WO2021077340A1 - 词条推送方法、装置、电子设备及存储介质 - Google Patents

词条推送方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2021077340A1
WO2021077340A1 PCT/CN2019/112845 CN2019112845W WO2021077340A1 WO 2021077340 A1 WO2021077340 A1 WO 2021077340A1 CN 2019112845 W CN2019112845 W CN 2019112845W WO 2021077340 A1 WO2021077340 A1 WO 2021077340A1
Authority
WO
WIPO (PCT)
Prior art keywords
mobile terminal
geographic location
location
list
scenario
Prior art date
Application number
PCT/CN2019/112845
Other languages
English (en)
French (fr)
Inventor
林进全
Original Assignee
深圳市欢太科技有限公司
Oppo广东移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市欢太科技有限公司, Oppo广东移动通信有限公司 filed Critical 深圳市欢太科技有限公司
Priority to CN201980099225.8A priority Critical patent/CN114223011A/zh
Priority to PCT/CN2019/112845 priority patent/WO2021077340A1/zh
Publication of WO2021077340A1 publication Critical patent/WO2021077340A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising

Definitions

  • This application relates to the field of data push technology, and more specifically, to an entry push method, device, electronic equipment, and storage medium.
  • the application can also display recommended terms to the user for the user to select and search for related content of the recommended terms.
  • the recommended terms usually displayed in the application program are not strongly related to the user itself, and are useless information for the user.
  • this application proposes an entry push method, device, electronic equipment and storage medium to improve the above-mentioned problems.
  • an embodiment of the present application provides an entry push method, the method includes: according to the user portrait of the mobile terminal to be pushed, an entry related to the user portrait is selected from the basic push dictionary to establish a first A vocabulary; if the current geographic location of the mobile terminal is a resident location, determine the usage scenario corresponding to the current geographic location as the recommended scenario; select the recommended scenario related from the first vocabulary The entries of are pushed to the mobile terminal.
  • an embodiment of the present application provides an entry push device, the device includes: a thesaurus establishment module, which is used to select the user from the basic push dictionary according to the user portrait of the mobile terminal to be pushed.
  • the first vocabulary is established for portrait-related entries;
  • the scenario determination module is used to determine the use scenario corresponding to the current geographic location if the current geographic location of the mobile terminal is the resident location, as a recommended scenario;
  • the module is used to select the terms related to the recommended scene from the first dictionary and push them to the mobile terminal.
  • an embodiment of the present application provides an electronic device, including: one or more processors; a memory; and one or more programs.
  • the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the above method.
  • an embodiment of the present application provides a computer-readable storage medium having program code stored in the computer-readable storage medium, and the program code can be invoked by a processor to execute the above-mentioned method.
  • the term push method, device, electronic device, and storage medium provided by the embodiments of the present application select relevant terms from the basic push word database according to the user portrait to establish the first word database. Moreover, when the mobile terminal is at the resident location, the current recommended scene is determined according to the current geographic location of the mobile terminal. Select the terms related to the recommended scenario from the first lexicon and push it to the mobile terminal. Therefore, the entries pushed to the mobile terminal not only combine the user portrait, but also the geographic location of the mobile terminal, which improves the relevance of the pushed entries to the user who uses the mobile terminal.
  • Fig. 1 shows a flowchart of a method for pushing entries provided by an embodiment of the present application.
  • Fig. 2 shows a flowchart of a method for pushing an entry provided by another embodiment of the present application.
  • Fig. 3 shows a flowchart of a method for pushing an entry provided by another embodiment of the present application.
  • Fig. 4 shows a functional module diagram of a term push device provided by an embodiment of the present application.
  • Fig. 5 shows a structural block diagram of an electronic device provided by an embodiment of the present application.
  • Fig. 6 is a storage unit for storing or carrying program codes for implementing the term pushing method according to the embodiment of the present application.
  • the application in the mobile terminal can push entries to the user in various ways. For example, when the user opens the search interface of the application, the pushed entry is displayed in the search interface. Or when the user enters a keyword through the search box to search, the pushed term is displayed under the search box corresponding to the entered keyword. Or when the notification permission is enabled in the application, the pushed entry is displayed in the notification bar of the mobile terminal.
  • the terms pushed by the application may only be popular content on the platform where the application is located, such as hot searches on Weibo; in other implementations, when the term is pushed in the search box, the pushed terms
  • the entry may only be related to the keywords entered by the user, for example, the content of the entry itself includes the keywords entered by the user. In these push methods, none of them paid attention to the needs of the users themselves in the current environment, and the pushed entries were not closely related to the users themselves and could not arouse user interest.
  • the inventor proposes the term push method, device, electronic device, and storage medium provided by the embodiments of the present application, which are used by the server to push terms to the mobile terminal according to the user portrait and the geographic location of the mobile terminal.
  • the server can push the entry to the application program served by the server in the mobile terminal.
  • specific embodiments will be used to describe in detail the term push method, device, electronic equipment, and storage medium provided in the embodiments of the present application.
  • FIG. 1 shows a method for pushing an entry provided by an embodiment of the present application. Specifically, the method includes:
  • Step S110 According to the user portrait of the mobile terminal to be pushed, terms related to the user portrait are selected from the basic push word database to establish a first word database.
  • the server may push the entry to the mobile terminal connected in communication, and the mobile terminal that needs to push the entry is the mobile terminal to be pushed.
  • the embodiment of the present application takes one mobile terminal as the mobile terminal to be pushed as an example for description.
  • a user portrait can be created for different mobile terminals.
  • the user portrait is an abstract representation of the mobile terminal user and is the user’s
  • Virtual representatives can include various information such as the user's identity and interest preferences.
  • the user portrait of a mobile terminal can abstract the specific information of the user of the mobile terminal into tags, so that these tags can be used to concretize the user's image, determine the user's focus more accurately, and provide the user with targeted services. .
  • the basic push dictionary includes various types of terms, and the terms pushed to different mobile terminals can be selected from the basic push dictionary.
  • some entries may be entries that are of interest to users of the mobile terminal to be pushed, and some entries may be entries that are not of interest to users of the mobile terminal to be pushed. Therefore, it is possible to select terms related to the user portrait from the basic push word database to establish the word database, and define the word database as the first word database.
  • the first vocabulary as the vocabulary of the mobile terminal to be pushed, conforms to the point of interest of the user of the mobile terminal to be pushed to a certain extent.
  • Step S120 If the current geographic location of the mobile terminal is the resident location, determine the usage scenario corresponding to the current geographic location as the recommended scenario.
  • the user's activities are usually regular, and the residence time and frequency in certain places are high. Define the user's residence time and the place with high frequency as the resident location. If the user is in the same resident location, the type of activities they are engaged in is relatively fixed, and the usage scenarios of the mobile terminal are relatively fixed. Therefore, if the current geographical location of the mobile terminal is the resident location, the use of the current geographical location can be determined Scene, to push entries related to the usage scene to the user. For ease of description, the use scenario corresponding to the determined current geographic location is defined as the recommended scenario.
  • the usage scenario of the mobile terminal can be used to indicate the type of activities performed through the mobile terminal. For example, if work-related activities are performed through a mobile terminal, such as searching for work-related information, video conferencing through video conferencing software, etc., it can be determined that the mobile terminal is in the work scene; if the mobile terminal is used for entertainment activities, such as games, videos, and movies , Celebrities, etc., you can determine that the mobile terminal is in an entertainment scene.
  • work-related activities are performed through a mobile terminal, such as searching for work-related information, video conferencing through video conferencing software, etc.
  • entertainment activities such as games, videos, and movies , Celebrities, etc.
  • Step S130 Select the term related to the recommended scene from the first dictionary, and push it to the mobile terminal.
  • Entries related to the recommended scenario are usually more suitable for the user's use needs in the current geographic location, and are highly relevant to the user. Therefore, in the case of determining the recommended scenario, the entry related to the recommended scenario can be selected from the first vocabulary, and the selected entry is used as the entry pushed to the mobile terminal. When an entry needs to be pushed to the mobile terminal, the selected entry is pushed to the mobile terminal.
  • the terms to be pushed to the mobile terminal are jointly determined, which improves the relevance of the pushed terms to the user, and makes the pushed terms more in line with the user’s interests. It is easier to be searched and viewed by users.
  • Another embodiment of the present application provides a method for recommending entries. In this embodiment, it focuses on the determination of whether the resident location is determined and the method of determining the usage scenario. See Figure 2.
  • the method includes:
  • Step S210 Grab entries from multiple designated network platforms, and establish the basic push dictionary.
  • the server can build a basic push vocabulary by grabbing the entries.
  • the server can grab entries from multiple designated network platforms, such as grabbing articles from major media websites.
  • the number of network platforms is not limited. It can be all network platforms in the entire network, that is, to grab entries from the entire network; it can also be a network platform where the daily activity of users is higher than a certain threshold.
  • the fetched entry can also be a popular entry on the Internet, so as to realize that the popular entry can be pushed to the user in time.
  • an entry in a content with a higher click-through rate can be used as a popular entry.
  • the server can search for content with a click-through rate exceeding a preset value from multiple designated network platforms, and then extract key words from the searched content, and establish the basic push vocabulary through the extracted key words.
  • the term can be a word, sentence or phrase, etc.
  • the extracted key words can be the specified keywords, key sentences or phrases in the searched content, or the words marked with special symbols used to mark the keywords in the searched content, or all the searched content Entries in which the frequency or number of occurrences is higher than the specified value, etc.
  • the basic database may also include words that meet special recommendation requirements. Therefore, the server can receive the entry entered in the background; add the entry entered in the background to the basic push dictionary. For example, if a mobile terminal manufacturer wants to recommend a new device to users due to operational needs, the relevant entries of the new device can be input to the server through the background, so that the server may push the entries entered in the background to the server when pushing entries. Mobile terminal.
  • the specific method for capturing entries is not limited, and may be, for example, a web crawler technology.
  • the basic push word database can be updated once at a certain frequency.
  • Step S220 Create the user profile based on the basic user information corresponding to the mobile terminal.
  • the mobile terminal can collect basic user information of the user corresponding to the mobile terminal, and build a user profile of the mobile terminal based on the collected basic user information.
  • the server can collect the data that the user operates on the mobile terminal and the data that the user authorizes the mobile terminal to collect, so as to obtain basic user information. For example, if the user turns on the location information authorization, the server can obtain the location change of the mobile terminal.
  • the server may also obtain each user account that logs in different applications in the mobile terminal to be pushed, and then obtain the basic information disclosed by each user account in the application as the basic user information corresponding to the mobile terminal. For example, if the user logs in to application A on the mobile terminal, and discloses his identity information such as his age, constellation, city and occupation in application A, the server can obtain the user disclosure from the network platform of application A ’S identity information. If the user watches some videos in the video application B, the server can obtain the viewing time period of the video application and the specific videos that have been watched.
  • user portraits can be created based on the basic user information.
  • the specific creation process of the user profile can be based on data analysis and learning, so I won’t repeat it again.
  • step S210 and step S220 is not limited.
  • Step S230 According to the user portrait of the mobile terminal to be pushed, terms related to the user portrait are selected from the basic push word database to establish a first word database.
  • the entry can be selected from the basic push vocabulary according to the user portrait of the mobile terminal, and the specific selection is the entry related to the user portrait.
  • the specific selection method is not limited.
  • a pre-trained classification model is used to identify which terms in the basic push vocabulary are related to the user portrait of the mobile terminal; and the big data analysis is used to determine which terms are related to the user portrait of the mobile terminal.
  • the user portrait is represented by tags, that is, the user portrait of each mobile terminal includes one or more tags.
  • the corresponding relationship between each entry and the label is established in advance. Then you can select the entry corresponding to the label of the user portrait from the basic push dictionary. If the tags in the user portrait include sports and patents, you can select terms related to sports and patents from the basic push vocabulary to create the first vocabulary.
  • user portraits are expressed in specific data formats.
  • the data format of a user portrait is gender, age, occupation, and constellation.
  • the user portrait to be pushed to the mobile terminal is gender male, age 25-30 years old, professional programmer,
  • For the constellation Capricorn you can choose a male programmer of Capricorn between 25 and 30 from the basic push thesaurus to browse the more frequent entries and establish the first thesaurus.
  • step S210 to step S230 can be used as a data preparation process for selecting an entry to push when the mobile terminal is at a resident location.
  • Steps S210 to S230 can be executed according to the update settings, updating the basic push vocabulary, the user portrait, and the first vocabulary.
  • Step S240 Determine whether the geographic location where the mobile terminal is currently located is a permanent location.
  • the server can obtain the current geographic location of the mobile terminal, and determine whether the current geographic location is a resident location.
  • the historical motion trajectory of the mobile terminal describes the geographic locations that the mobile terminal has traveled through, where it has resided in, and the specific residency duration, etc.
