CN112612957A - Interest point recommendation method, interest point recommendation model training method and device - Google Patents
Interest point recommendation method, interest point recommendation model training method and device Download PDFInfo
- Publication number
- CN112612957A CN112612957A CN202011554561.8A CN202011554561A CN112612957A CN 112612957 A CN112612957 A CN 112612957A CN 202011554561 A CN202011554561 A CN 202011554561A CN 112612957 A CN112612957 A CN 112612957A
- Authority
- CN
- China
- Prior art keywords
- interest
- points
- candidate
- point
- historical
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012549 training Methods 0.000 title claims abstract description 25
- 230000006399 behavior Effects 0.000 claims abstract description 42
- 238000004590 computer program Methods 0.000 claims abstract description 10
- 238000012163 sequencing technique Methods 0.000 claims description 30
- 238000000605 extraction Methods 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 235000017337 Persicaria hydropiper Nutrition 0.000 description 2
- 240000000275 Persicaria hydropiper Species 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 235000011201 Ginkgo Nutrition 0.000 description 1
- 235000008100 Ginkgo biloba Nutrition 0.000 description 1
- 244000194101 Ginkgo biloba Species 0.000 description 1
- 241000722921 Tulipa gesneriana Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a point of interest recommendation method, a point of interest recommendation model training method, a device, equipment, a storage medium and a computer program product, and relates to the fields of big data, artificial intelligence, deep learning and the like. The specific implementation scheme is as follows: determining historical interest points visited by the current user according to the historical behaviors of the current user; determining a plurality of candidate interest points according to the historical interest points; sorting the candidate interest points by using the label of each candidate interest point; and recommending a plurality of candidate interest points according to the ranking. And constructing the interest of the current user by using the historical behavior of the current user, and expanding the interest of the current user to obtain candidate interest points. And then, a recommendation sequence is obtained according to the labels of the candidate interest points, so that thousands of people can be found in the map application program by combining the interests of the user, the personalized requirements of the user are met, and the use experience of the user is improved.
Description
Technical Field
The application relates to the technical field of computers, in particular to the fields of big data, artificial intelligence, deep learning and the like.
Background
Most of the users' habits of using map applications are that they search themselves or find their surroundings by finding their entrances. When a user retrieves and discovers surrounding results, the map usually returns fixed results which are ranked based on the heat and quality of the points of interest, and the user experience is poor.
Disclosure of Invention
The application provides a point of interest recommendation method, a point of interest recommendation model training method, a device, equipment, a storage medium and a computer program product.
According to an aspect of the present application, there is provided a point of interest recommendation method, which may include the steps of:
determining historical interest points visited by the current user according to the historical behaviors of the current user;
determining a plurality of candidate interest points according to the historical interest points;
sorting the candidate interest points by using the label of each candidate interest point;
and recommending a plurality of candidate interest points according to the ranking.
According to another aspect of the present application, there is provided a method for training a point of interest recommendation model, which may include the following steps:
for a plurality of interest point samples, obtaining a label and a sequencing truth value of each interest point sample;
determining the weight of the label of the interest point sample;
obtaining a sequencing predicted value of each interest point sample by the interest point recommendation model to be trained according to the label of each interest point sample and the weight of the label;
and training the interest point recommendation model to be trained according to the sequencing predicted value and the sequencing true value until the error between the sequencing predicted value and the sequencing true value is within an allowable range.
According to a third aspect of the present application, there is provided an apparatus for recommending a point of interest, the apparatus may include:
the historical interest point determining module is used for determining the historical interest points visited by the current user according to the historical behaviors of the current user;
the candidate interest point determining module is used for determining a plurality of candidate interest points according to the historical interest points;
the ordering module is used for ordering the candidate interest points by utilizing the label of each candidate interest point;
and the recommending module is used for recommending a plurality of candidate interest points according to the sorting.
According to a fourth aspect of the present application, there is provided an apparatus for training a point of interest recommendation model, which may include:
the interest point sample information acquisition module is used for acquiring the label and the ordering truth value of each interest point sample for the plurality of interest point samples;
the weight determining module of the label of the interest point sample is used for determining the weight of the label of the interest point sample;
the ranking predicted value determining module is used for enabling the interest point recommendation model to be trained to obtain the ranking predicted value of each interest point sample according to the label of each interest point sample and the weight of the label;
and the training module is used for training the interest point recommendation model to be trained according to the sequencing predicted value and the sequencing true value until the error between the sequencing predicted value and the sequencing true value is within an allowable range.
In a fifth aspect, an embodiment of the present application provides an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to cause the at least one processor to perform a method provided by any one of the embodiments of the present application.
In a sixth aspect, embodiments of the present application provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a method provided by any one of the embodiments of the present application.
