CN112528145A - Information recommendation method, device, equipment and readable storage medium - Google Patents
Information recommendation method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN112528145A CN112528145A CN202011445091.1A CN202011445091A CN112528145A CN 112528145 A CN112528145 A CN 112528145A CN 202011445091 A CN202011445091 A CN 202011445091A CN 112528145 A CN112528145 A CN 112528145A
- Authority
- CN
- China
- Prior art keywords
- user
- historical
- model
- training sample
- retrieval
- 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 86
- 238000012549 training Methods 0.000 claims description 166
- 230000006399 behavior Effects 0.000 claims description 111
- 238000012545 processing Methods 0.000 claims description 18
- 238000013136 deep learning model Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 7
- 238000002372 labelling Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 abstract description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 21
- 238000010586 diagram Methods 0.000 description 20
- 235000013305 food Nutrition 0.000 description 17
- 238000013461 design Methods 0.000 description 16
- 238000004891 communication Methods 0.000 description 8
- 235000011888 snacks Nutrition 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 235000021170 buffet Nutrition 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 235000015219 food category Nutrition 0.000 description 2
- 238000007499 fusion processing Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 235000013410 fast food Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 235000015277 pork Nutrition 0.000 description 1
- 238000012827 research and development Methods 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
- 230000001960 triggered effect Effects 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
- G06F16/951—Indexing; Web crawling techniques
-
- 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
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses an information recommendation method, device, equipment and readable storage medium, and relates to the technical field of electronic maps in artificial intelligence. The specific implementation scheme is as follows: after receiving a request instruction of a user for requesting to open the electronic map, the server responds to the request instruction to predict whether the user has a retrieval intention. When the fact that the user has the search intention is predicted, a recommendation card is generated for the user and output, a plurality of search words are displayed on the recommendation card to be selected by the user, interaction efficiency is improved, and personalized recommendation is achieved.
Description
Technical Field
The present application relates to the field of electronic map technologies in artificial intelligence, and in particular, to an information recommendation method, apparatus, device, and readable storage medium.
Background
The electronic map has functions of navigation, positioning and the like, and becomes an indispensable tool in the life of people.
Users often use electronic maps to find a current location point or a certain type of POI near a certain point of interest (POI). In the searching process, buttons such as 'peripheral discovery' and the like on the electronic map are clicked, the electronic map pops up the window and recommends a card, a series of search terms are displayed on the recommending card, and each search term represents a type of POI. For example, if the search term is "food", the user clicks the "food", and then the electronic map jumps to a food page, and the food page displays various types of food, such as nearby food, snack, hot pot, and the like, for the user to select. Meanwhile, a plurality of hot restaurants and the like are displayed on the food page for the user to select. Due to the limited screen, if the kinds of the gourmets are various, some common gourmet kinds are displayed on the gourmet page, and some unusual gourmet kinds are displayed on the next-level page. For example, if the user clicks more on the food page, the next page is entered, and the next page lists more food categories for the user to select. In the process, each food category, such as chafing dish, etc., is regarded as a search word.
The electronic map can be triggered to directly initiate retrieval by clicking the 'periphery finding' mode, such as retrieving food, retrieving scenic spots and the like. However, if the search term desired by the user is hidden deeply, the user needs to interact with the electronic map for many times to find the search term, which is time-consuming, labor-consuming and inefficient.
Disclosure of Invention
The application provides an information recommendation method, an information recommendation device, information recommendation equipment and a readable storage medium, when a user is identified to have a search demand, a recommendation card which accords with user behaviors and a current scene is actively popped up, so that the user can click a search word on the recommendation card, and the user can quickly and conveniently find a certain type of interest point.
In a first aspect, an embodiment of the present application provides an information recommendation method, including: after receiving a request instruction of a user for requesting to open the electronic map, the server responds to the request instruction to predict whether the user has a retrieval intention. And when the fact that the user has the search intention is predicted, generating a recommendation card for the user and outputting the recommendation card, wherein a plurality of search terms are displayed on the recommendation card for the user to select.
In a second aspect, an embodiment of the present application provides a model training method, including: the electronic equipment utilizes historical data to construct a training sample, model training is conducted, a target model is obtained, the target model is a model associated with a recommendation card, a plurality of search terms are displayed on the recommendation card, and different search terms in the search terms represent POIs of different types.
In a third aspect, an embodiment of the present application provides an information recommendation device based on an electronic map, including:
the receiving module is used for receiving a request instruction of a user, and the request instruction is used for requesting to open the electronic map;
the prediction module is used for responding to the request instruction and predicting whether the user has the retrieval intention;
the processing module is used for generating a recommendation card for the user when the prediction module predicts that the user has a search intention, wherein a plurality of search terms are displayed on the recommendation card, and different search terms in the search terms represent POI (points of interest) of different categories;
and the output module is used for outputting the recommendation card.
In a fourth aspect, an embodiment of the present application provides a model training apparatus, including:
the construction module is used for constructing a training sample according to historical data to obtain a training sample set, wherein the historical data is data generated when a historical user operates the electronic map;
the training module is used for training an initial model by using the training sample to obtain a target model, the target model is a model associated with a recommendation card, a plurality of search terms are displayed on the recommendation card, and different search terms in the search terms represent interest points POI of different categories.
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 enable the at least one processor to perform the first aspect or any possible implementation of the method of the first aspect.
In a sixth 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 the second aspect or any possible implementation of the second aspect.
In a seventh aspect, embodiments of the present application provide a computer program product containing instructions, which when run on an electronic device, cause the electronic device computer to perform the method in the first aspect or in various possible implementation manners of the first aspect.
In an eighth aspect, embodiments of the present application provide a computer program product containing instructions, which when run on an electronic device, cause the electronic device computer to perform the method of the second aspect or the various possible implementations of the second aspect.
In a ninth aspect, embodiments of the present application provide a non-transitory computer-readable storage medium storing computer instructions for causing the electronic device to perform the method of the first aspect or the various possible implementations of the first aspect.
In a tenth aspect, embodiments of the present application provide a non-transitory computer-readable storage medium storing computer instructions for causing the electronic device to perform the method of the second aspect or the various possible implementations of the second aspect.
According to the technology of the application, when the user is identified to have the search appeal, the recommendation card which accords with the user behavior and the current scene is actively popped up for the user to click the search word on the recommendation card, so that the user can quickly and conveniently find a certain type of interest point, the input operation of the user on a search box is reduced, the user can be prevented from finding the search word through multiple clicks, the interaction efficiency is improved, and meanwhile, personalized recommendation is realized.