  • the server can establish a list of permanent locations based on the historical motion trajectory of the mobile terminal.
  • the geographic location in the list of permanent locations is considered to be the permanent location of the mobile terminal.
  • a list of resident locations can be obtained.
  • the server obtains the current geographic location of the mobile terminal, and determines whether the current geographic location is the geographic location in the permanent location list, that is, determines whether the permanent location list includes the current geographic location of the mobile terminal. If the current geographic location of the mobile terminal is the geographic location in the permanent location list, it can be determined that the mobile terminal is located at the permanent location.
  • the server can obtain the list of resident locations when it needs to determine whether the current geographic location of the mobile terminal is a resident location, or the list of resident locations is pre-established and stored, and obtained from the storage location of the list of resident locations .
  • the specific method for establishing the list of resident locations is not limited in the embodiments of the present application. For example, the following implementation methods may be included.
  • the permanent location may be determined according to the residence time and residence probability of the geographic location in the historical motion track. Specifically, in this embodiment, it is possible to obtain the geographic locations where the mobile terminal stays longer than the preset duration each time within the preset historical time period, and establish the first geographic location list. Among them, it can be understood that the mobile terminal can be regarded as staying in the geographic location once from reaching a geographic location to leaving the geographic location. How many times the mobile terminal has stayed in the same geographic location for more than the preset time period, then the geographic location is acquired how many times. Therefore, in the first geographic location list, some geographic locations may appear multiple times, and geographic locations that appear multiple times are usually geographic locations where users often reside.
  • a geographic location with a higher probability of occurrence is obtained from the first geographic location list, and a list of resident locations of the mobile terminal is established.
  • geographic locations with an appearance probability greater than the first probability threshold can be obtained from the first geographic location list.
  • the specific size of the first probability threshold is not limited in the embodiment of the present application, and it can be measured whether the user frequently resides in a certain geographic location, and may be 0.4, 0.5, etc., for example.
  • the geographic locations where the mobile terminal stays for more than one hour each time in the most recent month can be acquired. If in the most recent month, it is obtained that the mobile terminal has stayed in geographic location A 22 times for more than one hour, 30 times in geographic location B has been parked for more than one hour, and 3 times in geographic location C has stayed for more than one hour, Then in the first geographic location list, including 22 geographic locations A, 30 geographic locations B, and 3 geographic locations C, it can be counted that the occurrence probability of geographic location A is 22/55, and that of geographic location B is 30/55, the occurrence probability of geographic location C is 3/55. If 22/55 and 30/55 exceed the first probability threshold, the established list of usual residence locations includes geographic location A and geographic location B.
  • the two geographic locations with the highest occurrence probability may also be obtained from the first geographic location list as the home and company corresponding to the mobile terminal, respectively, and used to establish a list of permanent residence locations of the mobile terminal.
  • the time period and activity status of the mobile terminal it is possible to determine which geographic location is home and which geographic location is the company. For example, the geographic location where the mobile terminal resides during the day is determined as the company, and the geographic location where the mobile terminal resides at night is determined It is home; the geographic location where the mobile terminal has been in a static state for a long time is determined as home, and the other geographic location is determined as the company.
  • the list of permanent residence locations may be created according to the residence time of the mobile terminal. Specifically, in this embodiment, it is also possible to obtain geographic locations where the mobile terminal stays longer than the preset duration each time within a preset historical time period, and establish a first geographic location list.
  • the total residency duration of different geographic locations appearing in the first geographic location list can be counted.
  • the same geographic location may appear multiple times.
  • the residence time of all times in the same geographic location in the first geographic location list can be added to obtain the location of the geographic location. Total length of stay.
  • the multiple geographic locations in the first geographic location list are sorted according to the total length of stay of the mobile terminal in each geographic location. It is understandable that different geographic locations are sorted, that is, the sorting result includes different geographic locations where the mobile terminal resides for more than one period of time within a preset historical period.
  • a preset number of geographic locations with the longest total duration are selected from the first geographic location list to establish the permanent location list, and the geographic locations in the permanent location list are the selected preset number of geographic locations .
  • the total duration can be sorted from high to low, or the total duration can be sorted from low to high. If it is sorted from high to low, the first preset number of geographic locations in the sorting result can be obtained, and if it is sorted from low to high, then the second preset number of geographic locations in the sorting result can be obtained.
  • the total duration of 22 stays in geographic location A reached 176 hours
  • the total duration of 30 stays at geographic location B reached 480 hours
  • the total duration of two stays at geographic location C When it reaches 7 hours, the total time is sorted from high to low in order of geographic location B, geographic location A, and geographic location C.
  • 2 is the preset number
  • a list of resident locations is established based on geographic location B and geographic location A, that is, geographic locations in the list of permanent locations are geographic location B and geographic location A.
  • a geographic location with a total residence time greater than a set duration threshold may also be selected to establish a permanent location list.
  • the two geographic locations with the longest total stay time may also be obtained from the first geographic location list as the home and company corresponding to the mobile terminal, and used to establish the permanent residence of the mobile terminal. List.
  • the location of the mobile terminal may be periodic. For example, it may stay at the work place for a long time from Monday to Friday, but it will not stay at the work place at all on Saturdays and Sundays. Therefore, the embodiment of the present application also provides an implementation manner for creating a list of resident locations in combination with periodic statistical results.
  • the server may monitor the geographic location of the mobile terminal once every preset time interval.
  • the specific value of the preset time interval is not limited in the embodiment of the present application, for example, it may be less than the preset time length in the foregoing embodiment.
  • the monitoring result it is possible to obtain the geographic locations whose occurrence probability is greater than the second probability threshold within each preset period within a preset historical period of time, and establish a second geographic location list.
  • the preset historical period includes multiple preset periods. It is understandable that if the probability of the same geographic location in multiple preset periods is greater than the second probability threshold, the same geographic location appears multiple times in the second geographic location list, or in other words, for a certain geographic location, How many times the occurrence probability in the preset period is greater than the second probability threshold value in the second geographic location.
  • the specific values of the second probability threshold and the third probability threshold are not limited, and it is possible to measure whether the user frequently resides in a certain geographic location.
  • the preset period is days
  • the preset historical period is the most recent month
  • the geographic location of the mobile terminal is monitored every half an hour. Then, it is possible to obtain the number of stays of the mobile terminal in various geographic locations that are monitored every day in the last month. Calculate the number of times that different geographical locations are monitored every day to the total number of times that all geographical locations are monitored, and obtain the probability of each different geographical location appearing every day. And calculate the geographic location whose occurrence probability is greater than the second probability threshold that is monitored every day. Then calculate the occurrence probability of greater than the third threshold within one month
  • the mobile terminal was detected at geographic location A 16 times, the mobile terminal was detected at geographic location B 20 times, and the mobile terminal was monitored at geographic location C 2 times. Then it can be calculated that the mobile terminal has moved within this day.
  • the probability of appearance of terminal A is 16/38, the probability of appearance of mobile terminal B is 20/38, and the probability of appearance of mobile terminal C is 2/38. If the second probability threshold is 0.4, it can be determined that geographic location A and geographic location B are geographic locations whose occurrence probability is greater than the second probability threshold in this day.
  • the occurrence probability of geographic location A is greater than the second probability threshold for 22 days, and the occurrence probability of geographic location B is greater than the second probability threshold for 30 days, then in the second geographic location list, geographic location A is recorded 22 times, location B recorded 30 times.
  • the number of occurrences of geographic locations is divided by the total number of geographic locations. If there are only geographic location A and geographic location B in the second geographic location list, the occurrence probability of geographic location A in the second geographic location list is 22/55, and the appearance probability of geographic location B in the second geographic location list is 30 /55.
  • the two geographic locations with the highest occurrence probability may also be obtained from the second geographic location list, which are respectively used as the home and company corresponding to the mobile terminal, and are used to establish a list of habitual residence locations of the mobile terminal.
  • the size of the area of a geographic location is not limited, and can be set according to actual needs. For example, a geographic area within one square kilometer can be determined to be the same geographic location.
  • Step S250 If the current geographic location of the mobile terminal is the resident location, determine the usage scenario corresponding to the current geographic location as a recommended scenario.
  • the usage scenarios of each resident location can be determined in advance through big data analysis and stored.
  • the list of resident locations can be determined according to the historical operation data of each geographic location in the list of resident locations of the mobile terminal.
  • the use scenario corresponding to the current geographic location of the mobile terminal can be determined according to the current geographic location of the mobile terminal and the use scenario corresponding to each geographic location in the permanent location list.
  • the use scenario of the resident location may be determined through big data analysis as the recommended scenario. According to the historical operation data of the mobile terminal in the current geographic location, the current usage scenario of the mobile terminal is determined as the recommended scenario.
  • the types of activities that users engage in at the same permanent location are the same and the content is similar.
  • For each resident location by analyzing the historical operation data of the mobile terminal at the resident location, it can be obtained which type of activity the mobile terminal is engaged in at the resident location has a higher probability, and the type of activity is determined as mobile
  • the usage scenario of the terminal in the resident location For example, when the user is at the work place, it is usually a work-related activity.
  • the content that the user is interested in may be work-related, so as to determine the use scene of the mobile terminal as the work scene;
  • the use scene of the mobile terminal can be obtained as an entertainment scene.
  • the historical operation data may be data generated by the user operating the mobile terminal within a specified period of time in the past, such as the user's search data, questionnaire data, download data, etc. in the past year.
  • a classification model can be trained in advance through data, and the classification model can classify the input data as a usage scenario.
  • the historical operation data of this geographic location is input to the classification model, and the classification model classifies the use scenario corresponding to the geographic location according to the input historical operation data.
  • scenario keywords can be set for each preset usage scenario.
  • scenario keyword appears If the number of times is the most, it is determined that the geographic location belongs to the usage scenario.
  • the scenarios used by the user on the mobile terminal at different time periods may also be different.
  • the usage scenarios of the mobile terminal at different time periods within a time period are acquired. For example, for the work place, the usage scenarios of the morning, noon, and afternoon can be obtained in a day.
  • each resident location can store the usage scenarios in time periods.
  • the usage scenario of the current time period can be obtained from the list of resident locations.
  • the mobile terminal can be determined based on the current time and historical operating data of the mobile terminal in the current geographic location
  • the usage scenario of the current time period is the current usage scenario of the mobile terminal.
  • Step S260 Select the term related to the recommended scene from the first word database, and push it to the mobile terminal.
  • the correlation relationship between the entry and the usage scenario can be created in advance, so that the entry related to the recommended scenario can be selected. For example, when creating a basic push vocabulary, the correspondence between each vocabulary and usage scenario can be established. When selecting an entry from the first entry, select the entry corresponding to the recommended scenario.
  • the most popular entries can be selected from the entries corresponding to the recommended scene and pushed to the mobile terminal.
  • the popularity can be measured according to the click-through rate of the related content of the entry. The higher the click-through rate, the higher the popularity.
  • the user can perform content search on the mobile terminal, and the mobile terminal can send the keywords entered by the user during the search to the server.
  • the server may receive the search keyword sent by the mobile terminal, search for the entry associated with the search keyword from the selected entry, and push it to the mobile terminal.
  • the terms related to the search keyword may be terms with the same text or terms with the search keyword, etc.
  • the mobile terminal receives the entry pushed by the server and can display it.
  • the mobile terminal can search for related content of the entry and display it on the mobile terminal.
  • a basic push word database can be created for online hot words, and a user portrait can be created for a mobile terminal. Select the terms related to the user portrait from the basic push thesaurus to establish the first thesaurus.
  • the use scenario of the current geographic location can be determined, so that terms related to the use scenario can be selected from the first dictionary and pushed to the mobile terminal. Since the use scene of the current geographic location is the scene that the user is currently paying attention to, the terms pushed to the user not only closely follow the social hot spots, but also have a strong relevance to the user.
  • this application also provides an embodiment as shown in FIG. 3, and the term push method in this embodiment may include:
  • Step S310 According to the user portrait of the mobile terminal to be pushed, terms related to the user portrait are selected from the basic push vocabulary to establish a first vocabulary.
  • step S310 For the specific description of step S310, reference may be made to the foregoing embodiment, which will not be repeated here.
  • Step S320 Obtain the moving speed and the moving route of the mobile terminal.
  • Step S330 If the moving speed is greater than the preset speed and there is a public transportation that is the same as the moving route of the mobile terminal, it is determined that the mobile terminal is at a permanent location.
  • Step S340 If the current geographic location of the mobile terminal is the resident location, determine the usage scenario corresponding to the current geographic location as the recommended scenario.
  • Step S350 Select the term related to the recommended scene from the first word database, and push it to the mobile terminal.
  • the moving speed of the mobile terminal is the same as that of the vehicle, and the speed is usually higher than that of the user walking.
  • public transportation usually has a relatively fixed route. Therefore, if the user is taking a public transportation with a mobile terminal, the movement route is consistent with the route of the public transportation.
  • the moving speed and movement route of the mobile terminal can be acquired. If the moving speed of the mobile terminal is greater than the preset speed, it can be determined that the mobile terminal is in a vehicle. If there is a public transportation that is the same as the movement route of the mobile terminal at the same time, it can be determined that the mobile terminal is in the public transportation, so that it can be determined that the mobile terminal is in the resident location.
  • the server can obtain the movement route of the public transport in a certain area where the mobile terminal is located, and then compare the movement route of the mobile terminal with the movement route of each public transport, so as to determine whether there is a movement route of the public transport and the mobile terminal.
  • the exercise route is the same.
  • the mobile terminal if the mobile terminal is moving at a speed greater than the preset speed, and there is a public transportation that is the same as the moving route of the mobile terminal, it is determined that the usage scenario corresponding to the current geographic location is a traffic scenario, and Select the terms related to the traffic scene in the word database and push them to the mobile terminal.
  • the terms related to the traffic scene can be determined according to the historical operation data of the mobile terminal in the traffic scene.
  • the recommended terms that are related to the historical operation data are larger than the preset terms.
  • determine the type of historical operation data of the mobile terminal in the traffic scene and use the same type of terms as the terms related to the traffic scene.
  • the type of historical operation data is a movie-related type, and the movie-related entries are used as the traffic scene-related entries.
  • a movement route can be used as a special geographic location.
  • the movement route frequently passed by the mobile terminal is added to the list of permanent locations as the geographic location.
  • Whether to add to the list of resident locations can be determined according to the number or frequency of the movement route passed by the mobile terminal. For specific sports routes to be added to the movement route list, reference may be made to the foregoing embodiment, which will not be repeated here.
  • the movement route of the public transportation means is the same as the movement route of the mobile terminal, it can be judged whether the movement route is in the permanent location list, and if so, it can be determined that the mobile terminal is at the permanent location.
  • the mobile terminal has taken public transportation on the current movement route in history, it can be determined that the mobile terminal is at the resident location.
  • the mobile terminal if it is determined that the mobile terminal is at the resident location, it can be determined that the usage scenario corresponding to the current geographic location is a traffic scenario.
  • the historical operation data of the mobile terminal under the same trajectory of the public transportation means can be acquired as reference data. Then determine the type of the reference data, select the entry of the same type as the reference data from the first lexicon, and push it to the mobile terminal.
  • the mobile terminal if the user carries the mobile terminal and rides in a vehicle, it can also be determined that the user is in a resident location, and the mobile terminal can be determined to be in a traffic scene, and relevant entries in the traffic scene can be pushed to the mobile terminal. Therefore, even if the mobile terminal is not in a fixed place, if it is in the state of taking public transportation, it can push the entry to the mobile terminal based on the portrait of the user and the user's usage habits, thereby improving the relevance of the entry to the user.
  • the device 400 includes: a thesaurus establishment module 410, configured to select terms related to the user portrait from the basic pushed thesaurus to establish a first thesaurus according to the user portrait of the mobile terminal to be pushed;
  • the scenario determination module 420 is configured to determine the use scenario corresponding to the current geographic location if the current geographic location of the mobile terminal is the resident location, as a recommended scenario;
  • the push module 430 is configured to obtain information from the first
  • the vocabulary related to the recommended scene is selected from the vocabulary and pushed to the mobile terminal.
  • the device 400 may further include a resident location determining module, and the resident location module may include a list acquiring unit for acquiring a list of resident locations, the list of resident locations is based on the historical movement track of the mobile terminal Establishment; a location acquiring unit for acquiring the current geographic location of the mobile terminal; a determining unit for determining whether the current geographic location is a geographic location in the list of permanent locations; a determining unit for If the current geographic location is a geographic location in the list of permanent locations, it is determined that the mobile terminal is located at the permanent location.
  • the resident location module may include a list acquiring unit for acquiring a list of resident locations, the list of resident locations is based on the historical movement track of the mobile terminal Establishment; a location acquiring unit for acquiring the current geographic location of the mobile terminal; a determining unit for determining whether the current geographic location is a geographic location in the list of permanent locations; a determining unit for If the current geographic location is a geographic location in the list of permanent locations, it is determined that the mobile terminal
  • the device may include a location list creation module, which is used to obtain geographic locations where the mobile terminal stays longer than the preset duration each time within a preset historical period, and establish a first geographic location list; The geographic locations whose occurrence probability is greater than the first probability threshold are acquired from the geographic location list, and the permanent location list is established.
  • a location list creation module which is used to obtain geographic locations where the mobile terminal stays longer than the preset duration each time within a preset historical period, and establish a first geographic location list; The geographic locations whose occurrence probability is greater than the first probability threshold are acquired from the geographic location list, and the permanent location list is established.
  • the device may include a location list creation module, which is used to obtain geographic locations where the mobile terminal stays longer than the preset duration each time within a preset historical period, and establish a first geographic location list; according to the mobile terminal For the total residence time of each geographic location, sort the multiple geographic locations in the first geographic location list; according to the sorting result, select the preset number of geographic locations with the longest total duration from the first geographic location list. Location, establish the list of resident locations.
  • a location list creation module which is used to obtain geographic locations where the mobile terminal stays longer than the preset duration each time within a preset historical period, and establish a first geographic location list; according to the mobile terminal For the total residence time of each geographic location, sort the multiple geographic locations in the first geographic location list; according to the sorting result, select the preset number of geographic locations with the longest total duration from the first geographic location list. Location, establish the list of resident locations.
  • the device may include a location list creation module, which is used to monitor the geographic location of the mobile terminal every preset time interval; to obtain the preset historical time period, the detected occurrence probability in each preset period is greater than the second A geographic location with a probability threshold, a second geographic location list is established, and the preset historical period includes multiple preset periods; a geographic location with an occurrence probability greater than the third probability threshold is obtained from the second geographic location list, and the geographic location is established The list of resident locations.
  • a location list creation module which is used to monitor the geographic location of the mobile terminal every preset time interval; to obtain the preset historical time period, the detected occurrence probability in each preset period is greater than the second A geographic location with a probability threshold, a second geographic location list is established, and the preset historical period includes multiple preset periods; a geographic location with an occurrence probability greater than the third probability threshold is obtained from the second geographic location list, and the geographic location is established The list of resident locations.
  • the scenario determination module 420 may be configured to determine the usage scenario corresponding to each geographic location in the permanent location list according to the historical operation data of each geographic location in the permanent location list of the mobile terminal;
  • the use scenario corresponding to each geographic location in the list of residential locations determines the use scenario corresponding to the current geographic location of the mobile terminal as a recommended scenario.
  • the device may include a resident location determining module to obtain the moving speed and moving route of the mobile terminal; if the moving speed is greater than the preset speed and there is a public transportation that is the same as the moving route of the mobile terminal, It is determined that the mobile terminal is at a permanent location.
  • the scene determination module 420 may be used to determine that the usage scene corresponding to the current geographic location is a traffic scene .
  • the push module 430 can be used to obtain historical operation data of the mobile terminal in the same condition as the public transportation means as reference data; determine the type of the reference data; The entries of the same type as the reference data are pushed to the mobile terminal.
  • the scenario determination module 420 may be configured to determine the current use scenario of the mobile terminal according to the current time and historical operation data of the mobile terminal in the current geographic location, as a recommended scenario.
  • the push module 430 may also be used to receive search keywords sent by the mobile terminal; to search for terms associated with the search keywords from the selected terms, and push them to the mobile terminal.
  • the device may further include a portrait creation module, configured to create the user portrait based on the basic user information corresponding to the mobile terminal.
  • a portrait creation module configured to create the user portrait based on the basic user information corresponding to the mobile terminal.
  • the portrait creation module may be used to obtain various user accounts that log in different applications in the mobile terminal; obtain basic information disclosed in the application by each user account as the basic user information corresponding to the mobile terminal.
  • the device may also include a thesaurus establishment module, which is used to grab terms from multiple designated network platforms and establish the basic push thesaurus.
  • a thesaurus establishment module which is used to grab terms from multiple designated network platforms and establish the basic push thesaurus.
  • the thesaurus building module can be used to search for content with a click-through rate exceeding a preset value from multiple designated network platforms; extract key words from the searched content; establish the said key words from the extracted key words.
  • the vocabulary establishment module may also be used to receive back-end input terms; add the back-end input terms to the basic push vocabulary.
  • the coupling between the modules may be electrical, mechanical or other forms of coupling.
  • each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or software function modules.
  • Each module can be configured in different electronic devices, and can also be configured in the same electronic device, which is not limited in the embodiment of the present application.
  • FIG. 5 shows a structural block diagram of an electronic device 500 provided by an embodiment of the present application.
  • the electronic device 500 may be a smart device such as a server, a smart phone, a tablet computer, or a computer.
  • the term push method and device in the embodiments of the present application may be executed by one electronic device; or may be executed by multiple electronic devices, such as a system cluster composed of multiple servers.
  • the electronic device may include one or more processors 510 (only one is shown in the figure), a memory 520, and one or more programs. Wherein, the one or more programs are stored in the memory 520 and configured to be executed by the one or more processors 510. The one or more programs are configured to execute the methods described in the foregoing embodiments. If the method described in the foregoing embodiment is executed by multiple electronic devices, each electronic device may be configured with a part of the program to be executed.
  • the processor 510 may include one or more processing cores.
  • the processor 510 uses various interfaces and lines to connect various parts of the entire electronic device 400, and executes by running or executing instructions, programs, code sets, or instruction sets stored in the memory 520, and calling data stored in the memory 520.
  • the processor 510 may use at least one of Digital Signal Processing (DSP), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), and Programmable Logic Array (Programmable Logic Array, PLA).
  • DSP Digital Signal Processing
  • FPGA Field-Programmable Gate Array
  • PLA Programmable Logic Array
  • the processor 510 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), a modem, and the like.
  • the CPU mainly processes the operating system, user interface, and application programs; the GPU is used for rendering and drawing of display content; the modem is used for processing wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 510, but may be implemented by a communication chip alone.
  • the memory 520 may include random access memory (RAM) or read-only memory (Read-Only Memory).
  • the memory 520 may be used to store instructions, programs, codes, code sets or instruction sets.
  • the memory 520 may include a storage program area and a storage data area, where the storage program area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing each of the foregoing method embodiments, and the like.
  • the data storage area can also be the data created by the electronic device in use, etc.
  • FIG. 6 shows a structural block diagram of a computer-readable storage medium provided by an embodiment of the present application.
  • the computer-readable storage medium 600 stores program code, and the program code can be invoked by a processor to execute the method described in the foregoing method embodiment.
  • the computer-readable storage medium 600 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM.
  • the computer-readable storage medium 600 includes a non-transitory computer-readable storage medium.
  • the computer-readable storage medium 600 has storage space for the program code 610 for executing any method steps in the above-mentioned methods. These program codes can be read from or written into one or more computer program products.
  • the program code 610 may be compressed in a suitable form, for example.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Telephone Function (AREA)

Abstract

本申请公开了一种词条推送方法、装置、电子设备及存储介质，涉及数据处理技术领域。其中，该方法包括：根据待推送的移动终端的用户画像，从基础推送词库中选择与所述用户画像相关的词条建立第一词库；若所述移动终端当前所处的地理位置为常驻地点，确定当前所处的地理位置对应的使用场景，作为推荐场景；从所述第一词库中选择所述推荐场景相关的词条，向所述移动终端推送，提高了推送的词条与使用移动终端的用户本身的相关性。

Description

词条推送方法、装置、电子设备及存储介质 技术领域
本申请涉及数据推送技术领域，更具体地，涉及一种词条推送方法、装置、电子设备及存储介质。
背景技术
在移动终端中的很多应用程序都支持搜索功能，用户可以通过应用程序进行信息搜索。另外，应用程序也可以向用户显示推荐词条，用于用户选择搜索推荐词条相关内容。但是，通常在应用程序中显示的推荐词条与用户本身关联性不强，对用户而言是无用的信息。
发明内容
鉴于上述问题，本申请提出了一种词条推送方法、装置、电子设备及存储介质，以改善上述问题。
第一方面，本申请实施例提供了一种词条推送方法，所述方法包括：根据待推送的移动终端的用户画像，从基础推送词库中选择与所述用户画像相关的词条建立第一词库；若所述移动终端当前所处的地理位置为常驻地点，确定当前所处的地理位置对应的使用场景，作为推荐场景；从所述第一词库中选择所述推荐场景相关的词条，向所述移动终端推送。
第二方面，本申请实施例提供了一种词条推送装置，所述装置包括：词库建立模块，用于根据待推送的移动终端的用户画像，从基础推送词库中选择与所述用户画像相关的词条建立第一词库；场景确定模块，用于若所述移动终端当前所处的地理位置为常驻地点，确定当前所处的地理位置对应的使用场景，作为推荐场景；推送模块，用于从所述第一词库中选择所述推荐场景相关的词条，向所述移动终端推送。
第三方面，本申请实施例提供了一种电子设备，包括：一个或多个处理器；存储器；一个或多个程序。其中所述一个或多个程序被存储在所述存储器中并被配置为由所述一个或多个处理器执行，所述一个或多个程序配置用于执行上 述的方法。
第四方面，本申请实施例提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有程序代码，所述程序代码可被处理器调用执行上述的方法。
本申请实施例提供的词条推送方法、装置、电子设备及存储介质，根据用户画像从基础推送词库中选择相关词条建立第一词库。并且，当移动终端处于常驻地点时，根据移动终端当前所处地理位置确定当前的推荐场景。从第一词库中选择推荐场景相关的词条向移动终端推送。从而，向移动终端推送的词条既结合了用户画像，也结合了移动终端的地理位置，提高了推送的词条与使用移动终端的用户本身的相关性。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1示出了本申请一实施例提供的词条推送方法的流程图。
图2示出了本申请另一实施例提供的词条推送方法的流程图。
图3示出了本申请又一实施例提供的词条推送方法的流程图。
图4示出了本申请实施例提供的词条推送装置的功能模块图。
图5示出了本申请实施例提供的电子设备的结构框图。
图6是本申请实施例的用于保存或者携带实现根据本申请实施例的词条推送方法的程序代码的存储单元。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述。
移动终端中的应用程序可以通过各种方式向用户推送词条。例如，在用户打开应用程序的搜索界面时，在搜索界面中显示推送的词条。或者在用户通过搜索框输入关键词进行搜索时，在搜索框下对应输入的关键词显示推送的词条。又或者在应用程序开启了通知权限时，在移动终端的通知栏显示推送的词条。
在一些实施方式中，应用程序推送的词条可能仅仅为该应用程序所在平台上的热门内容，例如微博的热搜；在另一些实施方式中，对应搜索框推送词条时，推送的词条可能仅仅与用户输入的关键词相关，如词条本身内容中包括用户输入的关键词。在这些推送方式中，都没有关注用户本身在当前环境下的需求，推送的词条与用户本身关联性不强，无法引起用户兴趣。
因此，发明人提出了本申请实施例提供的词条推送方法、装置、电子设备及存储介质，用于服务器根据用户画像以及移动终端所处地理位置向移动终端推送词条。其中，服务器可以将词条推送到移动终端中该服务器所服务的应用程序。下面将通过具体实施例对本申请实施例提供的词条推送方法、装置、电子设备及存储介质进行详细说明。
请参阅图1，示出了本申请实施例提供的词条推送方法。具体的，该方法包括：
步骤S110：根据待推送的移动终端的用户画像，从基础推送词库中选择与所述用户画像相关的词条建立第一词库。
服务器可以向通信连接的移动终端推送词条，以需要推送词条的移动终端为待推送的移动终端，本申请实施例以向一个移动终端作为待推送的移动终端为例进行说明。
不同的移动终端的使用者可能不同，而不同的使用者感兴趣的内容不同，因此，针对不同的移动终端可以建立有用户画像，该用户画像是移动终端使用者的抽象表示，是使用者的虚拟代表，可以包括使用者的身份以及兴趣偏好等各种信息。例如，移动终端的用户画像可以是将移动终端的使用者的具体信息抽象成标签，从而可以利用这些标签将用户形象具体化，更准确地确定用户的关注点，为用户提供有针对性的服务。
在基础推送词库中，包括了各种类型的词条，向不同移动终端推送的词条都可以从该基础推送词库中进行选择。在基础推送词库中，有些词条可能是待推送移动终端的用户感兴趣的词条，有些词条可能是待推送移动终端的用户不感兴趣的词条。因此，可以从基础推送词库中选择与用户画像相关的词条建立词库，定义该词库为第一词库。第一词库作为待推送移动终端的词库，在一定程度上符合待推送移动终端的用户的兴趣点。
步骤S120：若所述移动终端当前所处的地理位置为常驻地点，确定当前所处的地理位置对应的使用场景，作为推荐场景。
用户的活动通常具有规律性，在某些地点驻留的时间以及频率较高，定义用户驻留时间以及频率较高的地点为常驻地点。若用户在同一常驻地点，所从事活动的类型较为固定，对移动终端的使用场景较为固定，因此，若移动终端当前所在的地理位置为常驻地点，可以确定当前所处的地理位置的使用场景，以向用户推送该使用场景相关的词条。为了便于描述，定义确定的当前所处地理位置对应的使用场景为推荐场景。
其中，移动终端的使用场景可以用于表示通过移动终端从事的活动的类型。例如，若通过移动终端进行工作相关的活动，如搜索工作相关的信息、通过视频会议软件进行视频会议等，可以确定移动终端处于工作场景；若通过移动终端进行娱乐活动，如游戏、视频、电影、明星等，可以确定移动终端处于娱乐场景。
步骤S130：从所述第一词库中选择所述推荐场景相关的词条，向所述移动终端推送。
与推荐场景相关的词条，通常比较契合于在当前地理位置用户的使用需求，与用户的相关性较高。因此，在确定推荐场景的情况下，可以从第一词库中选择与推荐场景相关的词条，将选择的词条作为向移动终端推送的词条。在需要向移动终端推送词条时，将选择的词条推送到移动终端。
本申请实施例中，基于用户画像以及移动终端的地理位置，共同确定向移动终端推送的词条，提高了推送的词条与用户的相关性，使推送的词条更符合用户的兴趣，从而更容易被用户搜索查看。
本申请另一实施例提供了一种词条推荐方法，在该实施例中，着重描述了是否常驻地点的确定以及使用场景的确定方式。请参见图2，该方法包括：
步骤S210：从多个指定的网络平台中抓取词条，建立所述基础推送词库。
服务器可以通过抓取词条的方式建立基础推送词库。
其中，服务器可以从多个指定的网络平台抓取词条，如从各大媒体网站的文章进行抓取。网络平台的数量并不限定，可以是全网所有的网络平台，即从全网进行词条抓取；也可以是用户日活跃量高于一定阈值的网络平台。另外，抓取的词条也可以是网络的热门词条，以实现能及时向用户推送热门词条。
具体的，可以以点击率较高的内容中的词条作为热门词条。服务器可以从 多个指定的网络平台中搜索点击率超过预设值的内容，再从搜索到的内容中提取关键词条，通过提取的关键词条建立所述基础推送词库。其中，词条可以是词语、句子或短语等。提取的关键词条可以是搜索到的内容中的指定的关键词、关键句子或短语等，或者搜索到的内容中用于标记关键词的特殊符号标记的词条、或者是搜索到的所有内容中出现频率或次数高于指定值的词条等。
另外，可选的，基础数据库中还可以包括满足特殊推荐需求的词语。因此，服务器可以接收后台输入的词条；将所述后台输入的词条添加到所述基础推送词库。例如，移动终端的厂商因运营需要，要向用户推荐新款设备，可以将该新款设备的相关的词条通过后台输入到服务器，以使服务器在推送词条时可能将后台输入的词条推送到移动终端。
在本申请实施例中，具体进行词条抓取的方式并不限定，例如可以是网络爬虫技术。
在本申请实施例中，由于网络中的热门内容会处于变化中，因此，可以以一定的频率更新一次基础推送词库。
步骤S220：基于所述移动终端对应的用户基本信息，建立所述用户画像。
移动终端可以搜集移动终端对应的用户的用户基本信息，根据搜集的用户基本信息，建立移动终端的用户画像。
其中，服务器可以搜集用户在该移动终端进行操作的数据以及用户授权移动终端进行采集的数据，获得用户基本信息。例如，用户开启了位置信息授权，服务器则可以获得移动终端的位置变化。
服务器还可以获取在待推送的移动终端中登录不同应用程序的各个用户帐号，再获取各个用户帐号在应用程序中公开的基本信息，作为所述移动终端对应的用户基本信息。例如，用户在移动终端登录了应用程序A，并且在应用程序A中公开了自己的年龄、星座、所处的城市以及职业等身份信息，服务器则可以从应用程序A的网络平台中获得用户公开的身份信息。若用户在视频应用程序B中观看了某些视频，则服务器可以获取到视频应用程序的观看时间段以及具体观看了哪些视频等。
若搜集到用户基本信息，则可以根据用户基本信息创建用户画像。用户画像的具体创建过程可以基于数据分析以及学习，再次不进行赘述。
在本申请实施例中，步骤S210以及步骤S220的执行顺序并不限定。
步骤S230：根据待推送的移动终端的用户画像，从基础推送词库中选择 与所述用户画像相关的词条建立第一词库。
在需要向移动终端推送词条时，可以根据移动终端的用户画像，从基础推送词库中选择词条，具体选择的为与用户画像相关的词条。
具体选择方式并不限定，例如，通过预先训练的分类模型识别基础推送词库哪些词条与移动终端的用户画像相关；通过大数据分析确定哪些词条与移动终端的用户画像相关等。
例如用户画像通过标签表示，即每个移动终端的用户画像包括一个或多个标签。并且，预先建立各个词条与标签的对应关系。则可以从基础推送词库中选择对应用户画像的标签的词条。如用户画像中的标签包括体育、专利，则可以从基础推送词库中选择与体育以及专利相关的词条创建第一词库。
又如，用户画像通过具体的数据形式进行表示，如一个用户画像的数据形式为性别、年龄、职业、星座，待推送移动终端的用户画像为性别男、年龄25～30岁、职业程序员、星座摩羯座，则可以从基础推送词库中选择25～30之间摩羯座的男性程序员浏览频率较高的词条，建立第一词库。
在本申请实施例中，步骤S210至步骤S230可以作为数据准备过程，用于在移动终端处于常驻地点时选择词条进行推送。步骤S210至步骤S230可以根据更新设置执行，更新基础推送词库、用户画像以及第一词库。
步骤S240：判断动终端当前所处的地理位置是否为常驻地点。
当需要向移动终端推送词条时，服务器可以获取移动终端当前的地理位置，并判断该当前地理位置是否为常驻地点。
具体的，移动终端的历史运动轨迹刻画了移动终端移动通过过哪些地理位置、在哪些地理位置进行过驻留以及具体驻留时长等，服务器可以根据移动终端的历史运动轨迹建立常驻地点列表，该常驻地点列表中的地理位置认为是移动终端的常驻地点。
在判断移动终端当前所处地理位置是否为常驻地点时，可以获取常驻地点列表。服务器获取移动终端当前所处的地理位置，判断当前所处的地理位置是否为所述常驻地点列表中的地理位置，即判断常驻地点列表中是否包括移动终端当前所处的地理位置。若移动终端当前所处的地理位置为常驻地点列表中的地理位置，可以确定所述移动终端处于常驻地点。
其中，服务器获取常驻地点列表可以是，在需要判断移动终端当前所处地 理位置是否为常驻地点时建立，也可以是常驻地点列表预先建立并存储，从常驻地点列表的存储位置获取。常驻地点列表的具体建立方式在本申请实施例中并不限定，例如可以包括如下几种实施方式。
在一种具体的实施方式中，可以根据历史运动轨迹中地理位置的驻留时长以及驻留概率确定常驻地点。具体的，在该实施方式中，可以获取预设的历史时段内，移动终端每次驻留时长超过预设时长的地理位置，建立第一地理位置列表。其中，可以理解的，移动终端完成从到达一个地理位置到离开该地理位置可以认为移动终端在该地理位置驻留一次。移动终端在同一个地理位置驻留超过预设时长达到多少次，则获取到多少次该地理位置。因此，在第一地理位置列表中，有些地理位置可能出现多次，而出现多次的地理位置通常为用户经常驻留的地理位置。因此，从第一地理位置列表中获取出现概率较高的地理位置，建立移动终端的常住地点列表，具体的，可以从所述第一地理位置列表中获取出现概率大于第一概率阈值的地理位置，建立所述常驻地点列表。该第一概率阈值的具体大小在本申请实施例中并不限定，以可以衡量用户是否经常某地理位置驻留为准，例如可以是0.4、0.5等。
例如，以最近一个月作为预设的历史时段，以一小时作为预设时长，则可以获取最近一个月内，移动终端每次驻留时长超过一小时的地理位置。若在最近一个月内，获取到移动终端在地理位置A有22次驻留超过一小时，在地理位置B有30次驻留超过一小时，在地理位置C有3次驻留超过一小时，则在第一地理位置列表中，包括22次地理位置A，30次地理位置B以及3次地理位置C，则可以统计到地理位置A的出现概率为22/55，地理位置B的出现概率为30/55，地理位置C的出现概率为3/55。若22/55以及30/55超过第一概率阈值，则在建立的常住地点列表中，包括地理位置A以及地理位置B。
可选的，在该实施方式中，也可以从第一地理位置列表中获取出现概率最高的两个地理位置，分别作为移动终端对应的家和公司，用于建立移动终端的常住地点列表。并且，根据移动终端驻留的时间段以及活动状态，可以将确定哪个地理位置为家，哪个地理位置为公司，如在白天期间驻留的地理位置确定为公司，在夜间驻留的地理位置确定为家；移动终端有长时间的静止状态的地理位置确定为家，另一个地理位置确定为公司。
在另一种具体的实施方式中，可以根据移动终端的驻留时长创建常住地点列表。具体的，在该实施方式中，也可以获取预设的历史时段内，移动终端每 次驻留时长超过预设时长的地理位置，建立第一地理位置列表。
由于移动终端在一个地理位置驻留的时间越长，则表明移动终端越常驻留于该地理位置，因此，可以统计第一地理位置列表中出现的不同地理位置的驻留总时长。如前一实施方式所述，在第一地理位置列表中，同一地理位置可能出现多次，可以将第一地理位置列表中相同地理位置所有次数的驻留时长相加，获得该地理位置的驻留总时长。
根据所述移动终端在每个地理位置的驻留总时长，对所述第一地理位置列表中的多个地理位置进行排序。可以理解的，进行排序的为不同的地理位置，即在排序结果中，包括预设的历史时段内，移动终端驻留超过一个时长的不同地理位置。
根据排序结果，从第一地理位置列表中选取总时长最长的预设数量的地理位置，建立所述常驻地点列表，在常驻地点列表中的地理位置为选取的预设数量的地理位置。其中，可以以总时长由高到低排序，也可以根据总时长由低到高排序。若是由高到低排序，则可以获取排序结果中前预设数量的地理位置，若是由低到高进行排序，则可以获取排序结果中后预设数量的地理位置。
继续以前述例子进行说明。若在最近一个月内，移动终端在地理位置A驻留的22次总时长达到176小时，在地理位置B驻留的30次总时长达到480小时，在地理位置C驻留的两次总时长达到7小时，则根据总时长由高到低排序依次为地理位置B、地理位置A以及地理位置C。若以2为预设数量，则根据地理位置B以及地理位置A建立常驻地点列表，即常驻地点列表中的地理位置为地理位置B以及地理位置A。
可选的，在该实施方式中，也可以选取驻留总时长大于设置的时长阈值的地理位置建立常驻地点列表。
可选的，在该实施方式中，也可以从第一地理位置列表中获取驻留总时长最长的两个地理位置，分别作为移动终端对应的家和公司，用于建立移动终端的常住地点列表。
在某些情况下，移动终端的地理位置驻留可能是周期性的，如周一至周五可能在工作地点长时间驻留，但是周六以及周日完全不会在工作地理位置驻留。因此，本申请实施例还提供了一种结合周期性统计结果创建常驻地点列表的实施方式。
在该实施方式中，服务器可以每隔预设时间间隔监测一次移动终端的地理位置。该预设时间间隔的具体值在本申请实施例中并不限定，例如可以是小于 前述实施方式中的预设时长。
根据监测结果，可以获取预设的历史时段内，每个预设周期内监测到出现概率大于第二概率阈值的地理位置，建立第二地理位置列表。其中，预设的历史时段内包括多个预设周期。可以理解的，若有多个预设周期内有同一个地理位置概率大于第二概率阈值，则第二地理位置列表中该同一个地理位置出现多次，或者说，对于某一地理位置，在多少个预设周期内出现概率大于第二概率阈值，则在第二地理位置中出现多少次。
从所述第二地理位置列表中获取出现概率大于第三概率阈值的地理位置，建立所述常驻地点列表。在本申请实施例中，第二概率阈值以及第三概率阈值的具体值并不限定，以可以衡量用户是否经常某地理位置驻留为准。
以具体的例子对该实施方式进行说明。若预设周期为天，预设的历史时段为最近一个月，每间隔半小时监测一次移动终端的地理位置。则可以获取最近一个月内，每天监测到的移动终端在各个地理位置的驻留次数。计算每天各个不同地理位置被监测到的次数占监测到的所有地理位置的总次数，获得各个不同地理位置在每天出现的概率。并计算得到每天监测到的出现概率大于第二概率阈值的地理位置。再计算一个月内出现概率大于第三阈值的
例如，在某天，有16次监测到移动终端在地理位置A，有20次监测到移动终端在地理位置B，有2次监测到移动终端在地理位置C，则可以计算到这一天内移动终端A出现的概率为16/38，移动终端B出现的概率为20/38，移动终端C出现的概率为2/38。若第二概率阈值为0.4，则可以确定地理位置A以及地理位置B为这一天内出现概率大于第二概率阈值的地理位置。
若一个月内，有22天地理位置A的出现概率都大于第二概率阈值，有30天地理位置B的出现概率都大于第二概率阈值，则在第二地理位置列表中，地理位置A记录22次，地理位置B记录30次。计算不同地理位置在第二地理位置列表中的出现概率时，用地理位置的出现次数除以所有地理位置的总次数。如第二地理位置列表中只有地理位置A和地理位置B，则地理位置A在第二地理位置列表中的出现概率为22/55，地理位置B在第二地理位置列表中的出现概率为30/55。
可选的，在该实施方式中，也可以从第二地理位置列表中获取出现概率最高的两个地理位置，分别作为移动终端对应的家和公司，用于建立移动终端的 常住地点列表。
在本申请实施例中，一个地理位置的区域范围大小并不限定，可以根据实际需要设定，例如，在一平方千米内的地理区域范围，可以确定为同一个地理位置。
步骤S250：若所述移动终端当前所处的地理位置为常驻地点，确定当前所处的地理位置对应的使用场景，作为推荐场景。
在一种具体的实施方式中，可以预先通过大数据分析确定各个常驻地点的使用场景并存储，如根据移动终端在常驻地点列表中每个地理位置的历史操作数据，确定常驻地点列表中每个地理位置对应的使用场景。在确定移动终端处于常驻地点时，可以根据移动终端当前所处的地理位置，根据常驻地点列表中每个地理位置对应的使用场景，确定移动终端当前的地理位置对应的使用场景。
在另一种具体的实施方式中，可以在确定移动终端处于常驻地点的情况下，再通过大数据分析确定该常驻地点的使用场景，作为推荐场景。根据移动终端在当前地理位置的历史操作数据，确定所述移动终端当前的使用场景，作为推荐场景。
其中，用户在同一常驻地点从事的活动类型相同，内容接近。对于每一常驻地点，通过对移动终端在该常驻地点的历史操作数据的分析，可以获得移动终端在常驻地点从事哪一类型的活动的概率较高，以该类型的活动确定为移动终端在该常驻地点的使用场景。例如，用户在工作地点，通常是进行工作相关的活动，通过对移动终端的历史操作数据分析可以确定用户感兴趣的内容可能与工作相关，从而确定移动终端的使用场景为工作场景；而用户在家里，从事的通常为比较放松的娱乐活动，如游戏、视频、观影等，通过对移动终端的历史操作数据分析，可以获得移动终端的使用场景为娱乐场景。其中，历史操作数据可以是在指定的过去一段时间内，用户在操作移动终端所产生的数据，如过去一年内用户的搜索数据、调查问卷数据、下载数据等。
在一种实施方式中，可以预先通过数据训练分类模型，该分类模型可以将输入的数据归为一个使用场景。在分析某一地理位置的使用场景时，将这一地理位置的历史操作数据输入到分类模型，由分类模型根据输入的历史操作数据归类该地理位置所对应的使用场景。
在另一种具体的实施方式中，可以为预设设置的每个使用场景设置场景关键词，在对移动终端在某一地理位置的历史操作数据分析时，哪个使用场景的场景关键词出现的次数最多，则确定该地理位置属于该使用场景。
当然，可以理解的，通过移动终端的历史操作数据分析使用场景的具体方式在本申请实施例中并不做具体限定，可以通过各种数据分析手段实现。
另外，可选的，在同一地理位置，用户在不同时段对移动终端使用的场景也可能不同。例如，在工作地点，在工作时间内可能从事工作相关的活动，而在休息时间内，可能从事娱乐活动。因此，在确定当前所处地理位置的使用场景时，还可以结合当前时间进行判断。
具体的，分析各个地理位置的使用场景时，获取一个时间周期内不同时间段移动终端的使用场景。如，对于工作地点，可以获取到一天内上午、中午、下午不同时间段的使用场景。
若预先在常驻地点列表中存储各个常驻地点的使用场景，每个常驻地点可以分时间段存储使用场景。在确定当前地理位置的使用场景时，可以从常驻地点列表中获取当前时间所在时间段的使用场景。
若在确定移动终端当前所处的地理位置为常驻地点时再通过历史操作数据分析确定使用场景，可以根据当前的时间以及所述移动终端在当前地理位置的历史操作数据，确定所述移动终端当前时间所在时间段的使用场景为移动终端当前的使用场景。
步骤S260：从所述第一词库中选择所述推荐场景相关的词条，向所述移动终端推送。
从第一词库选择词条向移动终端推送时，选择与推荐场景相关的词条进行推送。
其中，可以预先创建词条与使用场景之间相关性关系，从而可以选择到推荐场景相关的词条。例如，在创建基础推送词库时，可以建立各个词条与使用场景之间的对应关系。在从第一词条选择词条时，选择推荐场景对应的词条。
可选的，若推荐场景对应的词条过多，如大于一定的数量，可以从推荐场景对应的词条中选择热度最高的多条向移动终端推送。该热度可以根据词条相关内容的点击率衡量，点击率越高，热度越高。
可选的，用户可以在移动终端进行内容搜索，移动终端可以将用户搜索时输入的关键词发送到服务器。服务器可以接收移动终端发送的搜索关键词，从选择的词条中查找与所述搜索关键词相关联的词条，向所述移动终端推送。其中，与搜索关键词相关的词条，可以是，与搜索关键词有相同文字的词条、相同词语的词条等。
移动终端接收到服务器推送的词条，可以进行显示。当用户点击词条时，移动终端可以对该词条的相关内容进行搜索并在移动终端显示。
在本申请实施例通过的词条推送方法中，可以为基于网络热词创建基础推送词库，可以为移动终端创建用户画像。从基础推送词库中选择与用户画像相关的词条建立第一词库。再判定移动终端当前的地理位置位置为常驻地点时，可以确定当前地理位置的使用场景，从而可以从第一词库中选择与该使用场景相关的词条推送到移动终端。由于当前地理位置的使用场景为用户当前关注的场景，从而向用户推送的词条既紧跟社会热点，又是与用户本身的相关性较强。
另外，用户在乘坐地铁、公交车等公共交通工具时，不同用户对移动终端也有相应的使用习惯，通过移动终端从事的活动也比较固定。因此，公共交通工具可以认为是一种特殊的地理位置，用于进行使用场景的确定。具体的，本申请还提供了如图3所示的一种实施例，在该实施例中的词条推送方法可以包括：
步骤S310：根据待推送的移动终端的用户画像，从基础推送词库中选择与所述用户画像相关的词条建立第一词库。
步骤S310的具体描述可以参照前述实施例，在此不再进行赘述。
步骤S320：获取移动终端的移动速度以及运动路线。
步骤S330：若所述移动速度大于预设速度，且存在与所述移动终端的运动路线相同的公共交通工具，确定所述移动终端处于常驻地点。
步骤S340：若所述移动终端当前所处的地理位置为常驻地点，确定当前所处的地理位置对应的使用场景，作为推荐场景。
步骤S350：从所述第一词库中选择所述推荐场景相关的词条，向所述移动终端推送。
若用户携带移动终端乘坐交通工具，则移动终端的移动速度与交通工具一致，速度相对于用户步行等通常更高。而公共交通工具通常有相对固定的路线，因此，若用户携带移动终端乘坐的是公共交通工具，则运动路线与公共交通工具的路线一致。
因此，可以获取移动终端的移动速度以及运动路线。如果移动终端的移动速度大于预设速度，可以判断移动终端处于交通工具。若同时移动存在与移动终端运动路线相同的公共交通工具，则可以确定移动终端处于公共交通工具，从而可以确定移动终端处于常驻地点。
其中，服务器可以获取移动终端所在的一定区域内公共交通工具的运动路线，再将移动终端的运动路线与各公共交通工具的运动路线比较，从而可以确定是否有公共交通工具的运动路线与移动终端的运动路线相同。
在一种实施方式中，若移动终端移动速度大于预设速度，且存在与所述移动终端的运动路线相同的公共交通工具，则确定当前所处地理位置对应的使用场景为交通场景，从第一词库中选择交通场景相关的词条推送到移动终端。
在该实施方式中，可以根据移动终端在交通场景下的历史操作数据，确定交通场景相关的词条。例如，推荐与历史操作数据相关性的词条大于预设相关性的词条。例如，确定在交通工具场景下，移动终端的历史操作数据的类型，以相同类型的词条作为交通场景相关的词条。如在交通场景下，历史操作数据的类型为电影相关类型，则以影视相关的词条作为与交通场景相关的词条。
在另一种实施方式中，一条运动路线可以作为一个特殊的地理位置，根据移动终端的历史运动轨迹，将移动终端经常经过的运动路线作为地理位置添加到常驻地点列表中。可以根据移动终端经过运动路线的次数或者频率确定是否添加到常驻地点列表，具体哪些运动路线添加到运动路线列表中，可以参照前述实施例，在此不再赘述。
若有公共交通工具的运动路线与移动终端的运动路线相同，可以判断该运动路线是否在常驻地点列表中，若在，则可以确定移动终端处于常驻地点。
或者是，若移动终端历史上在当前的运动路线上乘坐过公共交通工具，则可以确定移动终端处于常驻地点。
在该实施方式中，若判定移动终端处于常驻地点，可以确定当前所处地理位置对应的使用场景为交通场景。可以获取所述移动终端在与公共交通工具运动轨迹相同的情况下的历史操作数据，作为参考数据。再确定所述参考数据的类型，从所述第一词库中选择与所述参考数据相同类型的词条，向所述移动终端推送。
在本申请实施例中，若用户携带移动终端乘坐交通工具，也可以确定用户处于常驻地点，并且可以确定移动终端处于交通场景，可以向移动终端推送在交通场景下相关的词条。从而实现移动终端即使不是在一个固定的地方，若是处于乘坐公共交通工具的状态，也可以基于用户画像以及用户的使用习惯向移动终端推送词条，提高词条与用户本身的相关性。
本申请实施例还提供了一种词条推送装置400。请参见图4，该装置400包括：词库建立模块410，用于根据待推送的移动终端的用户画像，从基础推送词库中选择与所述用户画像相关的词条建立第一词库；场景确定模块420，用于若所述移动终端当前所处的地理位置为常驻地点，确定当前所处的地理位置对应的使用场景，作为推荐场景；推送模块430，用于从所述第一词库中选择所述推荐场景相关的词条，向所述移动终端推送。
可选的，该装置400还可以包括常驻地点确定模块，该常驻地点模块可以包括列表获取单元，用于获取常驻地点列表，所述常驻地点列表根据所述移动终端的历史运动轨迹建立；位置获取单元，用于获取所述移动终端当前所处的地理位置；判断单元，用于判断当前所处的地理位置是否为所述常驻地点列表中的地理位置；确定单元，用于若当前所处的地理位置为所述常驻地点列表中的地理位置，确定所述移动终端处于常驻地点。
可选的，该装置可以包括地点列表创建模块，用于获取预设的历史时段内，移动终端每次驻留时长超过预设时长的地理位置，建立第一地理位置列表；从所述第一地理位置列表中获取出现概率大于第一概率阈值的地理位置，建立所述常驻地点列表。
可选的，该装置可以包括地点列表创建模块，用于获取预设的历史时段内，移动终端每次驻留时长超过预设时长的地理位置，建立第一地理位置列表；根据所述移动终端在每个地理位置的驻留总时长，对所述第一地理位置列表中的多个地理位置进行排序；根据排序结果，从第一地理位置列表中选取总时长最长的预设数量的地理位置，建立所述常驻地点列表。
可选的，该装置可以包括地点列表创建模块，用于每隔预设时间间隔监测一次移动终端的地理位置；获取预设的历史时段内，每个预设周期内监测到出现概率大于第二概率阈值的地理位置，建立第二地理位置列表，所述预设的历史时段内包括多个预设周期；从所述第二地理位置列表中获取出现概率大于第三概率阈值的地理位置，建立所述常驻地点列表。
可选的，场景确定模块420可以用于根据移动终端在常驻地点列表中每个地理位置的历史操作数据，确定所述常驻地点列表中每个地理位置对应的使用场景；根据所述常驻地点列表中每个地理位置对应的使用场景，确定移动终端当前的地理位置对应的使用场景，作为推荐场景。
可选的，该装置可以包括常驻地点确定模块，获取移动终端的移动速度以及运动路线；若所述移动速度大于预设速度，且存在与所述移动终端的运动路线相同的公共交通工具，确定所述移动终端处于常驻地点。
可选的，若所述移动速度大于预设速度，且存在与所述移动终端的运动路线相同的公共交通工具，场景确定模块420可以用于确定当前所处地理位置对应的使用场景为交通场景。推送模块430可以用于获取所述移动终端在与公共交通工具运动轨迹相同的情况下的历史操作数据，作为参考数据；确定所述参考数据的类型；从所述第一词库中选择与所述参考数据相同类型的词条，向所述移动终端推送。
可选的，场景确定模块420可以用于根据当前的时间以及所述移动终端在当前地理位置的历史操作数据，确定所述移动终端当前的使用场景，作为推荐场景。
可选的，推送模块430还可以用于接收移动终端发送的搜索关键词；从选择的词条中查找与所述搜索关键词相关联的词条，向所述移动终端推送。
可选的，该装置还可以包括画像建立模块，用于基于所述移动终端对应的用户基本信息，建立所述用户画像。
可选的，画像建立模块可以用于获取在所述移动终端中登录不同应用程序的各个用户帐号；获取各个用户帐号在应用程序中公开的基本信息，作为所述移动终端对应的用户基本信息。
可选的，该装置还可以包括词库建立模块，用于从多个指定的网络平台中抓取词条，建立所述基础推送词库。
可选的，该词库建立模块可以用于从多个指定的网络平台中搜索点击率超过预设值的内容；从搜索到的内容中提取关键词条；通过提取的关键词条建立所述基础推送词库。
可选的，该词库建立模块还可以用于接收后台输入的词条；将所述后台输入的词条添加到所述基础推送词库。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述 的各个方法实施例之间可以相互参照；上述描述装置和模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，模块相互之间的耦合可以是电性，机械或其它形式的耦合。
另外，在本申请各个实施例中的各功能模块可以集成在一个处理模块中，也可以是各个模块单独物理存在，也可以两个或两个以上模块集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。各个模块可以配置在不同的电子设备中，也可以配置在相同的电子设备中，本申请实施例并不限定。
请参考图5，其示出了本申请实施例提供的一种电子设备500的结构框图。该电子设备500可以是服务器、智能手机、平板电脑、计算机等智能设备。本申请实施例中的词条推送方法及装置，可以由一电子设备执行；也可以由多个电子设备配合执行，如多个服务器组成的系统集群。
该电子设备可以包括一个或多个处理器510(图中仅示出一个)，存储器520以及一个或多个程序。其中，所述一个或多个程序被存储在所述存储器520中，并被配置为由所述一个或多个处理器510执行。所述一个或多个程序配置用于执行前述实施例所描述的方法。若前述实施例所描述的方法由多个电子设备配合执行，每个电子设备中可以配置所要执行的部分程序。
处理器510可以包括一个或者多个处理核。处理器510利用各种接口和线路连接整个电子设备400内的各个部分，通过运行或执行存储在存储器520内的指令、程序、代码集或指令集，以及调用存储在存储器520内的数据，执行电子设备400的各种功能和处理数据。可选地，处理器510可以采用数字信号处理(Digital Signal Processing，DSP)、现场可编程门阵列(Field－Programmable Gate Array，FPGA)、可编程逻辑阵列(Programmable Logic Array，PLA)中的至少一种硬件形式来实现。处理器510可集成中央处理器(Central Processing Unit，CPU)、图像处理器(Graphics Processing Unit，GPU)和调制解调器等中的一种或几种的组合。其中，CPU主要处理操作系统、用户界面和应用程序等；GPU用于负责显示内容的渲染和绘制；调制解调器用于处理无线通信。可以理解的是，上述调制解调器也可以不集成到处理器510中，单独通过一块通信芯片进行 实现。
存储器520可以包括随机存储器(Random Access Memory，RAM)，也可以包括只读存储器(Read-Only Memory)。存储器520可用于存储指令、程序、代码、代码集或指令集。存储器520可包括存储程序区和存储数据区，其中，存储程序区可存储用于实现操作系统的指令、用于实现至少一个功能的指令、用于实现上述各个方法实施例的指令等。存储数据区还可以电子设备在使用中所创建的数据等。
请参考图6，其示出了本申请实施例提供的一种计算机可读存储介质的结构框图。该计算机可读存储介质600中存储有程序代码，所述程序代码可被处理器调用执行上述方法实施例中所描述的方法。
计算机可读存储介质600可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。可选地，计算机可读存储介质600包括非易失性计算机可读介质(non-transitory computer-readable storage medium)。计算机可读存储介质600具有执行上述方法中的任何方法步骤的程序代码610的存储空间。这些程序代码可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。程序代码610可以例如以适当形式进行压缩。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不驱使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (20)

  1. 一种词条推送方法，其特征在于，所述方法包括：
    根据待推送的移动终端的用户画像，从基础推送词库中选择与所述用户画像相关的词条建立第一词库；
    若所述移动终端当前所处的地理位置为常驻地点，确定当前所处的地理位置对应的使用场景，作为推荐场景；
    从所述第一词库中选择所述推荐场景相关的词条，向所述移动终端推送。
  2. 根据权利要求1所述的方法，其特征在于，所述若所述移动终端当前所处的地理位置为常驻地点，确定当前所处的地理位置对应的使用场景，作为推荐场景之前，还包括：
    获取常驻地点列表，所述常驻地点列表根据所述移动终端的历史运动轨迹建立；
    获取所述移动终端当前所处的地理位置；
    判断当前所处的地理位置是否为所述常驻地点列表中的地理位置；
    若是，确定所述移动终端处于常驻地点。
  3. 根据权利要求2所述的方法，其特征在于，根据所述移动终端的历史运动轨迹，建立移动终端的常驻地点列表，包括：
    获取预设的历史时段内，移动终端每次驻留时长超过预设时长的地理位置，建立第一地理位置列表；
    从所述第一地理位置列表中获取出现概率大于第一概率阈值的地理位置，建立所述常驻地点列表。
  4. 根据权利要求2所述的方法，其特征在于，根据所述移动终端的历史运动轨迹，建立移动终端的常驻地点列表，包括：
    获取预设的历史时段内，移动终端每次驻留时长超过预设时长的地理位置，建立第一地理位置列表；
    根据所述移动终端在每个地理位置的驻留总时长，对所述第一地理位置列表中的多个地理位置进行排序；
    根据排序结果，从第一地理位置列表中选取总时长最长的预设数量的地理位置，建立所述常驻地点列表。
  5. 根据权利要求2所述的方法，其特征在于，根据所述移动终端的历史运动轨迹，建立移动终端的常驻地点列表，包括：
    每隔预设时间间隔监测一次移动终端的地理位置；
    获取预设的历史时段内，每个预设周期内监测到出现概率大于第二概率阈值的地理位置，建立第二地理位置列表，所述预设的历史时段内包括多个预设周期；
    从所述第二地理位置列表中获取出现概率大于第三概率阈值的地理位置，建立所述常驻地点列表。
  6. 根据权利要求1-5任一项所述的方法，其特征在于，所述确定当前所处的地理位置对应的使用场景，作为推荐场景，包括：
    根据移动终端在常驻地点列表中每个地理位置的历史操作数据，确定所述常驻地点列表中每个地理位置对应的使用场景；
    根据所述常驻地点列表中每个地理位置对应的使用场景，确定移动终端当前的地理位置对应的使用场景，作为推荐场景。
  7. 根据权利要求1-6任一项所述的方法，其特征在于，所述若所述移动终端当前所处的地理位置为常驻地点，确定当前所处的地理位置对应的使用场景，作为推荐场景之前，还包括：
    获取移动终端的移动速度以及运动路线；
    若所述移动速度大于预设速度，且存在与所述移动终端的运动路线相同的公共交通工具，确定所述移动终端处于常驻地点。
  8. 根据权利要求7所述的方法，其特征在于，所述确定当前所处的地理位置对应的使用场景，作为推荐场景；从所述第一词库中选择所述推荐场景相关的词条，向所述移动终端推送从所述第一词库中选择所述推荐场景相关的词条，向所述移动终端推送包括：
    确定当前所处地理位置对应的使用场景为交通场景；
    获取所述移动终端在与公共交通工具运动轨迹相同的情况下的历史操作数据，作为参考数据；
    确定所述参考数据的类型；
    从所述第一词库中选择与所述参考数据相同类型的词条，向所述移动终端推送。
  9. 根据权利要求1-5以及7任一项所述的方法，其特征在于，所述确定当前所处的地理位置对应的使用场景，作为推荐场景，包括：
    根据当前的时间以及所述移动终端在当前地理位置的历史操作数据，确定所述移动终端当前的使用场景，作为推荐场景。
  10. 根据权利要求1所述的方法，其特征在于，所述从所述第一词库中选择所述推荐场景相关的词条，向所述移动终端推送，包括：
    接收移动终端发送的搜索关键词；
    从选择的词条中查找与所述搜索关键词相关联的词条，向所述移动终端推送。
  11. 根据权利要求1-10任一项所述的方法，其特征在于，所述根据待推送的移动终端的用户画像，从基础推送词库中选择对应所述用户画像的词条建立第一词库之前，还包括：
    基于所述移动终端对应的用户基本信息，建立所述用户画像。
  12. 根据权利要求11所述的方法，其特征在于，所述方法还包括：
    获取在所述移动终端中登录不同应用程序的各个用户帐号；
    获取各个用户帐号在应用程序中公开的基本信息，作为所述移动终端对应的用户基本信息。
  13. 根据权利要求1-12任一项所述的方法，其特征在于，所述根据待推送的移动终端的用户画像，从基础推送词库中选择与所述用户画像相关的词条建立第一词库之前，还包括：
    从多个指定的网络平台中抓取词条，建立所述基础推送词库。
  14. 根据权利要求13所述的方法，其特征在于，所述从多个指定的网络平台中抓取词条，建立所述基础推送词库，包括
    从多个指定的网络平台中搜索点击率超过预设值的内容；
    从搜索到的内容中提取关键词条；
    通过提取的关键词条建立所述基础推送词库。
  15. 根据权利要求1-14任一项所述的方法，其特征在于，所述方法还包括：
    接收后台输入的词条；
    将所述后台输入的词条添加到所述基础推送词库。
  16. 一种词条推送装置，其特征在于，所述装置包括：
    词库建立模块，用于根据待推送的移动终端的用户画像，从基础推送词库中选择与所述用户画像相关的词条建立第一词库；
    场景确定模块，用于若所述移动终端当前所处的地理位置为常驻地点，确定当前所处的地理位置对应的使用场景，作为推荐场景；
    推送模块，用于从所述第一词库中选择所述推荐场景相关的词条，向所述 移动终端推送。
  17. 根据权利要求16所述的装置，其特征在于，所述装置还包括常驻地点确定模块，所述常驻地点确定模块包括：
    列表获取单元，用于获取常驻地点列表，所述常驻地点列表根据所述移动终端的历史运动轨迹建立；
    位置获取单元，用于获取所述移动终端当前所处的地理位置；
    判断单元，用于判断当前所处的地理位置是否为所述常驻地点列表中的地理位置；
    确定单元，用于若当前所处的地理位置为所述常驻地点列表中的地理位置，确定所述移动终端处于常驻地点。
  18. 根据权利要求16或17所述的装置，其特征在于，所述场景确定模块用于：根据移动终端在常驻地点列表中每个地理位置的历史操作数据，确定所述常驻地点列表中每个地理位置对应的使用场景；根据所述常驻地点列表中每个地理位置对应的使用场景，确定移动终端当前的地理位置对应的使用场景，作为推荐场景。
  19. 一种电子设备，其特征在于，包括：
    一个或多个处理器；
    存储器；
    一个或多个程序，其中所述一个或多个程序被存储在所述存储器中并被配置为由所述一个或多个处理器执行，所述一个或多个程序配置用于执行如权利要求1-15任一项所述的方法。
  20. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有程序代码，所述程序代码可被处理器调用执行如权利要求1-15任一项所述的方法。
PCT/CN2019/112845 2019-10-23 2019-10-23 词条推送方法、装置、电子设备及存储介质 WO2021077340A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201980099225.8A CN114223011A (zh) 2019-10-23 2019-10-23 词条推送方法、装置、电子设备及存储介质
PCT/CN2019/112845 WO2021077340A1 (zh) 2019-10-23 2019-10-23 词条推送方法、装置、电子设备及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/112845 WO2021077340A1 (zh) 2019-10-23 2019-10-23 词条推送方法、装置、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2021077340A1 true WO2021077340A1 (zh) 2021-04-29