According to another aspect of the application, there is provided a computer program product comprising computer instructions which, when executed by a processor, implement the method of any of the embodiments of the application.
According to the technology of the application, the interest of the current user is constructed by utilizing the historical behavior of the current user, and the interest is expanded to obtain candidate interest points. And then, a recommendation sequence is obtained according to the labels of the candidate interest points, so that thousands of people can be found in the map application program by combining the interests of the user, the personalized requirements of the user are met, and the use experience of the user is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is a flow chart of a point of interest recommendation method according to the present application;
FIG. 2 is a flow diagram of ranking a plurality of candidate points of interest according to the present application;
FIG. 3 is a flow chart of determining a plurality of candidate points of interest according to the present application;
FIG. 4 is a flow chart of determining a plurality of candidate points of interest according to the present application;
FIG. 5 is a flow chart of a training method of a point of interest recommendation model according to the present application;
FIG. 6 is a schematic diagram of a recommendation device for points of interest according to the present application;
FIG. 7 is a schematic diagram of a training apparatus for a point of interest recommendation model according to the present application;
FIG. 8 is a scenario diagram of a recommendation method that may implement points of interest;
fig. 9 is a block diagram of an electronic device for implementing a point of interest recommendation method and/or a point of interest recommendation model training method according to an embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
As shown in fig. 1, in one embodiment, the present application relates to a point of interest recommendation method, which may include the following steps:
s101: determining historical interest points visited by the current user according to the historical behaviors of the current user;
s102: determining a plurality of candidate interest points according to the historical interest points;
s103: sorting the candidate interest points by using the label of each candidate interest point;
s104: and recommending a plurality of candidate interest points according to the ranking.
The scheme of the application can be applied to map applications. The historical behavior of the current user may include search records, navigation records, etc. of the current user. Such as sights searched by the current user, restaurants navigated, etc., can be taken as the historical behavior of the current user. In addition, the search record may also be a search for verticals. For example, a nearby hot pot restaurant, a nearby bookstore, etc. is searched. Then, the hot pot restaurant and the bookstore may be treated as different verticals.
Under the condition that the current user searches or navigates, the candidate interest points with higher relevance to the historical interest points can be obtained according to the historical interest points searched or navigated by the current user. The determination mode of the candidate interest points can be determined according to the geographic position, the same vertical category or not, the average consumption amount and the like. Or, weights may be set for the interest points determined in different determination manners, and a predetermined number of interest points may be screened out as candidate interest points by using a weighted sum manner.
Each candidate point of interest may include at least one tag. For example, the tag may be the number of times the point of interest is a candidate point of interest, the number of times the point of interest is visited, and so on. And comprehensively comparing each candidate interest point by using the tags, and sequencing each interest point according to the comparison result.
For example, the rank of each point of interest may be determined as a ratio of the number of times the point of interest is visited to the number of times it is a candidate point of interest. Or just the number of times the point of interest is visited, etc.
By ranking each candidate point of interest, the point of interest may be recommended using the ranking. For example, in the case where a current user search "gourmet" instruction is received. And adding a 'guess you like' module in the retrieval list. The content of the restaurant ranking method is that a plurality of candidate restaurants which are ranked completely are determined according to the historical behaviors of the current user. For another example, in the case that the current user click "view periphery" instruction is received, the candidate points of interest may be presented in different ways. For one, the points of interest with the same characteristics may be displayed in an aggregated manner, such as "the top ten of the surrounding chafing dish", "the most popular network red card places around", and so on. And secondly, the traditional recall results can be displayed after being reordered.
By the scheme, the interest of the current user is constructed by utilizing the historical behavior of the current user, and the interest is expanded to obtain the candidate interest point. And then, a recommendation sequence is obtained according to the labels of the candidate interest points, so that thousands of people can be found in the map application program by combining the interests of the user, the personalized requirements of the user are met, and the use experience of the user is improved.
Referring to fig. 2, in one embodiment, the step S102 of ranking the candidate points of interest by using the label of each candidate point of interest includes:
s201: extracting a plurality of labels of each candidate interest point;
s202: determining a weight for each tag of each candidate point of interest;
s203: and for each candidate interest point, inputting each label of the candidate interest point and the weight of each label into a pre-trained ranking model to obtain a ranking result of the candidate interest point.
The tags of a candidate point of interest may include the number of times it was selected as a candidate point of interest, which may be the number of times the point of interest (in response to a user search) was presented. The number of times presented may be the number of times presented in response to all users' searches or navigations.
The tags may in turn include the number of times the candidate point of interest was clicked on by the user for viewing. The candidate interest points are not limited to the current user but are clicked and viewed by all users.