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 schematic diagram illustrating a process of a user searching for a POI of a certain type near a current location point;
FIG. 2A is a schematic diagram of a large box search;
FIG. 2B is a schematic view of a fixed-list search term landing page;
fig. 3 is a scene schematic diagram of an information recommendation method provided in an embodiment of the present application;
FIG. 4 is a flowchart of an information recommendation method provided in an embodiment of the present application;
fig. 5A is a schematic view of an electronic map interface in an information recommendation method provided in an embodiment of the present application;
fig. 5B is another schematic diagram of an electronic map interface in the information recommendation method provided in the embodiment of the present application;
FIG. 6 is a schematic diagram of a process of training and applying a first model in an information recommendation method provided in an embodiment of the present application;
FIG. 7 is a schematic diagram of a process of training and applying a second model in an information recommendation method provided by an embodiment of the present application;
FIG. 8 is a flow chart of a model training method provided by an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic map-based information recommendation device according to an embodiment of the present application;
FIG. 10 is a schematic structural diagram of a model training apparatus according to an embodiment of the present disclosure;
fig. 11 is a block diagram of an electronic device for implementing an information recommendation 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.
Currently, users often use electronic maps to find a certain type of POI. Fig. 1 is a schematic diagram illustrating a process of a user finding a POI of a certain type near a current location point. Referring to fig. 1, after the user opens the electronic map, the user has a request to search for a peripheral casino property. In the searching process, the user clicks the periphery firstly, then clicks more, and enters a more search term landing page. Then, the user slides the screen on the landing page to find the playground, and after clicking the playground, the electronic map positions a plurality of playgrounds.
If a user wants to search a certain type of POI near a certain position (which is not the current positioning point), the user needs to search the position on the electronic map and then quickly search by clicking the periphery. Or, the user moves the electronic map, for example, the user is in the sea, the current location point is in the sea, and the user wants to find a coffee shop near a certain destination location in the beijing haichi area, so that the electronic map displays the beijing area, then displays the haichi area, and then displays the destination location through sliding operation. Finally, the user clicks on the "periphery" for quick retrieval. And the electronic equipment locates POI (point of interest) which are interested by the user according to the retrieval of the user and pushes the POI.
In the information recommendation process based on the electronic map, if the search term expected by the user is hidden deeply, the user needs to interact with the electronic map for many times to find the search term, which wastes time and labor. Resulting in the user being able to search within the search box. However, if the user cannot organize the valid search terms, the results obtained by the search box search method are incorrect.
Fig. 2A is a schematic diagram of a large box search. Fig. 2B is a schematic diagram of a fixed list type search term landing page. Referring to fig. 2A, the large-frame search refers to a manner in which a user inputs search terms organized by himself in a search frame to perform a search. If the user cannot organize valid terms, there is a possibility that valid structures may not be retrieved. Referring to fig. 2B, the search terms in the landing page are fixed, and are a series of search terms obtained by the research and development staff according to the search behaviors of thousands of ordinary users. The user enters the search term landing page by clicking the periphery and clicking more, and the interaction process is complicated. For example, when a user wants to find a coffee shop in a sunny building, the user needs to slide the electronic map to beijing through touch operation, find the sunny building, click the periphery, find the coffee shop in the search term landing page, and click, so that the POI in the coffee shop can be searched. Moreover, since the search terms in the fixed list are fixed, it is impossible to perform scene-oriented and personalized recommendation according to the current scene and usage habit of the user.
The embodiment of the application aims to actively pop up the recommendation card which accords with user behaviors and the current scene when the user is identified to have the search appeal, so that the user can click the search terms on the recommendation card, and the user can quickly and conveniently find some interest points.
Fig. 3 is a scene schematic diagram of an information recommendation method provided in an embodiment of the present application. Referring to fig. 3, the scenario includes: the terminal device 301 and the server 302, and the terminal device 301 and the server 302 establish network connection. Wherein the server 302 predicts whether the user has a retrieval intention. And when the server predicts that the user has a search intention, generating a recommendation card for the user and pushing the recommendation card, wherein the recommendation card is provided with a plurality of search terms, and each search term represents a POI (point of interest). The recommendation cards of different users are different. Therefore, the user can search without entering the search term landing page through multiple operations, and the efficiency is high. Moreover, the search words on the recommendation card are related to the current scene of the user, the historical operation behavior of the user on the electronic map and the like, so that the search words on the recommendation card are more in line with the current appeal of the user, the efficiency is further improved, and the personalized recommendation is realized.
In fig. 3, the terminal device 301 may be a desktop terminal or a mobile terminal, the desktop terminal may be a computer, the mobile terminal may be a mobile phone, a tablet computer, a notebook computer, and the like, and the server 302 may be an independent server or a server cluster formed by a plurality of servers, and the like.
Fig. 4 is a flowchart of an information recommendation method provided in an embodiment of the present application, where the embodiment is described from the perspective of a server, and the embodiment includes:
401. and receiving a request instruction of a user.
The request instruction is used for requesting to open the electronic map.
For example, in fig. 3, an electronic map Application (APP) is installed on the terminal device 301. When the user clicks the APP to request opening of the electronic map, the terminal device 301 sends a request instruction to the server 302.
402. Responding to the request instruction, predicting whether the user has a retrieval intention, and if the user has a detection intention, executing step 403; if the user does not have an intention to detect, step 405 is performed.
After receiving a request instruction from the terminal device, the server judges whether the user has a search intention according to current scene information of a current scene of the user, historical data of a previous electronic map used by the user and the like, namely judges whether the user has an appeal of clicking search words such as gourmet, snack, parking lots and the like. If the server predicts that the user has a strong search intention, execute step 403; if the server predicts that the user has no strong search intention, step 405 is executed.
403. Generating a recommendation card for the user.
And displaying a plurality of search terms on the recommendation card, wherein different search terms in the search terms represent interest points POI of different categories.
The server generates a recommendation card for the user according to current scene information of a scene where the user is located currently, historical data of an electronic map used by the user before and the like, wherein search words on the recommendation card are search words with higher user click probability, and the recommendation cards of different users are different.
Fig. 5A is a schematic view of an electronic map interface in the information recommendation method according to the embodiment of the present application. Referring to fig. 5A, when the user travels to a different place, the historical data shows that the user often searches for food at noon or searches for POIs of food in a large-frame search manner, and then when the user opens the electronic map, the electronic map actively pops up a recommendation card, and the search words on the recommendation card include special snacks, food, fast food, hot pot, stewed pork, etc.
Fig. 5B is another schematic diagram of an electronic map interface in the information recommendation method according to the embodiment of the present application. Referring to fig. 5B, when the user travels to a different place, the historical data shows that the user often searches for POIs of hotels, parking stations, gas stations, and the like, and then when the user opens the electronic map, the electronic map pops up a recommendation card, and the search terms on the recommendation card include star hotels, quick hotels, service areas, gas stations, parking stations, and the like.