Family

ID=75619580

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/112845 WO2021077340A1 (zh) 2019-10-23 2019-10-23 词条推送方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN114223011A (zh)
WO (1) WO2021077340A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050240943A1 (en) * 2001-07-10 2005-10-27 Microsoft Corporation Application program interface for network software platform
CN106326338A (zh) * 2016-08-03 2017-01-11 北京百度网讯科技有限公司 基于搜索引擎的服务提供方法和装置
CN107203894A (zh) * 2016-03-18 2017-09-26 百度在线网络技术（北京）有限公司 信息推送方法和装置
CN107862027A (zh) * 2017-10-31 2018-03-30 北京小度信息科技有限公司 检索意图识别方法、装置、电子设备及可读存储介质

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105354196B (zh) * 2014-08-19 2019-06-21 北京羽扇智信息科技有限公司 信息推送方法和信息推送装置
CN105142104A (zh) * 2015-06-19 2015-12-09 北京奇虎科技有限公司 提供推荐信息的方法、设备以及系统
CN107515890A (zh) * 2017-07-04 2017-12-26 深圳市金立通信设备有限公司 一种识别常驻点的方法及终端
CN107784092A (zh) * 2017-10-11 2018-03-09 深圳市金立通信设备有限公司 一种推荐热词的方法、服务器及计算机可读介质
CN107885346A (zh) * 2017-10-25 2018-04-06 努比亚技术有限公司 一种候选词推荐方法、终端及计算机可读存储介质
CN108011928A (zh) * 2017-11-10 2018-05-08 深圳市金立通信设备有限公司 一种信息推送方法、终端设备及计算机可读介质
CN109299367A (zh) * 2018-09-28 2019-02-01 中国平安财产保险股份有限公司 信息推送方法、装置、计算机设备及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050240943A1 (en) * 2001-07-10 2005-10-27 Microsoft Corporation Application program interface for network software platform
CN107203894A (zh) * 2016-03-18 2017-09-26 百度在线网络技术（北京）有限公司 信息推送方法和装置
CN106326338A (zh) * 2016-08-03 2017-01-11 北京百度网讯科技有限公司 基于搜索引擎的服务提供方法和装置
CN107862027A (zh) * 2017-10-31 2018-03-30 北京小度信息科技有限公司 检索意图识别方法、装置、电子设备及可读存储介质

Also Published As

Publication number Publication date
CN114223011A (zh) 2022-03-22

Similar Documents

Publication Publication Date Title
US10706094B2 (en) System and method for customizing a display of a user device based on multimedia content element signatures
US11870864B2 (en) System and method for automatic storyline construction based on determined breaking news
EP3779841B1 (en) Method, apparatus and system for sending information, and computer-readable storage medium
US10402703B2 (en) Training image-recognition systems using a joint embedding model on online social networks
US10484329B2 (en) Computerized notification system and method for delivering breaking news content
US20230306052A1 (en) Method and system for entity extraction and disambiguation
US20180101540A1 (en) Diversifying Media Search Results on Online Social Networks
CN110475155B (zh) 直播视频热度状态识别方法、装置、设备及可读介质
US20150293897A1 (en) Automatically coding fact check results in a web page
CN110334289B (zh) 出行目的地的确定方法和目标用户的确定方法
US20100030648A1 (en) Social media driven advertisement targeting
US20170097984A1 (en) Method and system for generating a knowledge representation
US11080287B2 (en) Methods, systems and techniques for ranking blended content retrieved from multiple disparate content sources
KR20140026305A (ko) 친구 추천 방법 및 이를 위한 서버 및 단말
TW201543238A (zh) 使用者會話之使用者滿意度評估方法與系統
US20130238390A1 (en) Informing sales strategies using social network event detection-based analytics
US11899728B2 (en) Methods, systems and techniques for ranking personalized and generic search query suggestions
CN110035302B (zh) 信息推荐及模型训练方法和装置、计算设备、存储介质
US20150112962A1 (en) System and method for launching applications on a user device based on the user intent
US11232522B2 (en) Methods, systems and techniques for blending online content from multiple disparate content sources including a personal content source or a semi-personal content source
US11558324B2 (en) Method and system for dynamically generating a card
CN111597446B (zh) 基于人工智能的内容推送方法、装置、服务器和存储介质
KR20140027011A (ko) 친구 추천 방법 및 이를 위한 서버 및 단말
CN109101505A (zh) 一种推荐方法、推荐装置和用于推荐的装置
WO2017062256A1 (en) Method and system for generating a card based on intent

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19949759

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19949759

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 10.10.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19949759

Country of ref document: EP

Kind code of ref document: A1