The tag may also include the time at which the candidate point of interest was visited. The time may be aggregated into several time periods of morning, noon, afternoon, evening, midnight, etc.
In addition, the tags may also include the proportion of candidate points of interest visited by local and foreign users. The judgment basis of the local user and the foreign user can be determined according to the historical behavior analysis of the user. For example, in the past year, more than a predetermined number of destinations in the first user's search and navigation records were in Beijing, then the first user may be determined to be a Beijing user. In the past year, more than a predetermined number of destinations in the search record and navigation record of the second user are in Shanghai, the second user may be determined to be a Shanghai user. When the Shanghai user visits a certain point of interest in Beijing, it can be recorded as the visit of the point of interest by the foreign user. The ratio of the number of times that the candidate interest point is accessed by the local user to the number of times that the candidate interest point is accessed by the foreign user in the past period can be used as the access ratio of the local user to the foreign user.
Different labels may be assigned different weights. The allocation mode can be determined in advance and can be determined by calculation by using a weight calculation model.
And inputting the label of each candidate interest point and the weight of the label into a pre-trained ranking model to obtain the ranking of each candidate interest point. The output of the ranking model may be the probability of each candidate point of interest being clicked, the probability of each candidate point of interest being exposed, etc. The candidate points of interest may be ranked according to the results output by the ranking model.
Through the scheme, after the candidate interest points are determined, the candidate interest points can be ranked according to the labels of the candidate interest points. So that the sorting result is more in line with the preference of the current user.
In one embodiment, the tags for the candidate points of interest include: as at least one of the number of candidate points of interest, the number of times visited, the time visited, and the ratio of the number of times visited by the local user to the number of times visited by the foreign user.
By the scheme, the accuracy of sequencing is improved by utilizing the multi-dimensional labels of the candidate interest points.
As shown in fig. 3, in one embodiment, the step of determining a plurality of candidate interest points according to historical interest points in step S102 may include the following sub-steps:
s301: acquiring the characteristics of historical interest points;
s302: and according to the similarity of the features, taking the interest points with similar features with the historical interest points as candidate interest points.
The historical behavior may include search records, navigation records, etc. of the current user. Through big data analysis, the historical behaviors of the user on the map for the consumption type interest points are sparse, and usually, the user only expresses interests in a few consumption type interest points within a period of time, so that the interest of the current user needs to be expanded and mined. The consumer points of interest may be restaurants, hotels, movie theaters, parks, and the like.
For example, if a current user's search or navigation record contains a certain hot pot restaurant, the hot pot restaurant may be a historical point of interest. The hot pot restaurant is characterized by being used for catering, hot pot, geographical position, per capita consumption amount, main dish serving and the like.
For another example, if a park is included in the current user's search or navigation records, the park may be a historical point of interest. The park may be characterized as a point of interest historic site, red leaf theme park, geographic location, etc.
According to the feature similarity, the interest points with the same or similar features as the historical interest points can be used as candidate interest points. The feature similarity may be interest points of the same verticals, and taking a hot pot restaurant as an example, the verticals of the hot pot restaurant may be restaurants or hot pots. Therefore, the interest points with the same verticals as the hot pot restaurant can be used as candidate interest points.
As another example, a park may be characterized as a red leaf theme park, and points of interest of similar characteristics may be selected without the same characteristic points of interest. For example, tulip theme parks, ginkgo theme parks, and the like may be selected.
In the above, taking the same or similar features as an example, in the process of substantially determining the candidate interest point, a plurality of features of the reference interest point may be synthesized, so as to achieve the best matching. Feature similarity may be matched according to euclidean distances between features.
By the scheme, under the condition that historical interest points are few, the interest points can be expanded by utilizing the feature similarity, so that candidate interest points are obtained.
In one embodiment, the characteristics of the historical points of interest include: at least one of a vertical category, a geographic location, an average cost price, and a user rating.
By the scheme, the number of candidate interest points can be increased by utilizing the multi-dimensional characteristics.
As shown in fig. 4, in one embodiment, the step of determining a plurality of candidate interest points according to historical interest points in step S102 may include the following sub-steps:
s401: acquiring historical operation behaviors of other users who have accessed historical interest points;
s402: and determining other interest points accessed by other users after accessing the historical interest points from the historical operation behaviors of the other users, and determining the other interest points as candidate interest points.
After determining the historical interest point visited by the current user, the historical operation behavior of other users who visited the historical interest point can be queried in the database.
For example, if the first user's historical point of interest is a hot pot restaurant, the database may be queried for other users who have also visited the hot pot restaurant. The interest points visited by other users after visiting the hot pot restaurant can be obtained, and the interest points visited by other users after visiting the hot pot restaurant are determined as candidate interest points.