In addition, the electronic device generates different recommendation cards for different users, for example, for a user who likes snacks, the search words on the recommendation card include snack snacks, special foods and the like, and for a user who likes western meals, the search words on the recommendation card include western restaurants, coffee shops and the like.
The electronic device generates different recommendation cards for the same user in different scenes, for example, when the user travels to a different place, the search terms on the recommendation cards include hotels, parking lots and the like, and when the user is local, the search terms include food and the like.
404. And outputting the recommendation card.
Illustratively, the server pushes the recommendation card to the terminal device of the user, so that the recommendation card is popped up on an electronic map interface of the terminal device, and the user can select a search term from the recommendation card and click the search term. In this way, the user does not need to click on the "periphery" or the like to perform the search.
405. And opening the electronic map, and not pushing the recommendation card.
An exemplary server only pushes data and the like related to an electronic map interface, and does not push a recommendation card, so that the electronic map is displayed on the terminal device but the recommendation card is not displayed.
According to the information recommendation method provided by the embodiment of the application, after the server receives a request instruction of a user for requesting to open the electronic map, whether the user has the retrieval intention or not is predicted in response to the request instruction. And when the fact that the user has the search intention is predicted, generating a recommendation card for the user and outputting the recommendation card, wherein a plurality of search terms are displayed on the recommendation card for the user to select. By adopting the scheme, when the user is identified to have the search appeal, the recommendation card which accords with the user behavior and the current scene is actively popped up for the user to click the search word on the recommendation card, so that the user can quickly and conveniently find a certain type of interest point, the input operation of the user on the search box is reduced, the user can be prevented from finding the search word through multiple clicks, the interaction efficiency is improved, and the personalized recommendation is realized.
In the above embodiment, when the server responds to the request instruction and predicts whether the user has the retrieval intention, first, current scene information is determined, and the retrieval probability of the user is determined according to the current scene information. And when the retrieval probability is larger than the preset retrieval probability, predicting that the user has the retrieval intention. And when the retrieval probability is less than or equal to the preset retrieval probability, predicting that the user does not have the retrieval intention.
Illustratively, the current scene information includes time, place, gender of the user, whether the user is out of the country, historical operation behaviors of the user, POI semantics, behavior sequence of the user, and the like when the user requests to open the electronic map. The historical operation behaviors of the user comprise a behavior that the user clicks a search word on the electronic map before, a behavior that the user inputs the search word in a search frame of the electronic map and searches, a behavior that the user navigates by using the electronic map, a behavior that the user positions by using the electronic map, and the like. The historical operation behavior of the user can reflect the interest of the user and the like. The historical operation behaviors of the user comprise a behavior that the user clicks a search word on the electronic map before, a behavior that the user inputs the search word in a search frame of the electronic map and searches, a behavior that the user navigates by using the electronic map, a behavior that the user positions by using the electronic map, and the like. The server acquires the current scene information. And then, the server determines the retrieval probability of the user according to the current scene information, and compares the retrieval probability with the preset retrieval probability. For example, if the preset retrieval probability is 70%, the user is considered to have the retrieval intention when the retrieval probability is greater than 70%. When the retrieval probability is less than or equal to 70%, the user is considered not to have the retrieval intention, but to use the electronic map for navigation, positioning, and the like.
By adopting the scheme, the server acquires the current scene information and determines the retrieval probability of the user according to the current scene information, so that the purpose of determining whether the user has the retrieval intention is achieved, and the method is simple in process and high in accuracy. When the fact that the user has the search intention is predicted, the recommendation card is actively bounced, the path of the user for searching the expected search word is shortened, and the efficiency of the user in using the electronic map is improved.
When the server generates a recommendation card for the user when predicting that the user has a search intention, first, current scene information is determined. And then, the server determines the click probability of each search word in a plurality of preset search words clicked by the user according to the current scene information. Then, the server selects at least one search term with a click probability exceeding a preset click probability from the plurality of search terms, and generates the recommendation card according to the at least one search term.
Illustratively, a plurality of search terms are preset on the server, and each search term represents a certain type of POI. The current scene information comprises time, place, user gender, whether the user is out of place, historical operation behaviors of the user, POI semantics and the like when the user requests to open the electronic map. The historical operation behaviors of the user comprise a behavior that the user clicks a search word on the electronic map before, a behavior that the user inputs the search word in a search frame of the electronic map and searches, a behavior that the user navigates by using the electronic map, a behavior that the user positions by using the electronic map, and the like. The historical operation behavior of the user can reflect the interest of the user and the like.
The server acquires the current scene information. And then, the server determines the click probability of each search term in the plurality of search terms clicked by the user according to the current scene information. For example, if there are 100 preset search terms, the server determines the click probability of each of the 100 search terms, and sorts the search terms in the order of the click probability from high to low. Then, the server takes the search term of TOP N as the search term displayed by the recommended card, and generates the recommended card based on the search term of TOP N. Where N is, for example, an integer of 15 or more, and the embodiment of the present application is not limited.
By adopting the scheme, the server acquires the current scene information, determines the click probability of each search word in the plurality of search words according to the current scene information, determines the search words displayed on the recommendation card according to the click probability and generates the recommendation card more fitting the use habit of the user, so that the interaction cost between the user and the electronic map is reduced.
In the above embodiment, the server needs to train a first model for determining the retrieval probability of the user before predicting the retrieval probability of the user. Before the server generates a recommendation card for the user, a second model for calculating the click probability of each search term in the plurality of search terms needs to be trained. In the following, how to train the two models will be described in detail.
First, a first model.
The server constructs a plurality of first training samples according to historical data to obtain a first training sample set, wherein the historical data is data generated when a historical user operates the electronic map. Then, the server trains a first model by using the first training sample set, wherein the first model is used for determining the retrieval probability of the user.
Illustratively, when the server trains out the first model, historical data of historical user usage of the electronic map is obtained, and the historical data comprises historical behaviors and scene information when the historical behaviors occur. The historical behaviors are the operation behaviors of the historical user on the electronic map, and include but are not limited to general retrieval, positioning, navigation, clicking any retrieval word after clicking the periphery, and the like. For example, the behavior of inputting a search word by a user through a large-frame search mode, the behavior of clicking the search word on a search word landing page by a historical user, the behavior of inputting POI positioning, the navigation behavior and the like. The historical scene information includes: time, place, local or foreign of the historical user, gender of the historical user, historical interest POI of the historical user, behavioral sequence of the historical user, etc. when the historical behavior occurs. The scene information also becomes the characteristics of the sample. The behavior sequence of the historical user is obtained by sequencing the behaviors of the historical user in a period of time according to the sequence. For example, if the historical behavior of the historical user is to click on a gourmet and click on a hot pot, a gourmet and a buffet within one week before the gourmet, the behavior sequence is to click on the hot pot, click on the gourmet and click on the buffet.
