises:
determining hotel product information of all hotels in a target city, removing hotels without the hotel product information, and leaving hotels with the hotel product information;
obtaining recommendation levels of all hotels in the hotel with hotel product information, wherein the recommendation levels comprise gold cards, silver cards, copper cards, general lists and blacklists;
performing first sorting according to the recommendation level, and determining a first sorting table;
sequentially and respectively acquiring orderable states of the hotels in the first ranking list, wherein the orderable states comprise instant confirmation, to-be-confirmed, checking and partial orderable;
carrying out secondary sorting on hotels with the same recommendation level in the first sorting table according to the orderable state, and determining a secondary sorting table;
sequentially and respectively acquiring the star grades of the hotels in the second ranking list, wherein the star grades comprise five stars, quasi five stars, four stars, quasi four stars, three stars, quasi three stars, two stars, quasi two stars, below quasi two stars and the like; the other representations have no star rating;
carrying out third sorting on hotels with the same recommendation level and the same orderable state in the second sorting table according to the star level, and determining a third sorting table;
and sequentially and respectively acquiring per-capita consumption of the hotels in the third ranking table, sorting the hotels with the same recommendation level, the same orderable state and the same star level in the third ranking table for the fourth time according to the per-capita consumption level, and determining the hotel ranking table.
According to some embodiments of the invention, after the target hotel required by the user is determined according to the matched hotel sequencing table, the room type sequencing of the target hotel is displayed after the user opens the display interface of the target hotel;
determining the demand house type of the user, and adjusting the house type sequence according to the demand house type.
According to some embodiments of the invention, the method for determining the house type ranking of the target hotel comprises:
determining house type orderable information in a target hotel, wherein the house type orderable information comprises: instant confirmation, waiting confirmation, checking, partial orderable and finishing ordering;
and sequencing according to the house type orderable information, after sequencing is finished, re-sequencing the house types with the same house type orderable information according to the price of the house types, and determining the house type sequencing of the target hotel.
According to some embodiments of the present invention, the determining the target hotel required by the user according to the matching hotel ranking table includes:
acquiring an image to be detected of a first matched hotel in the matched hotel sequencing list;
inputting the image to be detected into a hotel scoring model, and outputting the score of the image to be detected;
acquiring a demand score input by a user;
when the score of the image to be detected is determined to be larger than or equal to the requirement score, acquiring a face image of a user when the user views the image to be detected;
extracting the features of the facial image to obtain facial features, inputting the facial features into an age group identification model, and determining the age group of the user;
determining a plurality of preference factors of the user to the hotel according to the age group of the user;
determining an entropy weight of the preference factor;
calculating to obtain a weight value of the preference factor according to the specific gravity of the preset preference factor and the entropy weight of the preference factor;
intercepting an eye movement image in the facial image, determining an eye movement track in the eye movement image based on an eye movement tracking algorithm, and calculating the contact ratio of the eye movement track and a preset eye movement track;
calculating the preference degree of the user to the first matched hotel according to the preference factors, the weight values of the preference factors and the contact degree;
when the preference degree is determined to be greater than or equal to a preset preference degree, determining that a first matched hotel is a target hotel; and otherwise, repeating the steps for a second matching hotel behind the first matching hotel until the matching hotel with the preference degree larger than or equal to the preset preference degree is determined as the target hotel.
According to some embodiments of the invention, further comprising: and when the preference degrees of the user to all the matched hotels in the matched hotel sequencing list are determined to be less than the preset preference degree, taking the matched hotels with the maximum preference degree in the matched hotel sequencing list as target hotels.
According to some embodiments of the invention, further comprising:
in the process of learning and training the hotel scoring model, calculating a learning error, judging whether the learning error is smaller than a preset learning error, obtaining a learning and training parameter of the hotel scoring model when the learning error is determined to be smaller than the preset learning error, and stopping training;
the learning error is calculated based on equation (1):
wherein w is a learning error; m is an input sample included in the learning training set; n is the neuron number of the output layer of the hotel scoring model, and n belongs to (1, 3); y isijAn ideal output based on the jth neuron for the ith input sample; oijBased on the actual output of the jth neuron for the ith input sample.
According to some embodiments of the present invention, before inputting the image to be detected into the hotel scoring model, the method further includes preprocessing the image to be detected, including:
performing low-pass filtering on the image to be detected based on a low-pass filter to determine a low-frequency area of the image to be detected;
dividing the low-frequency area, determining a plurality of sub low-frequency areas, respectively determining first average pixel values of the sub low-frequency areas, and calculating second average pixel values of the low-frequency areas;
respectively calculating absolute values of differences between first average pixel values and second average pixel values of a plurality of sub-low-frequency areas, and taking the sub-low-frequency area corresponding to the maximum absolute value of the difference as a target sub-low-frequency area;
carrying out bilateral filtering on the target sub-low-frequency area based on a bilateral filter, and carrying out correction processing on the target sub-low-frequency area based on a formula (2) to obtain a corrected target sub-low-frequency area;
wherein the content of the first and second substances,
the corrected target sub-low-frequency area is obtained; caThe number of pixel points to be corrected in the target sub-low-frequency area is set; t (b) is adjacent to the target sub-low frequency regionThe pixel value of the b-th pixel point in the sub-low frequency region; t (a) is the pixel value of the a-th pixel point to be corrected in the target sub-low-frequency region; e is a natural constant; sigma is the standard deviation of the Gaussian distribution function;
processing the modified low-frequency region based on an AGC algorithm and a histogram equalization algorithm to obtain a low-frequency image;
carrying out high-pass filtering on the image to be detected based on a high-pass filter, and determining a high-frequency area of the image to be detected;
processing the high-frequency image based on an AGC algorithm to obtain a high-frequency image;
performing fusion processing on the low-frequency image and the high-frequency image, and obtaining a preprocessed image to be detected based on a formula (3);
wherein E is0The image to be detected is preprocessed; k is a radical of1Is a weighting factor for the low frequency image; e2The low-frequency images of other sub low-frequency areas except the target sub low-frequency area are obtained; k is a radical of2Weighting factor, k, for high frequency images1+k2＝1；E1Is a high-frequency image;
is the low-frequency image of the modified target sub-low-frequency area.