It will be appreciated that other points of interest accessed by other users prior to accessing historical points of interest are also possible.
By the scheme, the interest points can be expanded by using the historical behaviors of the current user and other users. Namely, the expansion of the interest points is realized by searching the historical behaviors of the users with the same interests and hobbies.
Referring to fig. 5, the present application provides a method for training a point of interest recommendation model, which may include the following steps:
s501: for a plurality of interest point samples, obtaining a label and a sequencing truth value of each interest point sample;
s502: determining the weight of the label of the interest point sample;
s503: obtaining a sequencing predicted value of each interest point sample by the interest point recommendation model to be trained according to the label of each interest point sample and the weight of the label;
s504: and training the interest point recommendation model to be trained according to the sequencing predicted value and the sequencing true value until the error between the sequencing predicted value and the sequencing true value is within an allowable range.
The point of interest samples may be pre-labeled samples. For example, for a hot pot restaurant, labels such as the number of times the hot pot restaurant is a candidate point of interest, the number of times it is visited, the time visited, the proportion visited by local users and foreign users, etc. may be counted.
Second, weights may be assigned for different tags. The weight distribution mode may be a weight distribution calculation model distribution, or may be other distribution modes.
In addition, the labeled samples also include ordering truth values. The ranking truth value can be click rate, search times and other data.
And inputting the labels loaded with different weights into the interest point recommendation model to be trained to obtain the sequencing predicted value of each interest point sample. The rank prediction value has an error when compared to the rank true value. The error is propagated backwards in each layer of the interest point recommendation model to be trained, and the parameters of each layer are adjusted according to the error until the output of the interest point recommendation model to be trained converges or reaches the expected effect. For example, the error between the predicted value and the true value may be within an allowable range.
In one embodiment, the labels for the point of interest samples include: at least one of the number of times exposed, the number of times accessed, the time accessed, the proportion accessed by local users and foreign users.
Referring to fig. 6, the present application provides a point of interest recommendation apparatus, which may include:
a historical interest point determining module 601, configured to determine a historical interest point visited by a current user according to a historical behavior of the current user;
a candidate interest point determining module 602, configured to determine a plurality of candidate interest points according to historical interest points;
a ranking module 603, configured to rank, using the tag of each candidate interest point, a plurality of candidate interest points;
a recommending module 604, configured to recommend the candidate points of interest according to the ranking.
In one embodiment, the sorting module 604 may further include:
the label extraction submodule is used for extracting a plurality of labels of each candidate interest point;
the weight determining submodule is used for determining the weight of each label of each candidate interest point;
and the ranking execution sub-module is used for inputting each label of each candidate interest point and the weight of each label into a pre-trained ranking model for each candidate interest point to obtain a ranking result of the candidate interest point.
In one embodiment, the tags for the candidate points of interest include: as at least one of the number of candidate points of interest, the number of times visited, the time visited, and the ratio of the number of times visited by the local user to the number of times visited by the foreign user.
In one embodiment, the candidate point of interest determination module 602 may further include:
the characteristic acquisition submodule is used for acquiring the characteristics of the historical interest points;
and the candidate interest point determination execution submodule is used for taking the interest points with similar characteristics with the historical interest points as candidate interest points according to the similarity of the characteristics.
In one embodiment, the characteristics of the historical points of interest include: at least one of a vertical category, a geographic location, an average cost price, and a user rating.
In one embodiment, the candidate interest point determining module 602 may further include:
the historical operation behavior acquisition module of other users is used for acquiring the historical operation behaviors of other users who have accessed the historical interest points;
and the candidate interest point determining and executing submodule is used for determining other interest points accessed by other users after accessing the historical interest points from the historical operation behaviors of the other users, and determining the other interest points as candidate interest points.
As shown in fig. 7, the present application provides an apparatus for training a point of interest recommendation model, which may include:
an interest point sample information obtaining module 701, configured to obtain, for multiple interest point samples, a label and a ranking true value of each interest point sample;
a weight determination module 702 of the label of the interest point sample, configured to determine the weight of the label of the interest point sample;
a ranking prediction value determination module 703, configured to enable the to-be-trained interest point recommendation model to obtain a ranking prediction value of each interest point sample according to the label of each interest point sample and the weight of the label;
the training module 704 is configured to train the interest point recommendation model to be trained according to the predicted ranking value and the true ranking value until an error between the predicted ranking value and the true ranking value is within an allowable range.
In one embodiment, the labels for the point of interest samples include: at least one of the number of times of being exposed, the number of times of being accessed, the time of being accessed, and the ratio of the number of times of being accessed by the local user to the number of times of being accessed by the foreign user.
FIG. 8 is a scenario diagram in which a point of interest recommendation method may be implemented.