After the historical data are obtained, the server marks historical behaviors by using historical scene information corresponding to the historical behaviors, and an obtained first sample is a positive sample; and marking historical behaviors by using other historical scene information, wherein the obtained first sample is a negative sample. For example, in the historical data, if the historical user a clicks a food at noon, the clicking food at noon is a positive sample, and the clicking scenic spot at noon is a negative sample.
In the above model training process, if only one-sided factors are considered, for example, if a user clicks to find a behavior such as a periphery, the habit of the user cannot be reflected. At the same time, the trained model is constrained. For example, the search terms in the search term landing page are all fixed and only contain scenic spots, gourmets and hotels, if only the user clicks and finds the surrounding behaviors, the model is trained, and the first model or the second model below cannot reflect the interest of the user in the stewing and burning process. In the embodiment of the application, the server utilizes various operation behaviors of the historical user on the electronic map to construct the training sample set, the training samples in the training sample set are influenced comprehensively and singly by an entrance, and therefore more scenes can be adapted to the trained first model and second model.
After the server constructs the first sample set, a Deep learning model, such as a Convolutional Neural Network (CNN) model and a Deep Neural network (Deep Neural network, DNN) model, is trained to obtain a first model, and the first model is used for predicting the retrieval probability of the current user.
After the server trains the first model, when the first model is used online, the current scene information of the current user is input into the first model, and the retrieval probability of the user can be automatically and accurately obtained.
Fig. 6 is a schematic process diagram of training and applying a first model in the information recommendation method provided in the embodiment of the present application. Referring to fig. 6, the history data includes a scene log and a behavior log. In the process of learning the model offline, the server determines a plurality of historical behaviors from user logs contained in the historical data, and different historical behaviors in the plurality of historical behaviors are used for indicating different operations of the user on the electronic map. And meanwhile, the server determines scene information of each historical behavior in the plurality of historical behaviors from a scene log contained in the historical data.
And after acquiring the historical behaviors and the scene information of each historical behavior, the server analyzes and fuses logs. In the fusion process, the server marks corresponding behavior samples by using the scene information of each historical behavior in the plurality of historical behaviors to obtain a first training sample in the training sample set. Then, the server trains the deep learning model by using the first sample in the first sample set, thereby obtaining a first model.
In the process of using the first model online, the server acquires current scene information and inputs the current scene information into the first model, so that the retrieval probability of the current user can be obtained. The first model calculates the retrieval probability under the triggering of user behaviors, if a user clicks the electronic map to request to open the electronic map, the server carries out online streaming analysis on current scene information to obtain features, the analyzed features are input into the first model, and the retrieval probability is calculated based on the features. Assuming that there are 10 features when the first model is trained, and when the first model is used, the current scene information includes 7 features, the server sets the remaining 3 features to 0, and determines the retrieval probability based on the 7 features. The more features the current scene information contains, the more accurate the predicted retrieval probability.
By adopting the scheme, the electronic equipment constructs a first training sample set based on historical data and carries out model training, trains a first model, and can accurately predict whether a user has a retrieval intention based on the first model.
Second, a second model.
When the user is predicted to have the retrieval intention, the server determines current scene information. And then, the server determines the click probability of each search word in a plurality of preset search words clicked by the user according to the current scene information. Then, the server selects at least one search term with a click probability exceeding a preset click probability from the plurality of search terms, and generates the recommendation card according to the at least one search term.
For example, when the server trains the second model, the server obtains historical data of the electronic map used by the historical user, where the historical data may refer to the related description in the process of training the first model, and is not described herein again. After the historical data is obtained, the server marks the search word by using the historical scene information corresponding to the search word, and the obtained second sample is a positive sample; and marking the search term by using other historical scene information, wherein the obtained second sample is a negative sample. For example, if the historical user A clicked a food at noon, then noon-food is a positive sample and noon-sight is a negative sample.
After a second sample set is constructed by the server, training a Learning To Ranking (LTR) model to obtain a second model, wherein the second model is used for determining the probability of each search term being clicked in a certain scene.
After the server trains the second model, when the second model is used online, current scene information of the current user is input into the second model, and then the click probability of each search term can be obtained. And then, sequencing the click probabilities, and generating a recommendation card by using the search terms of the ranking top N.
By adopting the scheme, the server determines the click probability of each search term through the second model, and the method has the advantages of high automation degree and high accuracy.
Fig. 7 is a schematic process diagram of training and applying a second model in the information recommendation method provided in the embodiment of the present application. Referring to fig. 7, the history data includes a scene log and a behavior log. In the process of off-line learning the model, the server determines a search term set from a user log contained in the historical data, wherein different search terms in the search term set are generated by different operations of the user on the electronic map. And meanwhile, the server determines scene information of each search term in the plurality of search terms from a scene log contained in the historical data.
And after acquiring the search terms and the scene information of each search term, the server analyzes and fuses logs. In the fusion process, the server labels the corresponding search terms by using the scene information of a plurality of search terms to obtain a positive sample; and labeling the search terms by using the scene information which does not correspond to the search terms to obtain negative samples, wherein the positive samples and the negative samples form a second sample set.
In the process of using the second model online, the server acquires current scene information and inputs the current scene information into the second model, so that the click probability of each search term can be obtained. And the second model calculates the click probability of each search term under the trigger of the user behavior, if the user clicks the electronic map to request to open the electronic map, the server carries out online streaming analysis on the current scene information to obtain characteristics, inputs the analyzed characteristics to the second model, and calculates the click probability of each search term based on the characteristics.
In addition, after the second model is online, in the using process of the electronic map by the user, the server continues to generate a scene log and a behavior log according to the operation behavior of the user, and continues to learn the LTR model for a long time, so that the LTR model is updated.
By adopting the scheme, the electronic equipment constructs a second training sample set based on historical data and carries out model training to train a second model, and a recommendation card fitting with the current scene of the user can be generated based on the second model, so that the interactive operation of the user and the electronic map is reduced.
In the above embodiment, after the server outputs the recommendation card, the recommendation card is pushed to the terminal device, so that the terminal device pops up the recommendation card on the electronic map. And after the user clicks any search word on the recommendation card, triggering the terminal equipment to send a search instruction. And after receiving the retrieval instruction, the server determines a plurality of POIs related to the retrieval word according to the retrieval word and outputs the POIs. And the terminal equipment displays the POIs on the electronic map and displays information such as scores of the POIs.
By adopting the scheme, after the server receives the recommendation instruction of the user, the POI expected by the user is determined according to the search word carried by the recommendation instruction and is pushed to the terminal equipment, so that the interaction times of the user and the electronic map are reduced.