In order to achieve the above object, an embodiment of a second aspect of the present invention provides an apparatus for hotel searching and information management, including:
the first determination module is used for determining a target city input by a user;
the first obtaining module is used for loading a code cache according to the target city and obtaining a hotel sequencing list in the target city; hotels in the hotel sequencing list all comprise corresponding hotel labels;
the second acquisition module is used for acquiring the basic information and the historical order information of the user;
the extraction module is used for extracting key labels of the users according to the basic information and the historical order information;
the second determining module is used for respectively matching the key labels with hotel labels included in hotels in the hotel sequencing list, sequentially determining a plurality of matched hotels, and determining the matched hotel sequencing list for the hotels according to the sequence of matching;
and the third determining module is used for determining the target hotel required by the user according to the matched hotel sequencing list.
To achieve the above object, a third aspect of the present invention provides an electronic device, including:
a display;
a memory for storing at least one program; and
and the processor is connected with the memory and is used for running the at least one program to execute the hotel searching and information management method.
To achieve the above object, a fourth aspect of the present invention provides a computer storage medium storing at least one program, the program being executed by a processor to perform the hotel search and information management method as described above.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart of a hotel search and information management method according to an embodiment of the present invention.
Fig. 2 is a block diagram of a hotel search and information management apparatus according to one embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
As shown in fig. 1, an embodiment of the first aspect of the present invention provides a hotel search and information management method, including steps S1-S6:
s1, determining a target city input by a user;
s2, loading a codis cache according to the target city, and acquiring a hotel sequencing list in the target city; hotels in the hotel sequencing list all comprise corresponding hotel labels;
s3, acquiring basic information and historical order information of the user;
s4, extracting key labels of the users according to the basic information and the historical order information;
s5, matching the key labels with hotel labels included in hotels in the hotel sequencing list respectively, determining a plurality of matched hotels in sequence, and determining a matched hotel sequencing list for the hotels according to the sequence of matching;
and S6, determining the target hotel required by the user according to the matching hotel ranking table.
The working principle of the technical scheme is as follows: the realization of the invention is based on JStorm + Elastic Search (ES) + coding + xxl-jobMQ and other key technologies. Codis is a buffering technique. Determining a target city input by a user; loading a code cache according to the target city, and acquiring a hotel sequencing list in the target city; hotels in the hotel sequencing list all comprise corresponding hotel labels; the hotel sequencing list is stored in a code cache in advance, when a user operates and inquires the cache to have no hotel sequencing list for the first time, the city hotel sequencing is immediately and asynchronously triggered, all hotels in the target city are sequenced, and the hotel sequencing list is determined. The hotel label includes: young, middle-aged, high-consumer, low-consumer, traffic-convenient, and the like. Traffic facilitation includes a distance within a preset kilometer range from a train station. Acquiring basic information and historical order information of a user; the basic information includes the name, sex, etc. of the user. The historical order information includes hotel information previously determined by the user. Extracting key labels of the users according to the basic information and the historical order information; key labels include age labels and the like. And matching the key labels with hotel labels included by hotels in the hotel sequencing list respectively, determining a plurality of matched hotels in sequence, and determining the matched hotel sequencing list for the hotels according to the sequence of matching. And determining the target hotel required by the user according to the matched hotel ranking table.
The beneficial effects of the above technical scheme are that: the user can intuitively determine the required hotel, time and labor are saved, and great convenience is brought to the user for selecting the hotel before going out.
According to some embodiments of the invention, the method for determining the hotel ranking list comprises:
determining hotel product information of all hotels in a target city, removing hotels without the hotel product information, and leaving hotels with the hotel product information;
obtaining recommendation levels of all hotels in the hotel with hotel product information, wherein the recommendation levels comprise gold cards, silver cards, copper cards, general lists and blacklists;
performing first sorting according to the recommendation level, and determining a first sorting table;
sequentially and respectively acquiring orderable states of the hotels in the first ranking list, wherein the orderable states comprise instant confirmation, to-be-confirmed, checking and partial orderable;
carrying out secondary sorting on hotels with the same recommendation level in the first sorting table according to the orderable state, and determining a secondary sorting table;
sequentially and respectively acquiring the star grades of the hotels in the second ranking list, wherein the star grades comprise five stars, quasi five stars, four stars, quasi four stars, three stars, quasi three stars, two stars, quasi two stars, below quasi two stars and the like; the other representations have no star rating;
carrying out third sorting on hotels with the same recommendation level and the same orderable state in the second sorting table according to the star level, and determining a third sorting table;
and sequentially and respectively acquiring per-capita consumption of the hotels in the third ranking table, sorting the hotels with the same recommendation level, the same orderable state and the same star level in the third ranking table for the fourth time according to the per-capita consumption level, and determining the hotel ranking table.