The interest capturing module is used for storing the behaviors of the user in the whole map, such as retrieval, navigation and the like, into the behavior log library so as to learn the interest of the user in the interest points. Such as the user having retrieved the summer palace, navigated to the palace, etc., at which step it will be recorded as a sequence of points of interest, different actions (retrieval, navigation) being given different weights.
For example, the following steps are carried out: assuming that the user searched for the summer garden, the old palace, the Yuanming garden over a period of time, the sequence of interest is recorded as:
[ Yihe garden, feat1] [ Imperial palace, feat2] [ Yuanming garden, feat3]
The flat contains the operation characteristics of the user on the interest point, such as operation time, operation type (retrieval, navigation, etc.), user status (whether on the way to travel, etc.), and the like.
The interest expansion mining module: the behavior of a user on a map for consumer interest points is usually sparse, and usually only a few interest points are expressed in a period of time, so that the interest of the user needs to be expanded and mined. And performing interest expansion data mining and offline storage through behavior association mining, a tag library and a content library. The online part can achieve the purpose of interest expansion only by carrying out query operation according to the interest point sequence of the user.
Behavior association mining is mainly performed from two aspects: first, association of contents. Recommending recommended items similar to the interesting point of interest content for the user. When the user clicks the hot pot restaurant, the hot pot restaurant with the same price and a short distance can be used as a recommendation. And II, association of click behaviors. It can be understood that most users search for which places after searching for the hot pot restaurant, and take the places searched subsequently as similar interest points. And mining corresponding behavior association recalls by the behavior association.
The content depot may be used for ontology recalls. The user searches the hot pot restaurant A, and the hot pot restaurant A can be used as a recommendation, namely the self-recall. The tag library stores tags of each interest point, so that the similarity of the interest points can be conveniently determined according to the tag distance, namely content association recall is performed.
The ontology recall, the content association recall and the behavior association recall constitute the candidate interest points.
The interest ranking module is used for ranking the candidate interest points. The candidate interest points can be scored by utilizing the LTR model, and finally, a sorting result is output. The LTR model can be learned according to the stored content of the behavior log and the scene log. The scene log is used for storing scenes when the user acts, such as action time, place, whether to drive a car and the like. For the learning of the LTR model, iteration can be performed with the help of user behavior collected in real time by big data. Therefore, the accuracy of the on-line sequencing model meets the requirement.
There is also provided, in accordance with an embodiment of the present application, an electronic device, a readable storage medium, and a computer program product.
FIG. 9 illustrates a schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 9, the device 900 includes a computing unit 910 that may perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)920 or a computer program loaded from a storage unit 980 into a Random Access Memory (RAM) 930. In the RAM 930, various programs and data required for the operation of the device 900 may also be stored. The calculation unit 910, the ROM 920, and the RAM 930 are connected to each other via a bus 940. An input/output (I/O) interface 950 is also connected to bus 940.
Various components in device 900 are connected to I/O interface 950, including: an input unit 960 such as a keyboard, a mouse, etc.; an output unit 970 such as various types of displays, speakers, and the like; a storage unit 980 such as a magnetic disk, optical disk, or the like; and a communication unit 990 such as a network card, a modem, a wireless communication transceiver, or the like. The communication unit 990 allows the device 900 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present application may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this application, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present application can be achieved, and the present invention is not limited herein.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (19)
1. A point of interest recommendation method comprises the following steps:
determining historical interest points visited by the current user according to the historical behaviors of the current user;
determining a plurality of candidate interest points according to the historical interest points;
ranking the plurality of candidate points of interest using the label of each of the candidate points of interest;
and recommending the candidate interest points according to the sorting.
2. The method of claim 1, wherein said ranking said plurality of candidate points of interest with a label for each of said candidate points of interest comprises:
extracting a plurality of labels of each candidate interest point;
determining a weight for each tag of each of the candidate points of interest;
and for each candidate interest point, inputting each label of the candidate interest point and the weight of each label into a pre-trained ranking model to obtain a ranking result of the candidate interest point.
3. The method of claim 2, wherein the labels of the candidate points of interest comprise: as at least one of the number of candidate points of interest, the number of times visited, the time visited, and the ratio of the number of times visited by the local user to the number of times visited by the foreign user.
4. The method of any one of claims 1 to 3, wherein the determining historical points of interest visited by the current user based on the historical behavior of the current user comprises:
acquiring the characteristics of the historical interest points;
and according to the similarity of the features, taking the interest points with similar features with the historical interest points as candidate interest points.
5. The method of claim 4, the characteristics of the historical points of interest comprising: at least one of a vertical category, a geographic location, an average cost price, and a user rating.