Fig. 8 is a flowchart of a model training method provided in an embodiment of the present application, where an execution subject of the embodiment is an electronic device such as a server, and the embodiment includes:
801. and constructing a training sample according to historical data to obtain a training sample set, wherein the historical data is data generated when a historical user operates the electronic map.
802. Training an initial model by using the training sample to obtain a target model, wherein the target model is a model associated with a recommendation card, a plurality of search terms are displayed on the recommendation card, and different search terms in the search terms represent POI (points of interest) of different categories.
Illustratively, the target model is, for example, the first model described above, and the initial model is a deep learning model. Alternatively, the target model is the second model described above and the initial model is the ranking model.
According to the model training method provided by the embodiment, the electronic equipment constructs a training sample by using historical data, performs model training to obtain a target model, and predicts the retrieval probability of a user and the probability of each retrieval word being clicked by using the target model, so that the purpose of accurately identifying whether the user has retrieval complaints and the click probability of each retrieval word is achieved.
In a feasible design, when the initial model is a deep learning model and the target model is a first model, the electronic device constructs training samples according to historical data to obtain a training sample set, and constructs a plurality of first training samples according to the historical data to obtain a first training sample set. Then, the electronic device trains the deep learning model by using the first training sample set to obtain the first model, and the first model is used for determining the retrieval probability of the user.
In a feasible design, when the electronic device constructs a plurality of first training samples according to historical data to obtain a first training sample set, firstly, a plurality of historical behaviors are determined from a user log contained in the historical data, and different historical behaviors in the plurality of historical behaviors are used for indicating different operations of historical users on the electronic map. Then, the electronic device determines scene information of each historical behavior in the plurality of historical behaviors from a scene log contained in the historical data, and labels a corresponding behavior sample by using the scene information of each historical behavior in the plurality of historical behaviors to obtain a first training sample in the training sample set.
In the above embodiment, when the initial model is the ranking model and the target model is the second model, the electronic device constructs the training samples according to the historical data to obtain the training sample set, and constructs the second training samples according to the historical data to obtain the second training sample set. Then, the electronic device trains the ranking model by using the second training sample set to obtain a second model, wherein the second model is used for determining the click probability of each search term in the plurality of search terms.
In a feasible design, when the electronic device constructs a second training sample according to the historical data to obtain a second training sample set, firstly, a search term set is determined from a user log contained in the historical data, and different search terms in the search term set are generated by different operations of the historical user on the electronic map. Then, the electronic device determines scene information of each search term in the plurality of search terms from a scene log included in the historical data, and labels the corresponding search term by using the scene information of each search term in the plurality of search terms to obtain a second training sample in the second training sample set.
In the above embodiment, the operation of the historical user on the electronic map includes at least one of the following operations: and performing general retrieval, positioning, navigation and clicking any retrieval word after clicking the periphery.
In the above, a specific implementation of the information recommendation method mentioned in the embodiments of the present application is introduced, and the following is an embodiment of the apparatus of the present application, which can be used to implement the embodiments of the method of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the embodiments of the method of the present application.
Fig. 9 is a schematic structural diagram of an information recommendation device based on an electronic map according to an embodiment of the present application. The apparatus may be integrated in or implemented by an electronic device. As shown in fig. 9, in the present embodiment, the electronic map-based information recommendation apparatus 900 may include:
a receiving module 91, configured to receive a request instruction of a user, where the request instruction is used to request to open an electronic map;
a prediction module 92, configured to predict whether the user has a retrieval intention in response to the request instruction;
a processing module 93, configured to generate a recommendation card for the user when the prediction module 92 predicts that the user has a search intention, where a plurality of search terms are displayed on the recommendation card, and different search terms in the plurality of search terms represent different categories of POI;
and the output module 94 is used for outputting the recommendation card.
In a possible design, the prediction module 92 is specifically configured to determine current scene information in response to the request instruction, determine a retrieval probability of the user according to the current scene information, and predict that the user has a retrieval intention when the retrieval probability is greater than a preset retrieval probability.
In a feasible design, when determining the retrieval probability of the user according to the current scene information, the prediction module 92 is configured to construct a plurality of first training samples according to historical data to obtain a first training sample set, where the historical data is data generated when a historical user operates the electronic map; training a first model by using the first training sample set, wherein the first model is used for determining the retrieval probability of the user; and inputting the current scene information into the first model to obtain the retrieval probability of the user.
In a possible design, the prediction module 92 constructs a plurality of first training samples according to historical data, and determines a plurality of historical behaviors from user logs included in the historical data when obtaining a first training sample set, where different historical behaviors in the plurality of historical behaviors are used for indicating different operations of historical users on the electronic map; determining scene information of each historical behavior in the plurality of historical behaviors from a scene log contained in the historical data; and marking corresponding behavior samples by using the scene information of each historical behavior in the plurality of historical behaviors to obtain a first training sample in the training sample set.
In a possible design, the processing module 93 is configured to determine current scene information when the prediction module 92 predicts that the user has a search intention, and determine, according to the current scene information, a click probability of each search term in a plurality of preset search terms being clicked by the user; selecting at least one search term with a click probability exceeding a preset click probability from the plurality of search terms; and generating the recommendation card according to the at least one search term.
In a feasible design, when the processing module 93 determines the click probability of each of a plurality of preset search terms clicked by a user according to the current scene information, a second training sample is constructed according to historical data to obtain a second training sample set, wherein the historical data is data generated when the historical user operates the electronic map; training a second model by using the second training sample set, wherein the second model is used for determining the click probability of each search term in the plurality of search terms; and inputting the current scene information into the second model to obtain the click probability of each search term in the plurality of search terms.
In a feasible design, the processing module 93 constructs a second training sample according to the historical data, and when obtaining a second training sample set, is configured to determine a search term set from a user log included in the historical data, where different search terms in the search term set are generated by different operations of a historical user on an electronic map; determining scene information of each search term in the plurality of search terms from a scene log contained in the historical data; and labeling the corresponding search term by using the scene information of each search term in the plurality of search terms to obtain a second training sample in the second training sample set.
In one possible design, the operation of the electronic map by the historical user includes at least one of the following operations: and performing general retrieval, positioning, navigation and clicking any retrieval word after clicking the periphery.
In a possible design, after the output module 94 outputs the recommendation card, the receiving module 91 is further configured to receive a search instruction of the user, where the search instruction carries any search term on the recommendation card; the processing module 93 is further configured to determine, according to the search term, a plurality of POIs related to the search term; the output module 94 is further configured to output the multiple POIs.