The working principle of the technical scheme is as follows: the hotel sequencing considers the following points that a, whether products exist, the hotel with the products is arranged in front, and the hotel without the products does not show. b. The recommended grade comprises the following steps: gold, silver, copper, general, black list-the system can be set manually. In the hotel which can be ordered or can not be ordered, the gold medals are ranked at the top and the black list is ranked at the back according to the grades. c. The hotel booking status comprises the following steps: instant confirmation, waiting confirmation, checking and partial orderable. In the same recommendation level ordering, the hotel orderable states are ordered, namely the order is confirmed to be the front most instantly, and the order is partially ordered to be the back most. d. The hotel star level is divided into: five stars, quasi-five stars, four stars, quasi-four stars, three stars, quasi-three stars, two stars, quasi-two stars, and others-consider "others" because some hotels do not have star-level data in the basic information of the hotel. When the bookable states of the hotel are the same, the hotel is ranked according to the star level of the hotel, wherein the five-star row is the front row, and the other rows are the back row. e. The price is high, when the star levels of the hotels are the same, the hotels are ranked according to the price, namely the front row of the hotel with low price is ranked and the back row with high price is ranked.
The beneficial effects of the above technical scheme are that: the ordering scheme aims to achieve the aims of intuition, dynamics, instantaneity, reproducibility, intervention and the like of hotel ordering. Intuition: the visual feeling of the user is met, such as: hotels without products and with no orders are arranged at the end; the hotel confirmed immediately is arranged in front; low prices are ranked in the front, etc. The dynamic property: according to different query dates and screening conditions, dynamic sequencing can be performed aiming at different query results. Instantaneity: the time required by sorting is short, the user does not need to wait for too long, the user can sort the data at the same time after clicking the query button, and the query result is sorted well as the query result is obtained. Replication: not only is the hotel ordering suitable for B2B, but also the hotel ordering of the hotel with the letter, business union can be used. Intervention property: certain sort control may be performed by manually setting a "recommended level".
According to some embodiments of the invention, after the target hotel required by the user is determined according to the matched hotel sequencing table, the room type sequencing of the target hotel is displayed after the user opens the display interface of the target hotel;
determining the demand house type of the user, and adjusting the house type sequence according to the demand house type.
The beneficial effects of the above technical scheme are that: the house type sequencing is dynamically adjusted according to the house type required by the user, and the house type searching requirement of the user is met.
According to some embodiments of the invention, the method for determining the house type ranking of the target hotel comprises:
determining house type orderable information in a target hotel, wherein the house type orderable information comprises: instant confirmation, waiting confirmation, checking, partial orderable and finishing ordering;
and sequencing according to the house type orderable information, after sequencing is finished, re-sequencing the house types with the same house type orderable information according to the price of the house types, and determining the house type sequencing of the target hotel.
The beneficial effects of the above technical scheme are that: the room types in the target hotel are sorted, so that a user can conveniently and quickly determine the required room type in the target hotel, the waste of excessive searching time of the user is avoided, and the user experience is improved.
According to some embodiments of the present invention, the determining the target hotel required by the user according to the matching hotel ranking table includes:
acquiring an image to be detected of a first matched hotel in the matched hotel sequencing list;
inputting the image to be detected into a hotel scoring model, and outputting the score of the image to be detected;
acquiring a demand score input by a user;
when the score of the image to be detected is determined to be larger than or equal to the requirement score, acquiring a face image of a user when the user views the image to be detected;
extracting the features of the facial image to obtain facial features, inputting the facial features into an age group identification model, and determining the age group of the user;
determining a plurality of preference factors of the user to the hotel according to the age group of the user;
determining an entropy weight of the preference factor;
calculating to obtain a weight value of the preference factor according to the specific gravity of the preset preference factor and the entropy weight of the preference factor;
intercepting an eye movement image in the facial image, determining an eye movement track in the eye movement image based on an eye movement tracking algorithm, and calculating the contact ratio of the eye movement track and a preset eye movement track;
calculating the preference degree of the user to the first matched hotel according to the preference factors, the weight values of the preference factors and the contact degree;
when the preference degree is determined to be greater than or equal to a preset preference degree, determining that a first matched hotel is a target hotel; and otherwise, repeating the steps for a second matching hotel behind the first matching hotel until the matching hotel with the preference degree larger than or equal to the preset preference degree is determined as the target hotel.
The working principle of the technical scheme is as follows: acquiring an image to be detected of a first matched hotel in the matched hotel sequencing list; inputting the image to be detected into a hotel scoring model, and outputting the score of the image to be detected; the images to be detected comprise room pictures of a hotel, service hall pictures and the like. Acquiring a demand score input by a user; when the score of the image to be detected is determined to be larger than or equal to the requirement score, acquiring a face image of a user when the user views the image to be detected; extracting the features of the facial image to obtain facial features, inputting the facial features into an age group identification model, and determining the age group of the user; determining a plurality of preference factors of the user to the hotel according to the age group of the user; determining an entropy weight of the preference factor; calculating to obtain a weight value of the preference factor according to the specific gravity of the preset preference factor and the entropy weight of the preference factor; intercepting an eye movement image in the facial image, determining an eye movement track in the eye movement image based on an eye movement tracking algorithm, and calculating the contact ratio of the eye movement track and a preset eye movement track; calculating the preference degree of the user to the first matched hotel according to the preference factors, the weight values of the preference factors and the contact degree; when the preference degree is determined to be greater than or equal to a preset preference degree, determining that a first matched hotel is a target hotel; and otherwise, repeating the steps for a second matching hotel behind the first matching hotel until the matching hotel with the preference degree larger than or equal to the preset preference degree is determined as the target hotel.