6. The method of any one of claims 1 to 3, wherein the determining historical points of interest visited by the current user based on the historical behavior of the current user comprises:
acquiring historical operation behaviors of other users who have accessed the historical interest points;
and determining other interest points accessed by the other users after accessing the historical interest points from the historical operation behaviors of the other users, and determining the other interest points as candidate interest points.
7. A training method of an interest point recommendation model comprises the following steps:
for a plurality of interest point samples, obtaining a label and a sequencing truth value of each interest point sample;
determining a weight of a label of the point of interest sample;
obtaining a sequencing predicted value of each interest point sample by the interest point recommendation model to be trained according to the label of each interest point sample and the weight of the label;
and training the interest point recommendation model to be trained according to the sequencing predicted value and the sequencing true value until the error between the sequencing predicted value and the sequencing true value is within an allowable range.
8. The method of claim 7, wherein the label of the point of interest sample comprises: at least one of the number of times of being exposed, the number of times of being accessed, the time of being accessed, and the ratio of the number of times of being accessed by the local user to the number of times of being accessed by the foreign user.
9. An apparatus for recommending points of interest, comprising:
the historical interest point determining module is used for determining the historical interest points visited by the current user according to the historical behaviors of the current user;
a candidate interest point determining module, configured to determine a plurality of candidate interest points according to the historical interest points;
a ranking module for ranking the plurality of candidate interest points using the label of each of the candidate interest points;
and the recommending module is used for recommending the candidate interest points according to the sorting.
10. The apparatus of claim 9, wherein the ranking module comprises:
a label extraction submodule, configured to extract a plurality of labels of each candidate interest point;
the weight determining submodule is used for determining the weight of each label of each candidate interest point;
and the ranking execution sub-module is used for inputting each label of the candidate interest point and the weight of each label into a pre-trained ranking model for each candidate interest point to obtain a ranking result of the candidate interest point.
11. The apparatus of claim 9, wherein the labels of the candidate points of interest comprise: as at least one of the number of candidate points of interest, the number of times visited, the time visited, and the ratio of the number of times visited by the local user to the number of times visited by the foreign user.
12. The apparatus of any of claims 9 to 11, wherein the candidate point of interest determination module comprises:
the characteristic obtaining submodule is used for obtaining the characteristics of the historical interest points;
and the candidate interest point determination execution submodule is used for taking the interest points with similar characteristics with the historical interest points as candidate interest points according to the characteristic similarity.
13. The apparatus of claim 12, the characteristics of the historical points of interest comprising: at least one of a vertical category, a geographic location, an average cost price, and a user rating.
14. The apparatus of any of claims 9 to 11, wherein the candidate point of interest determination module comprises:
the historical operation behavior acquisition module of other users is used for acquiring the historical operation behaviors of other users who have accessed the historical interest points;
and the candidate interest point determining and executing submodule is used for determining other interest points accessed by the other users after the other users access the historical interest points from the historical operation behaviors of the other users, and determining the other interest points as candidate interest points.
15. An apparatus for training a point of interest recommendation model, comprising:
the interest point sample information acquisition module is used for acquiring the label and the ordering truth value of each interest point sample for a plurality of interest point samples;
the weight determining module of the label of the interest point sample is used for determining the weight of the label of the interest point sample;
the ranking predicted value determining module is used for enabling the interest point recommendation model to be trained to obtain the ranking predicted value of each interest point sample according to the label of each interest point sample and the weight of the label;
and the training module is used for training the interest point recommendation model to be trained according to the sequencing predicted value and the sequencing true value until the error between the sequencing predicted value and the sequencing true value is within an allowable range.
16. The apparatus of claim 15, wherein the label of the point of interest sample comprises: at least one of the number of times of being exposed, the number of times of being accessed, the time of being accessed, and the ratio of the number of times of being accessed by the local user to the number of times of being accessed by the foreign user.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 8.
18. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 8.