Fig. 10 is a schematic structural diagram of a model training apparatus according to an embodiment of the present application. The apparatus may be integrated in or implemented by an electronic device. As shown in fig. 10, in this embodiment, the model training apparatus 1000 may include:
the building module 1001 is configured to build a training sample according to historical data to obtain a training sample set, where the historical data is data generated when a historical user operates an electronic map;
the training module 1002 is configured to train an initial model by using the training sample to obtain a target model, where the target model is a model associated with a recommendation card, and multiple search terms are displayed on the recommendation card, and different search terms in the multiple search terms represent different types of POI.
In a feasible design, when the initial model is a deep learning model and the target model is a first model, the constructing module 1001 is configured to construct a plurality of first training samples according to historical data to obtain a first training sample set;
the training module 1002 is configured to train the deep learning model to obtain the first model, where the first model is used to determine the retrieval probability of the user, by using the first training sample set.
In a possible design, the building module 1001 is configured to determine context information of each historical behavior in the plurality of historical behaviors from a context log included in the historical data; and marking corresponding behavior samples by using the scene information of each historical behavior in the plurality of historical behaviors to obtain a first training sample in the training sample set.
In a feasible design, when the initial model is a ranking model and the target model is a second model, the constructing module 1001 is configured to construct a second training sample according to historical data to obtain a second training sample set, and train the ranking model by using the second training sample set to obtain the second model, where the second model is used to determine the click probability of each term in the plurality of terms.
In a possible design, the training module 1002 is configured to determine a search term set from a user log included in the historical data, where different search terms in the search term set are generated by different operations of a historical user on an electronic map, determine scene information of each search term in the plurality of search terms from a scene log included in the historical data, and label the corresponding search term with the scene information of each search term in the plurality of search terms to obtain a second training sample in the second training sample set.
Fig. 11 is a block diagram of an electronic device for implementing an information recommendation method according to an embodiment of the present application. The electronic device can also execute the model training method provided by the embodiment of the application. The following describes the electronic device provided in the embodiments of the present application in detail, taking an example of a method for the electronic device to execute information recommendation. 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 disclosure described and/or claimed herein.
As shown in fig. 11, the electronic device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)1102 or a computer program loaded from a storage unit 1108 into a Random Access Memory (RAM) 1103. In the RAM 1103, various programs and data necessary for the operation of the device 1100 may also be stored. The calculation unit 1101, the ROM 1102, and the RAM 1103 are connected to each other by a bus 1104. An input/output (I/O) interface 1105 is also connected to bus 1104.
A number of components in device 1100 connect to I/O interface 1105, including: an input unit 1106 such as a keyboard, a mouse, and the like; an output unit 1107 such as various types of displays, speakers, and the like; a storage unit 1108 such as a magnetic disk, optical disk, or the like; and a communication unit 1109 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 1109 allows the device 1100 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The computing unit 1101 can be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 1101 performs the respective methods and processes described above, such as the information recommendation method. For example, in some embodiments, the information recommendation method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1100 via ROM 1102 and/or communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the information recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform the information recommendation method in any other suitable manner (e.g., by means of firmware).
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 disclosure 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 disclosure, 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, speech, 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. The Server may be a cloud Server, which is also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of large management difficulty, weak service extensibility and the like in a conventional physical host and a Virtual Private Server (VPS). The server can also be a server of a distributed system or a server combined with a block chain
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, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
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 (31)
1. An information recommendation method, comprising:
receiving a request instruction of a user, wherein the request instruction is used for requesting to open an electronic map;
predicting whether the user has a retrieval intention in response to the request instruction;
generating a recommendation card for the user when the user is predicted to have a retrieval intention, wherein a plurality of retrieval words are displayed on the recommendation card, and different retrieval words in the plurality of retrieval words represent POI (points of interest) of different categories;
and outputting the recommendation card.
2. The method of claim 1, wherein said predicting whether the user has a retrieval intent in response to the request instruction comprises:
determining current scene information in response to the request instruction,
determining the retrieval probability of the user according to the current scene information;
and when the retrieval probability is larger than the preset retrieval probability, predicting that the user has the retrieval intention.
3. The method of claim 2, wherein said determining a retrieval probability of the user based on the current context information comprises:
a plurality of first training samples are constructed according to historical data to obtain a first training sample set, wherein the historical data is data generated when a historical user operates the electronic map;
training a first model by using the first training sample set, wherein the first model is used for determining the retrieval probability of the user;
and inputting the current scene information into the first model to obtain the retrieval probability of the user.
4. The method of claim 3, wherein the constructing a plurality of first training samples from historical data resulting in a first set of training samples comprises:
determining a plurality of historical behaviors from user logs contained in the historical data, wherein different historical behaviors in the plurality of historical behaviors are used for indicating different operations of historical users on the electronic map;
determining scene information of each historical behavior in the plurality of historical behaviors from a scene log contained in the historical data;
and marking corresponding behavior samples by using the scene information of each historical behavior in the plurality of historical behaviors to obtain a first training sample in the training sample set.
5. The method of any of claims 1-4, wherein the generating a recommendation card for the user when the user is predicted to have a retrieval intent comprises:
when the user is predicted to have the retrieval intention, determining current scene information;
determining the click probability of each search word in a plurality of preset search words clicked by a user according to the current scene information;
selecting at least one search term with a click probability exceeding a preset click probability from the plurality of search terms;
and generating the recommendation card according to the at least one search term.
6. The method of claim 5, wherein the determining, according to the current scene information, a click probability of each of a plurality of preset search terms clicked by a user comprises:
constructing a second training sample according to historical data to obtain a second training sample set, wherein the historical data is data generated when a historical user operates the electronic map;
training a second model by using the second training sample set, wherein the second model is used for determining the click probability of each search term in the plurality of search terms;
and inputting the current scene information into the second model to obtain the click probability of each search term in the plurality of search terms.
7. The method of claim 6, wherein the constructing a second training sample from the historical data resulting in a second set of training samples comprises:
determining a search term set from a user log contained in the historical data, wherein different search terms in the search term set are generated by different operations of the historical user on the electronic map;
determining scene information of each search term in the plurality of search terms from a scene log contained in the historical data;
and labeling the corresponding search term by using the scene information of each search term in the plurality of search terms to obtain a second training sample in the second training sample set.
8. The method of claim 4 or 7, wherein the operation of the electronic map by the historical user comprises at least one of: and performing general retrieval, positioning, navigation and clicking any retrieval word after clicking the periphery.
9. The method of any of claims 1-4, wherein after outputting the recommendation card, further comprising:
receiving a retrieval instruction of the user, wherein the retrieval instruction carries any retrieval word on the recommendation card;
determining a plurality of POIs related to the search term according to the search term;
outputting the plurality of POIs.