The beneficial effects of the above technical scheme are that: the image to be detected is scored based on the hotel scoring model, so that screening and recommendation are facilitated, the image to be detected of the hotel is effectively utilized, consistency of the hotel picture published on the internet and actual conditions of the hotel is guaranteed, and strong fall of the user after the user enters the hotel is avoided, and user experience is not influenced. And objectively scoring the first matched hotel, so that whether the scoring meets the requirement of the user or not is conveniently screened. The method comprises the steps of accurately determining the age group of a user, further determining a plurality of preference factors of the user to a hotel, wherein entropy weight is determined based on an entropy method, the entropy method is a mathematical method for judging the dispersion degree of a certain index, the dispersion degree of the preference factors is determined based on the entropy weight, and the influence of the determined preference factors on the too large or too small preference degree of individual difference, namely the influence on the accuracy of the finally calculated preference degree is avoided. And calculating the contact ratio of the eye movement track and a preset eye movement track, wherein the higher the contact ratio is, the more interesting the user is to the hotel, and the lower the contact ratio is, the less interesting the user is to the hotel. And judging whether the user is satisfied with the first matching hotel or not according to the preference of the user to the first matching hotel until the hotel satisfied with the user is selected as the target hotel. In the process of repeating the steps, the hotel sorting table is executed based on the sequence matched with the hotel sorting table, so that the hotel is more rapid, and the hotel satisfied by the user, namely the target hotel, is selected earlier with higher probability, so that the time of the user is saved, and the user experience is improved.
According to some embodiments of the invention, further comprising: and when the preference degrees of the user to all the matched hotels in the matched hotel sequencing list are determined to be less than the preset preference degree, taking the matched hotels with the maximum preference degree in the matched hotel sequencing list as target hotels.
The beneficial effects of the above technical scheme are that: the most suitable hotel is selected from the matched hotel ranking table and used as the target hotel, and then recommended to the user, and efficiency of searching and booking the hotel by the user is improved.
According to some embodiments of the invention, further comprising:
in the process of learning and training the hotel scoring model, calculating a learning error, judging whether the learning error is smaller than a preset learning error, obtaining a learning and training parameter of the hotel scoring model when the learning error is determined to be smaller than the preset learning error, and stopping training;
the learning error is calculated based on equation (1):
wherein w is a learning error; m is an input sample included in the learning training set; n is the neuron number of the output layer of the hotel scoring model, and n belongs to (1, 3); y isijAn ideal output based on the jth neuron for the ith input sample; oijBased on the actual output of the jth neuron for the ith input sample.
The working principle and the beneficial effects of the technical scheme are as follows: in the process of learning and training the hotel scoring model, calculating a learning error, judging whether the learning error is smaller than a preset learning error, obtaining a learning and training parameter of the hotel scoring model when the learning error is determined to be smaller than the preset learning error, and stopping training; the method has the advantages that the training threshold value is accurately set, the training process of the hotel scoring model is monitored in the training process, large deviation in the training process is avoided, the accuracy of learning training parameters after training is finished is guaranteed, and the scoring accuracy of the hotel scoring model on the input to-be-detected image is guaranteed. When the learning error is calculated, parameters such as an input sample included in the learning training set and the neuron number of an output layer of the hotel scoring model are considered, the accuracy of the calculated learning error is guaranteed, and the accuracy of the learning error and the preset learning error is further judged.
According to some embodiments of the present invention, before inputting the image to be detected into the hotel scoring model, the method further includes preprocessing the image to be detected, including:
performing low-pass filtering on the image to be detected based on a low-pass filter to determine a low-frequency area of the image to be detected;
dividing the low-frequency area, determining a plurality of sub low-frequency areas, respectively determining first average pixel values of the sub low-frequency areas, and calculating second average pixel values of the low-frequency areas;
respectively calculating absolute values of differences between first average pixel values and second average pixel values of a plurality of sub-low-frequency areas, and taking the sub-low-frequency area corresponding to the maximum absolute value of the difference as a target sub-low-frequency area;
carrying out bilateral filtering on the target sub-low-frequency area based on a bilateral filter, and carrying out correction processing on the target sub-low-frequency area based on a formula (2) to obtain a corrected target sub-low-frequency area;
wherein the content of the first and second substances,
the corrected target sub-low-frequency area is obtained; caThe number of pixel points to be corrected in the target sub-low-frequency area is set; t (b) is in a sub low frequency region adjacent to the target sub low frequency regionThe pixel value of the b-th pixel point; t (a) is the pixel value of the a-th pixel point to be corrected in the target sub-low-frequency region; e is a natural constant; sigma is the standard deviation of the Gaussian distribution function;
processing the modified low-frequency region based on an AGC algorithm and a histogram equalization algorithm to obtain a low-frequency image;
carrying out high-pass filtering on the image to be detected based on a high-pass filter, and determining a high-frequency area of the image to be detected;
processing the high-frequency image based on an AGC algorithm to obtain a high-frequency image;
performing fusion processing on the low-frequency image and the high-frequency image, and obtaining a preprocessed image to be detected based on a formula (3);
wherein E is0The image to be detected is preprocessed; k is a radical of1Is a weighting factor for the low frequency image; e2The low-frequency images of other sub low-frequency areas except the target sub low-frequency area are obtained; k is a radical of2Weighting factor, k, for high frequency images1+k2＝1；E1Is a high-frequency image;
is the low-frequency image of the modified target sub-low-frequency area.
The working principle and the beneficial effects of the technical scheme are as follows: before the image to be detected is input into the hotel scoring model, the image to be detected is preprocessed, so that the accuracy of the image to be detected input into the hotel scoring model is ensured, the noise influence of the image to be detected is eliminated, the identification accuracy of the image to be detected is improved, and the output scoring result is more accurate. Performing low-pass filtering on the image to be detected based on a low-pass filter to determine a low-frequency area of the image to be detected; dividing the low-frequency area, determining a plurality of sub low-frequency areas, and respectively determining a first average of the plurality of sub low-frequency areasPixel values and calculating a second average pixel value of the low-frequency area; respectively calculating absolute values of differences between first average pixel values and second average pixel values of a plurality of sub-low-frequency areas, and taking the sub-low-frequency area corresponding to the maximum absolute value of the difference as a target sub-low-frequency area; carrying out bilateral filtering on the target sub-low-frequency area based on a bilateral filter, and carrying out correction processing on the target sub-low-frequency area based on a formula (2) to obtain a corrected target sub-low-frequency area; processing the modified low-frequency region based on an AGC algorithm and a histogram equalization algorithm to obtain a low-frequency image; carrying out high-pass filtering on the image to be detected based on a high-pass filter, and determining a high-frequency area of the image to be detected; processing the high-frequency image based on an AGC algorithm to obtain a high-frequency image; and (3) carrying out fusion processing on the low-frequency image and the high-frequency image, and obtaining a preprocessed image to be detected based on a formula (3). The method has the advantages that the low-frequency region and the high-frequency region in the image to be detected are accurately divided based on the high-pass filter and the low-pass filter, the low-frequency region and the high-frequency region can be conveniently and respectively generated into the corresponding low-frequency image and the high-frequency image subsequently, effective filtering and image enhancement processing are carried out on the image to be detected, and the image quality is improved. In low-pass filtering based on a low-pass filter, black edges occur in the low-frequency region, i.e., the gray value decreases. The target sub-low-frequency area is accurately determined and bilateral filtering is carried out based on a bilateral filter, different weights are originally set based on the distance of the position, and the target sub-low-frequency area is readjusted and corrected based on the gray difference value between the target sub-low-frequency area and the adjacent sub-low-frequency area. And sigma is a standard deviation of a Gaussian distribution function, the amplitude of the low-frequency interception can be controlled, the larger sigma is, the larger the extracted low-frequency amplitude is, and the smaller sigma is, the smaller the extracted low-frequency amplitude is. k is a radical of1Relating to the enhancement effect of the low frequency image. k is a radical of2Relating to the enhancement effect of the high frequency image. The problem of black edges which are easy to appear based on a low-pass filter in the prior art is avoided, the accuracy of a low-frequency area is guaranteed, the accuracy of a low-frequency image is further guaranteed, and the accuracy of a preprocessed image to be detected is further guaranteed.
As shown in fig. 2, a second embodiment of the present invention provides a hotel searching and information managing apparatus, including:
the first determination module is used for determining a target city input by a user;
the first obtaining module is used for loading a code cache according to the target city and obtaining a hotel sequencing list in the target city; hotels in the hotel sequencing list all comprise corresponding hotel labels;
the second acquisition module is used for acquiring the basic information and the historical order information of the user;
the extraction module is used for extracting key labels of the users according to the basic information and the historical order information;
the second determining module is used for respectively matching the key labels with hotel labels included in hotels in the hotel sequencing list, sequentially determining a plurality of matched hotels, and determining the matched hotel sequencing list for the hotels according to the sequence of matching;
and the third determining module is used for determining the target hotel required by the user according to the matched hotel sequencing list.
The working principle of the technical scheme is as follows: the realization of the invention is based on JStorm + Elastic Search (ES) + coding + xxl-jobMQ and other key technologies. Codis is a buffering technique. The first determination module determines a target city input by a user; a first obtaining module loads a code cache according to the target city to obtain a hotel sequencing list in the target city; hotels in the hotel sequencing list all comprise corresponding hotel labels; the hotel sequencing list is stored in a code cache in advance, when a user operates and inquires the cache to have no hotel sequencing list for the first time, the city hotel sequencing is immediately and asynchronously triggered, all hotels in the target city are sequenced, and the hotel sequencing list is determined. The hotel label includes: young, middle-aged, high-consumer, low-consumer, traffic-convenient, and the like. Traffic facilitation includes a distance within a preset kilometer range from a train station. The second acquisition module acquires basic information and historical order information of the user; the basic information includes the name, sex, etc. of the user. The historical order information includes hotel information previously determined by the user. The extraction module extracts a key label of the user according to the basic information and the historical order information; key labels include age labels and the like. And the second determination module respectively matches the key labels with hotel labels included by hotels in the hotel sequencing list, sequentially determines a plurality of matched hotels, and determines the matched hotel sequencing list according to the sequence of matching of the hotels. And the third determining module determines the target hotel required by the user according to the matched hotel sequencing list.
The beneficial effects of the above technical scheme are that: the user can intuitively determine the required hotel, time and labor are saved, and great convenience is brought to the user for selecting the hotel before going out.
An embodiment of a third aspect of the present invention provides an electronic device, including:
a display;
a memory for storing at least one program; and
and the processor is connected with the memory and is used for running the at least one program to execute the hotel searching and information management method.
A fourth aspect of the present invention provides a computer storage medium storing at least one program, where the program is executed by a processor to perform the hotel search and information management method as described in any one of the above.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A hotel searching and information management method is characterized by comprising the following steps:
determining a target city input by a user;
loading a code cache according to the target city, and acquiring a hotel sequencing list in the target city; hotels in the hotel sequencing list all comprise corresponding hotel labels; the hotel label includes: young group, middle-aged group, high consumption group, low consumption group, and convenient transportation;
acquiring basic information and historical order information of a user;
extracting key labels of the users according to the basic information and the historical order information; key tags include age tags;
matching the key labels with hotel labels included in hotels in the hotel sequencing list respectively, determining a plurality of matched hotels in sequence, and determining the matched hotel sequencing list for the hotels according to the sequence of matching;
determining a target hotel required by the user according to the matched hotel sequencing list;
the determining the target hotel required by the user according to the matched hotel ranking table comprises:
acquiring an image to be detected of a first matched hotel in the matched hotel sequencing list;
inputting the image to be detected into a hotel scoring model, and outputting the score of the image to be detected;
acquiring a demand score input by a user;
when the score of the image to be detected is determined to be larger than or equal to the requirement score, acquiring a face image of a user when the user views the image to be detected;
extracting the features of the facial image to obtain facial features, inputting the facial features into an age group identification model, and determining the age group of the user;
determining a plurality of preference factors of the user to the hotel according to the age group of the user;
determining an entropy weight of the preference factor;
calculating to obtain a weight value of the preference factor according to the specific gravity of the preset preference factor and the entropy weight of the preference factor;
intercepting an eye movement image in the facial image, determining an eye movement track in the eye movement image based on an eye movement tracking algorithm, and calculating the contact ratio of the eye movement track and a preset eye movement track;
calculating the preference degree of the user to the first matched hotel according to the preference factors, the weight values of the preference factors and the contact degree;
when the preference degree is determined to be greater than or equal to a preset preference degree, determining that a first matched hotel is a target hotel; otherwise, repeating the steps for a second matching hotel behind the first matching hotel until the matching hotel with the preference degree larger than or equal to the preset preference degree is determined as the target hotel;
before the image to be detected is input into the hotel scoring model, preprocessing the image to be detected, comprising the following steps:
performing low-pass filtering on the image to be detected based on a low-pass filter to determine a low-frequency area of the image to be detected;
dividing the low-frequency area, determining a plurality of sub low-frequency areas, respectively determining first average pixel values of the sub low-frequency areas, and calculating second average pixel values of the low-frequency areas;
respectively calculating absolute values of differences between first average pixel values and second average pixel values of a plurality of sub-low-frequency areas, and taking the sub-low-frequency area corresponding to the maximum absolute value of the difference as a target sub-low-frequency area;
carrying out bilateral filtering on the target sub-low-frequency area based on a bilateral filter, and carrying out correction processing on the target sub-low-frequency area based on a formula (2) to obtain a corrected target sub-low-frequency area;
wherein the content of the first and second substances,
the corrected target sub-low-frequency area is obtained; caThe number of pixel points to be corrected in the target sub-low-frequency area is set; t (b) is the pixel value of the b-th pixel point in the sub-low frequency region adjacent to the target sub-low frequency region; t (a) is the pixel value of the a-th pixel point to be corrected in the target sub-low-frequency region; e is natureA constant; sigma is the standard deviation of the Gaussian distribution function;
processing the modified low-frequency region based on an AGC algorithm and a histogram equalization algorithm to obtain a low-frequency image;
carrying out high-pass filtering on the image to be detected based on a high-pass filter, and determining a high-frequency area of the image to be detected;
processing the high-frequency image based on an AGC algorithm to obtain a high-frequency image;
performing fusion processing on the low-frequency image and the high-frequency image, and obtaining a preprocessed image to be detected based on a formula (3);
wherein E is0The image to be detected is preprocessed; k is a radical of1Is a weighting factor for the low frequency image; e2The low-frequency images of other sub low-frequency areas except the target sub low-frequency area are obtained; k is a radical of2Weighting factor, k, for high frequency images1+k2＝1；E1Is a high-frequency image;
is the low-frequency image of the modified target sub-low-frequency area.
2. The hotel searching and information management method of claim 1, wherein the method for determining the hotel ranking list comprises:
determining hotel product information of all hotels in a target city, removing hotels without the hotel product information, and leaving hotels with the hotel product information;
obtaining recommendation levels of all hotels in the hotel with hotel product information, wherein the recommendation levels comprise gold cards, silver cards, copper cards, general lists and blacklists;
performing first sorting according to the recommendation level, and determining a first sorting table;
sequentially and respectively acquiring orderable states of the hotels in the first ranking list, wherein the orderable states comprise instant confirmation, to-be-confirmed, checking and partial orderable;
carrying out secondary sorting on hotels with the same recommendation level in the first sorting table according to the orderable state, and determining a secondary sorting table;
sequentially and respectively acquiring the star grades of the hotels in the second ranking list, wherein the star grades comprise five stars, quasi five stars, four stars, quasi four stars, three stars, quasi three stars, two stars, quasi two stars, below quasi two stars and the like; the other representations have no star rating;
carrying out third sorting on hotels with the same recommendation level and the same orderable state in the second sorting table according to the star level, and determining a third sorting table;
and sequentially and respectively acquiring per-capita consumption of the hotels in the third ranking table, sorting the hotels with the same recommendation level, the same orderable state and the same star level in the third ranking table for the fourth time according to the per-capita consumption level, and determining the hotel ranking table.
3. The hotel searching and information management method according to claim 1, wherein after the target hotel required by the user is determined according to the matched hotel ranking table, the room type ranking of the target hotel is displayed after the user opens a display interface of the target hotel;
determining the demand house type of the user, and adjusting the house type sequence according to the demand house type.
4. The hotel searching and information management method of claim 3, wherein the method for determining the room type ranking of the target hotel comprises:
determining house type orderable information in a target hotel, wherein the house type orderable information comprises: instant confirmation, waiting confirmation, checking, partial orderable and finishing ordering;
and sequencing according to the house type orderable information, after sequencing is finished, re-sequencing the house types with the same house type orderable information according to the price of the house types, and determining the house type sequencing of the target hotel.
5. The hotel search and information management method of claim 1, further comprising: and when the preference degrees of the user to all the matched hotels in the matched hotel sequencing list are determined to be less than the preset preference degree, taking the matched hotels with the maximum preference degree in the matched hotel sequencing list as target hotels.
6. The hotel search and information management method of claim 1, further comprising:
in the process of learning and training the hotel scoring model, calculating a learning error, judging whether the learning error is smaller than a preset learning error, obtaining a learning and training parameter of the hotel scoring model when the learning error is determined to be smaller than the preset learning error, and stopping training;
the learning error is calculated based on equation (1):
wherein w is a learning error; m is an input sample included in the learning training set; n is the neuron number of the output layer of the hotel scoring model, and n belongs to (1, 3); y isijAn ideal output based on the jth neuron for the ith input sample; oijBased on the actual output of the jth neuron for the ith input sample.
7. A hotel search and information management device, comprising:
the first determination module is used for determining a target city input by a user;
the first obtaining module is used for loading a code cache according to the target city and obtaining a hotel sequencing list in the target city; hotels in the hotel sequencing list all comprise corresponding hotel labels; the hotel label includes: young group, middle-aged group, high consumption group, low consumption group, and convenient transportation;
the second acquisition module is used for acquiring the basic information and the historical order information of the user;
the extraction module is used for extracting key labels of the users according to the basic information and the historical order information; key tags include age tags;
the second determining module is used for respectively matching the key labels with hotel labels included in hotels in the hotel sequencing list, sequentially determining a plurality of matched hotels, and determining the matched hotel sequencing list for the hotels according to the sequence of matching;
the third determining module is used for determining the target hotel required by the user according to the matched hotel sequencing list;
the third determining module determines the target hotel required by the user according to the matched hotel ranking table, and comprises the following steps:
acquiring an image to be detected of a first matched hotel in the matched hotel sequencing list;
inputting the image to be detected into a hotel scoring model, and outputting the score of the image to be detected;
acquiring a demand score input by a user;
when the score of the image to be detected is determined to be larger than or equal to the requirement score, acquiring a face image of a user when the user views the image to be detected;
extracting the features of the facial image to obtain facial features, inputting the facial features into an age group identification model, and determining the age group of the user;
determining a plurality of preference factors of the user to the hotel according to the age group of the user;
determining an entropy weight of the preference factor;
calculating to obtain a weight value of the preference factor according to the specific gravity of the preset preference factor and the entropy weight of the preference factor;
intercepting an eye movement image in the facial image, determining an eye movement track in the eye movement image based on an eye movement tracking algorithm, and calculating the contact ratio of the eye movement track and a preset eye movement track;
calculating the preference degree of the user to the first matched hotel according to the preference factors, the weight values of the preference factors and the contact degree;
when the preference degree is determined to be greater than or equal to a preset preference degree, determining that a first matched hotel is a target hotel; otherwise, repeating the steps for a second matching hotel behind the first matching hotel until the matching hotel with the preference degree larger than or equal to the preset preference degree is determined as the target hotel;
before the image to be detected is input into the hotel scoring model, preprocessing the image to be detected, comprising the following steps:
performing low-pass filtering on the image to be detected based on a low-pass filter to determine a low-frequency area of the image to be detected;
dividing the low-frequency area, determining a plurality of sub low-frequency areas, respectively determining first average pixel values of the sub low-frequency areas, and calculating second average pixel values of the low-frequency areas;
respectively calculating absolute values of differences between first average pixel values and second average pixel values of a plurality of sub-low-frequency areas, and taking the sub-low-frequency area corresponding to the maximum absolute value of the difference as a target sub-low-frequency area;
carrying out bilateral filtering on the target sub-low-frequency area based on a bilateral filter, and carrying out correction processing on the target sub-low-frequency area based on a formula (2) to obtain a corrected target sub-low-frequency area;
wherein the content of the first and second substances,
the corrected target sub-low-frequency area is obtained; caThe number of pixel points to be corrected in the target sub-low-frequency area is set; t (b) is the pixel value of the b-th pixel point in the sub-low frequency region adjacent to the target sub-low frequency region; t (a) is the target sub-low frequencyThe pixel value of the a-th pixel point to be corrected in the area; e is a natural constant; sigma is the standard deviation of the Gaussian distribution function;
processing the modified low-frequency region based on an AGC algorithm and a histogram equalization algorithm to obtain a low-frequency image;
carrying out high-pass filtering on the image to be detected based on a high-pass filter, and determining a high-frequency area of the image to be detected;
processing the high-frequency image based on an AGC algorithm to obtain a high-frequency image;
performing fusion processing on the low-frequency image and the high-frequency image, and obtaining a preprocessed image to be detected based on a formula (3);
wherein E is0The image to be detected is preprocessed; k is a radical of1Is a weighting factor for the low frequency image; e2The low-frequency images of other sub low-frequency areas except the target sub low-frequency area are obtained; k is a radical of2Weighting factor, k, for high frequency images1+k2＝1；E1Is a high-frequency image;
is the low-frequency image of the modified target sub-low-frequency area.
8. An electronic device, comprising:
a display;
a memory for storing at least one program; and
a processor, coupled to the memory, for executing the at least one program to perform the hotel search and information management method of any of claims 1-6.
9. A computer storage medium storing at least one program for executing the hotel search and information management method according to any one of claims 1 to 6 by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110757970.6A CN113590937B (en) | 2021-07-05 | 2021-07-05 | Hotel searching and information management method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110757970.6A CN113590937B (en) | 2021-07-05 | 2021-07-05 | Hotel searching and information management method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113590937A CN113590937A (en) | 2021-11-02 |
| CN113590937B true CN113590937B (en) | 2022-04-19 |
Family
ID=78245937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110757970.6A Active CN113590937B (en) | 2021-07-05 | 2021-07-05 | Hotel searching and information management method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113590937B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117332994B (en) * | 2023-12-01 | 2024-02-20 | 青岛小帅智能科技股份有限公司 | Hotel multimedia resource allocation method, system, electronic equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107481054A (en) * | 2017-08-14 | 2017-12-15 | 携程计算机技术（上海）有限公司 | The push of hotel's favor information and device, electronic equipment, storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013016362A1 (en) * | 2011-07-25 | 2013-01-31 | Google Inc. | Hotel results interface |
| US20150073941A1 (en) * | 2011-12-13 | 2015-03-12 | Emma Burrows | Hotel finder interface |
| CN109740072B (en) * | 2018-12-29 | 2023-07-04 | 携程计算机技术（上海）有限公司 | Hotel ordering method and system based on POI under OTA platform |
| CN110070393A (en) * | 2019-06-19 | 2019-07-30 | 成都大象分形智能科技有限公司 | Ads on Vehicles interacts jettison system under line based on cloud artificial intelligence |
| CN111353851A (en) * | 2020-02-27 | 2020-06-30 | 携程计算机技术（上海）有限公司 | Hotel sorting recommendation method and device, electronic equipment and storage medium |
-
2021
- 2021-07-05 CN CN202110757970.6A patent/CN113590937B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107481054A (en) * | 2017-08-14 | 2017-12-15 | 携程计算机技术（上海）有限公司 | The push of hotel's favor information and device, electronic equipment, storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113590937A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109299372B (en) | Intelligent course selection recommendation method based on collaborative filtering | |
| CN109582875B (en) | Personalized recommendation method and system for online medical education resources | |
| CN104732413B (en) | A kind of intelligent personalized video ads method for pushing and system | |
| CN101523412B (en) | Face-based image clustering | |
| CN112131978B (en) | Video classification method and device, electronic equipment and storage medium | |
| CN107305557A (en) | Content recommendation method and device | |
| Kaur et al. | Deep neural network for food image classification and nutrient identification: A systematic review | |
| Ragab et al. | HRSPCA: Hybrid recommender system for predicting college admission | |
| CN108446351B (en) | Hotel screening method and system based on user preference of OTA platform | |
| CN108897750B (en) | Personalized place recommendation method and device integrating multiple contextual information | |
| CN103793717A (en) | Methods for determining image-subject significance and training image-subject significance determining classifier and systems for same | |
| CN108197636A (en) | A kind of paddy detection and sorting technique based on depth multiple views feature | |
| CN113761259A (en) | Image processing method and device and computer equipment | |
| CN109558541A (en) | A kind of method, apparatus and computer storage medium of information processing | |
| CN108427740A (en) | A kind of Image emotional semantic classification and searching algorithm based on depth measure study | |
| CN110929746A (en) | Electronic file title positioning, extracting and classifying method based on deep neural network | |
| CN113590937B (en) | Hotel searching and information management method and device, electronic equipment and storage medium | |
| CN114330752A (en) | Ranking model training method and ranking method | |
| CN111738856A (en) | Stock public opinion investment decision analysis method and device | |
| CN115280353A (en) | Fund combination updating method, apparatus, device and medium based on artificial intelligence | |
| CN115396389A (en) | Internet of things information technology customer service system based on emotion energy perception | |
| CN114997956A (en) | Mother and infant product intelligent recommendation system based on big data | |
| CN110909193B (en) | Image ordering display method, system, device and storage medium | |
| CN110472639B (en) | Target extraction method based on significance prior information | |
| CN111445280A (en) | Model generation method, restaurant ranking method, system, device and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Hotel search and information management methods, devices, electronic devices, and storage media Effective date of registration: 20231025 Granted publication date: 20220419 Pledgee: Industrial and Commercial Bank of China Limited Shenzhen Nanshan Sub branch Pledgor: SHENZHEN TIANXIA FANGCANG TECHNOLOGY CO.,LTD. Registration number: Y2023980062595 |