19. A computer program product comprising computer instructions which, when executed by a processor, implement the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011554561.8A CN112612957B (en) | 2020-12-24 | 2020-12-24 | Recommendation method of interest points and training method and device of recommendation model of interest points |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011554561.8A CN112612957B (en) | 2020-12-24 | 2020-12-24 | Recommendation method of interest points and training method and device of recommendation model of interest points |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112612957A true CN112612957A (en) | 2021-04-06 |
| CN112612957B CN112612957B (en) | 2023-09-29 |
Family
ID=75245208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011554561.8A Active CN112612957B (en) | 2020-12-24 | 2020-12-24 | Recommendation method of interest points and training method and device of recommendation model of interest points |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112612957B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113139139A (en) * | 2021-04-28 | 2021-07-20 | 北京百度网讯科技有限公司 | Method, apparatus, electronic device, and medium for determining boarding point |
| CN113407849A (en) * | 2021-07-15 | 2021-09-17 | 百果园技术(新加坡)有限公司 | Coarse sorting method and device |
| CN113536120A (en) * | 2021-07-14 | 2021-10-22 | 北京百度网讯科技有限公司 | User behavior based point of interest recall and apparatus |
| CN113536152A (en) * | 2021-06-30 | 2021-10-22 | 北京百度网讯科技有限公司 | Map interest point display method and device and electronic equipment |
| CN113569149A (en) * | 2021-07-30 | 2021-10-29 | 拉扎斯网络科技（上海）有限公司 | Information processing method and device and electronic equipment |
| CN113822594A (en) * | 2021-09-30 | 2021-12-21 | 阿里巴巴新加坡控股有限公司 | Interest point grading determination method, electronic equipment and computer program product |
| CN113868532A (en) * | 2021-09-30 | 2021-12-31 | 北京百度网讯科技有限公司 | Location recommendation method and device, electronic equipment and storage medium |
| CN114662020A (en) * | 2022-04-29 | 2022-06-24 | 深圳依时货拉拉科技有限公司 | Method and device for point of interest recommendation based on contour of point of interest |
| CN114708008A (en) * | 2021-12-30 | 2022-07-05 | 北京有竹居网络技术有限公司 | A promotion content processing method, device, equipment, medium and product |
| CN115344175A (en) * | 2022-08-17 | 2022-11-15 | 江苏满运物流信息有限公司 | Map navigation method, apparatus, device and medium |
| CN115858954A (en) * | 2022-12-29 | 2023-03-28 | 腾讯科技（深圳）有限公司 | Method and device for recommending interest points, electronic equipment and storage medium |
| CN116757348A (en) * | 2023-07-05 | 2023-09-15 | 黑龙江省辰源投资管理有限公司 | Travel information intelligent planning management system and method based on artificial intelligence |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140071138A1 (en) * | 2012-09-11 | 2014-03-13 | International Business Machines Corporation | Determining Alternative Visualizations for Data Based on an Initial Data Visualization |
| CN105227971A (en) * | 2015-07-09 | 2016-01-06 | 传成文化传媒（上海）有限公司 | The information recommendation method of a kind of hotel TV and system |
| CN108804619A (en) * | 2018-05-31 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Interest preference prediction technique, device, computer equipment and storage medium |
| WO2019187421A1 (en) * | 2018-03-29 | 2019-10-03 | ソニー株式会社 | Information processing device, information processing method, and program |
| CN110941739A (en) * | 2018-09-22 | 2020-03-31 | 北京微播视界科技有限公司 | Media file recommendation method and device, media file server and storage medium |
| CN111008321A (en) * | 2019-11-18 | 2020-04-14 | 广东技术师范大学 | Recommendation method and device based on logistic regression, computing equipment and readable storage medium |
| CN111831899A (en) * | 2019-09-24 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Navigation interest point recommendation method and device and server |
-
2020
- 2020-12-24 CN CN202011554561.8A patent/CN112612957B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140071138A1 (en) * | 2012-09-11 | 2014-03-13 | International Business Machines Corporation | Determining Alternative Visualizations for Data Based on an Initial Data Visualization |
| CN105227971A (en) * | 2015-07-09 | 2016-01-06 | 传成文化传媒（上海）有限公司 | The information recommendation method of a kind of hotel TV and system |
| WO2019187421A1 (en) * | 2018-03-29 | 2019-10-03 | ソニー株式会社 | Information processing device, information processing method, and program |
| CN108804619A (en) * | 2018-05-31 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Interest preference prediction technique, device, computer equipment and storage medium |
| CN110941739A (en) * | 2018-09-22 | 2020-03-31 | 北京微播视界科技有限公司 | Media file recommendation method and device, media file server and storage medium |
| CN111831899A (en) * | 2019-09-24 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Navigation interest point recommendation method and device and server |
| CN111008321A (en) * | 2019-11-18 | 2020-04-14 | 广东技术师范大学 | Recommendation method and device based on logistic regression, computing equipment and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 胡德敏;杨晨;: "一种基于多类型情景信息的兴趣点推荐模型", 计算机应用研究, no. 06 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113139139A (en) * | 2021-04-28 | 2021-07-20 | 北京百度网讯科技有限公司 | Method, apparatus, electronic device, and medium for determining boarding point |