10. A model training method, comprising:
constructing a training sample according to historical data to obtain a training sample set, wherein the historical data is data generated when a historical user operates an electronic map;
training an initial model by using the training sample to obtain a target model, wherein the target model is a model associated with a recommendation card, a plurality of search terms are displayed on the recommendation card, and different search terms in the search terms represent POI (points of interest) of different categories.
11. The method according to claim 10, wherein when the initial model is a deep learning model and the target model is a first model, the constructing training samples according to the historical data to obtain a training sample set includes:
constructing a plurality of first training samples according to historical data to obtain a first training sample set;
training the deep learning model by using the first training sample set to obtain the first model, wherein the first model is used for determining the retrieval probability of the user.
12. The method of claim 11, wherein the constructing a plurality of first training samples from historical data resulting in a first set of training samples comprises:
determining a plurality of historical behaviors from user logs contained in the historical data, wherein different historical behaviors in the plurality of historical behaviors are used for indicating different operations of historical users on the electronic map;
determining scene information of each historical behavior in the plurality of historical behaviors from a scene log contained in the historical data;
and marking corresponding behavior samples by using the scene information of each historical behavior in the plurality of historical behaviors to obtain a first training sample in the training sample set.
13. The method of claim 10, wherein when the initial model is a ranking model and the target model is a second model, the constructing training samples according to the historical data to obtain a training sample set comprises:
constructing a second training sample according to the historical data to obtain a second training sample set;
and training the ranking model by using the second training sample set to obtain a second model, wherein the second model is used for determining the click probability of each search term in the plurality of search terms.
14. The method of claim 13, wherein the constructing a second training sample from the historical data resulting in a second set of training samples comprises:
determining a search term set from a user log contained in the historical data, wherein different search terms in the search term set are generated by different operations of the historical user on the electronic map;
determining scene information of each search term in the plurality of search terms from a scene log contained in the historical data;
and labeling the corresponding search term by using the scene information of each search term in the plurality of search terms to obtain a second training sample in the second training sample set.
15. An electronic map-based information recommendation apparatus comprising:
the receiving module is used for receiving a request instruction of a user, and the request instruction is used for requesting to open the electronic map;
the prediction module is used for responding to the request instruction and predicting whether the user has the retrieval intention;
the processing module is used for generating a recommendation card for the user when the prediction module predicts that the user has a search intention, wherein a plurality of search terms are displayed on the recommendation card, and different search terms in the search terms represent POI (points of interest) of different categories;
and the output module is used for outputting the recommendation card.
16. The apparatus according to claim 15, wherein the prediction module is specifically configured to determine current context information in response to the request instruction, determine a retrieval probability of the user according to the current context information, and predict that the user has a retrieval intention when the retrieval probability is greater than a preset retrieval probability.
17. The device of claim 16, wherein the prediction module is configured to, when determining the retrieval probability of the user according to the current scenario information, construct a plurality of first training samples according to historical data to obtain a first training sample set, where the historical data is data generated when a historical user operates the electronic map; training a first model by using the first training sample set, wherein the first model is used for determining the retrieval probability of the user; and inputting the current scene information into the first model to obtain the retrieval probability of the user.
18. The apparatus of claim 17, wherein the prediction module constructs a plurality of first training samples according to historical data, and determines a plurality of historical behaviors from a user log included in the historical data when the first training sample set is obtained, and different historical behaviors in the plurality of historical behaviors are used for indicating different operations of historical users on the electronic map; determining scene information of each historical behavior in the plurality of historical behaviors from a scene log contained in the historical data; and marking corresponding behavior samples by using the scene information of each historical behavior in the plurality of historical behaviors to obtain a first training sample in the training sample set.
19. The apparatus according to any one of claims 15 to 18, wherein the processing module is configured to determine current scene information when the prediction module predicts that the user has a search intention, and determine, according to the current scene information, a click probability of each of a plurality of search terms being clicked by the user; selecting at least one search term with a click probability exceeding a preset click probability from the plurality of search terms; and generating the recommendation card according to the at least one search term.
20. The device of claim 19, wherein when determining the click probability of each of the preset multiple search terms clicked by the user according to the current scene information, the processing module constructs a second training sample according to historical data to obtain a second training sample set, wherein the historical data is data generated when the historical user operates the electronic map; training a second model by using the second training sample set, wherein the second model is used for determining the click probability of each search term in the plurality of search terms; and inputting the current scene information into the second model to obtain the click probability of each search term in the plurality of search terms.
21. The apparatus according to claim 20, wherein the processing module constructs a second training sample according to the historical data, and when obtaining a second training sample set, the processing module is configured to determine a search term set from a user log included in the historical data, where different search terms in the search term set are generated by different operations of the historical user on the electronic map; determining scene information of each search term in the plurality of search terms from a scene log contained in the historical data; and labeling the corresponding search term by using the scene information of each search term in the plurality of search terms to obtain a second training sample in the second training sample set.
22. The apparatus of claim 18 or 21, wherein the operation of the electronic map by the historical user comprises at least one of: and performing general retrieval, positioning, navigation and clicking any retrieval word after clicking the periphery.
23. The apparatus of any one of claims 15-18,
the receiving module is used for receiving a retrieval instruction of the user after the output module outputs the recommendation card, wherein the retrieval instruction carries any retrieval word on the recommendation card;
the processing module is further used for determining a plurality of POIs related to the search term according to the search term;
the output module is further configured to output the multiple POIs.
24. A model training apparatus comprising:
the construction module is used for constructing a training sample according to historical data to obtain a training sample set, wherein the historical data is data generated when a historical user operates the electronic map;
the training module is used for training an initial model by using the training sample to obtain a target model, the target model is a model associated with a recommendation card, a plurality of search terms are displayed on the recommendation card, and different search terms in the search terms represent interest points POI of different categories.
25. The apparatus according to claim 24, wherein when the initial model is a deep learning model and the target model is a first model, the constructing module is configured to construct a plurality of first training samples according to historical data to obtain a first training sample set;
the training module is configured to train the deep learning model to obtain the first model by using the first training sample set, where the first model is used to determine the retrieval probability of the user.
26. The apparatus of claim 25, wherein the constructing module is configured to determine context information of each historical behavior of the plurality of historical behaviors from a context log included in the historical data; and marking corresponding behavior samples by using the scene information of each historical behavior in the plurality of historical behaviors to obtain a first training sample in the training sample set.
27. The apparatus of claim 24, wherein when the initial model is a ranking model and the target model is a second model, the constructing module is configured to construct a second training sample according to historical data to obtain a second training sample set, and train the ranking model to obtain the second model using the second training sample set, and the second model is configured to determine a click probability of each term in the plurality of terms.
28. The apparatus of claim 27, wherein the training module is configured to determine a set of search terms from a user log included in the historical data, different search terms in the set of search terms are generated by different operations of the historical user on the electronic map, determine scene information of each search term in the plurality of search terms from a scene log included in the historical data, and label a corresponding search term using the scene information of each search term in the plurality of search terms to obtain the second training sample in the second training sample set.
29. 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 1-14.
30. A non-transitory computer readable storage medium having stored thereon computer instructions for causing an electronic device to perform the method of any of claims 1-14.
31. A computer program product which, when run on an electronic device, causes the electronic device to perform the method of any one of claims 1-14.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011445091.1A CN112528145B (en) | 2020-12-11 | 2020-12-11 | Information recommendation method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011445091.1A CN112528145B (en) | 2020-12-11 | 2020-12-11 | Information recommendation method, device, equipment and readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112528145A true CN112528145A (en) | 2021-03-19 |
CN112528145B CN112528145B (en) | 2023-09-05 |
Family
ID=75000273
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011445091.1A Active CN112528145B (en) | 2020-12-11 | 2020-12-11 | Information recommendation method, device, equipment and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112528145B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103631954A (en) * | 2013-12-13 | 2014-03-12 | 百度在线网络技术(北京)有限公司 | Individualized recommendation method and device |
CN103914536A (en) * | 2014-03-31 | 2014-07-09 | 北京百度网讯科技有限公司 | Interest point recommending method and system for electronic maps |
CN104050176A (en) * | 2013-03-13 | 2014-09-17 | 电子科技大学 | Map-based information recommendation method |
CN104615620A (en) * | 2014-06-24 | 2015-05-13 | 腾讯科技(深圳)有限公司 | Map search type identification method and device and map search method and system |
US20160055177A1 (en) * | 2013-03-18 | 2016-02-25 | Baidu Online Network Technology (Beijing) Co., Ltd | Search recommendation method and apparatus for map search, computer storage medium, and device |
CN106202103A (en) * | 2015-05-06 | 2016-12-07 | 阿里巴巴集团控股有限公司 | Music recommends method and apparatus |
CN108197211A (en) * | 2017-12-28 | 2018-06-22 | 百度在线网络技术(北京)有限公司 | A kind of information recommendation method, device, server and storage medium |
US10652619B1 (en) * | 2019-03-26 | 2020-05-12 | Rovi Guides, Inc. | Systems and methods for providing media asset recommendations |
CN111475730A (en) * | 2020-04-09 | 2020-07-31 | 腾讯科技(北京)有限公司 | Information recommendation method and device based on artificial intelligence and electronic equipment |
CN112000700A (en) * | 2020-07-14 | 2020-11-27 | 北京百度网讯科技有限公司 | Map information display method and device, electronic equipment and storage medium |
-
2020
- 2020-12-11 CN CN202011445091.1A patent/CN112528145B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104050176A (en) * | 2013-03-13 | 2014-09-17 | 电子科技大学 | Map-based information recommendation method |
US20160055177A1 (en) * | 2013-03-18 | 2016-02-25 | Baidu Online Network Technology (Beijing) Co., Ltd | Search recommendation method and apparatus for map search, computer storage medium, and device |
CN103631954A (en) * | 2013-12-13 | 2014-03-12 | 百度在线网络技术(北京)有限公司 | Individualized recommendation method and device |
CN103914536A (en) * | 2014-03-31 | 2014-07-09 | 北京百度网讯科技有限公司 | Interest point recommending method and system for electronic maps |
CN104615620A (en) * | 2014-06-24 | 2015-05-13 | 腾讯科技(深圳)有限公司 | Map search type identification method and device and map search method and system |
CN106202103A (en) * | 2015-05-06 | 2016-12-07 | 阿里巴巴集团控股有限公司 | Music recommends method and apparatus |
CN108197211A (en) * | 2017-12-28 | 2018-06-22 | 百度在线网络技术(北京)有限公司 | A kind of information recommendation method, device, server and storage medium |
US10652619B1 (en) * | 2019-03-26 | 2020-05-12 | Rovi Guides, Inc. | Systems and methods for providing media asset recommendations |
CN111475730A (en) * | 2020-04-09 | 2020-07-31 | 腾讯科技(北京)有限公司 | Information recommendation method and device based on artificial intelligence and electronic equipment |
CN112000700A (en) * | 2020-07-14 | 2020-11-27 | 北京百度网讯科技有限公司 | Map information display method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
胡旷达;代飞;: "一种基于神经网络模型的多检索词用户兴趣模型", 九江职业技术学院学报, no. 01 * |
韩欣欣;: "基于位置社交网络的POI推荐影响因素分析与研究", 电脑知识与技术, no. 24 * |
Also Published As
Publication number | Publication date |
---|---|
CN112528145B (en) | 2023-09-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11397772B2 (en) | Information search method, apparatus, and system | |
CN112612957B (en) | Recommendation method of interest points and training method and device of recommendation model of interest points | |
CN104102719B (en) | The method for pushing and device of a kind of trace information | |
US10049099B2 (en) | Spell correction with hidden markov models on online social networks | |
US20160299882A1 (en) | Contextual speller models on online social networks | |
CN108268573B (en) | Method and device for pushing information | |
US11468136B2 (en) | Item inventory locating from search queries | |
WO2013102262A1 (en) | Goal-oriented user matching among social networking environments | |
CN110619076A (en) | Search term recommendation method and device, computer and storage medium | |
CN110750697B (en) | Merchant classification method, device, equipment and storage medium | |
CN112559879B (en) | Interest model training method, interest point recommending method, device and equipment | |
CN113536152B (en) | Map interest point display method and device and electronic equipment | |
CN113836435A (en) | Information recommendation method, device, equipment and computer readable storage medium | |
CA2898766A1 (en) | Contextual socially aware local search | |
CN112632379A (en) | Route recommendation method and device, electronic equipment and storage medium | |
CN111754278A (en) | Article recommendation method and device, computer storage medium and electronic equipment | |
KR20210141393A (en) | Geographic position point ranking method, ranking model training method and corresponding device | |
CN113656698A (en) | Training method and device of interest feature extraction model and electronic equipment | |
Alsudais | Quantifying the offline interactions between hosts and guests of Airbnb | |
CN113077312A (en) | Hotel recommendation method, system, equipment and storage medium | |
CN112541123A (en) | Map region recommendation method, device, equipment and storage medium | |
CN112528145B (en) | Information recommendation method, device, equipment and readable storage medium | |
CN114491232B (en) | Information query method and device, electronic equipment and storage medium | |
CN113449754B (en) | Label matching model training and displaying method, device, equipment and medium | |
CN112559876A (en) | Method, device and equipment for displaying map search result 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 |