| CN113139139B (en) * | 2021-04-28 | 2023-09-22 | 北京百度网讯科技有限公司 | Method, device, electronic equipment and medium for determining boarding point |
| CN113536152B (en) * | 2021-06-30 | 2024-02-09 | 北京百度网讯科技有限公司 | Map interest point display method and device and electronic equipment |
| CN113536152A (en) * | 2021-06-30 | 2021-10-22 | 北京百度网讯科技有限公司 | Map interest point display method and device and electronic equipment |
| US11893073B2 (en) | 2021-06-30 | 2024-02-06 | Beijing Baidu Netcom Science Technology Co., Ltd. | Method and apparatus for displaying map points of interest, and electronic device |
| CN113536120A (en) * | 2021-07-14 | 2021-10-22 | 北京百度网讯科技有限公司 | User behavior based point of interest recall and apparatus |
| CN113536120B (en) * | 2021-07-14 | 2023-08-01 | 北京百度网讯科技有限公司 | Point-of-interest recall method and device based on user behavior |
| CN113407849A (en) * | 2021-07-15 | 2021-09-17 | 百果园技术(新加坡)有限公司 | Coarse sorting method and device |
| CN113569149A (en) * | 2021-07-30 | 2021-10-29 | 拉扎斯网络科技（上海）有限公司 | Information processing method and device and electronic equipment |
| CN113569149B (en) * | 2021-07-30 | 2024-01-19 | 拉扎斯网络科技（上海）有限公司 | Information processing method and device and electronic equipment |
| CN113822594A (en) * | 2021-09-30 | 2021-12-21 | 阿里巴巴新加坡控股有限公司 | Interest point grading determination method, electronic equipment and computer program product |
| CN113868532A (en) * | 2021-09-30 | 2021-12-31 | 北京百度网讯科技有限公司 | Location recommendation method and device, electronic equipment and storage medium |
| US12067067B2 (en) | 2021-09-30 | 2024-08-20 | Beijing Baidu Netcom Science Technology Co., Ltd. | Site recommendation method, electronic device, and storage medium |
| CN114708008A (en) * | 2021-12-30 | 2022-07-05 | 北京有竹居网络技术有限公司 | A promotion content processing method, device, equipment, medium and product |
| CN114662020A (en) * | 2022-04-29 | 2022-06-24 | 深圳依时货拉拉科技有限公司 | Method and device for point of interest recommendation based on contour of point of interest |
| CN115344175A (en) * | 2022-08-17 | 2022-11-15 | 江苏满运物流信息有限公司 | Map navigation method, apparatus, device and medium |
| CN115858954A (en) * | 2022-12-29 | 2023-03-28 | 腾讯科技（深圳）有限公司 | Method and device for recommending interest points, electronic equipment and storage medium |
| CN116757348A (en) * | 2023-07-05 | 2023-09-15 | 黑龙江省辰源投资管理有限公司 | Travel information intelligent planning management system and method based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112612957B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112612957B (en) | Recommendation method of interest points and training method and device of recommendation model of interest points | |
| CN111538904B (en) | Method and device for recommending interest points | |
| CN112559879B (en) | Interest model training method, interest point recommending method, device and equipment | |
| WO2022134478A1 (en) | Route recommendation method and apparatus, electronic device, and storage medium | |
| US10169797B2 (en) | Identification of entities based on deviations in value | |
| CN111666461B (en) | Method, apparatus, device and computer storage medium for retrieving geographic location | |
| CN106776707A (en) | The method and apparatus of information pushing | |
| CN113536152B (en) | Map interest point display method and device and electronic equipment | |
| CN113656698A (en) | Training method and device of interest feature extraction model and electronic equipment | |
| CN113792212A (en) | Multimedia resource recommendation method, device, equipment and storage medium | |
| JP7206514B2 (en) | Method for sorting geolocation points, training method for sorting model, and corresponding device | |
| CN111754278A (en) | Item recommendation method, apparatus, computer storage medium and electronic device | |
| CN104516980B (en) | The output method and server system of search result | |
| CN111339423B (en) | User-based travel city pushing method, system, equipment and storage medium | |
| CN109977292A (en) | Searching method, calculates equipment and computer readable storage medium at device | |
| CN113326450B (en) | Point-of-interest recall method and device, electronic equipment and storage medium | |
| US20210389154A1 (en) | Method and apparatus for recommending map area, device and storage medium | |
| CN112000495B (en) | Method, electronic device and storage medium for point of interest information management | |
| CN113868532B (en) | Location recommendation method and device, electronic equipment and storage medium | |
| US11976935B2 (en) | Route recommendation method, electronic device, and storage medium | |
| CN112861023B (en) | Map information processing method, apparatus, device, storage medium, and program product | |
| CN114881557A (en) | Material information pushing method, device and equipment based on regions | |
| CN112528145A (en) | Information recommendation method, device, equipment and readable storage medium | |
| CN114036414A (en) | Method and device for processing interest points, electronic equipment, medium and program product | |
| CN114092192A (en) | Product pushing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |