WO2019158068A1 - 聚集店铺信息的推送方法及装置 - Google Patents

聚集店铺信息的推送方法及装置 Download PDF

Info

Publication number
WO2019158068A1
WO2019158068A1 PCT/CN2019/074925 CN2019074925W WO2019158068A1 WO 2019158068 A1 WO2019158068 A1 WO 2019158068A1 CN 2019074925 W CN2019074925 W CN 2019074925W WO 2019158068 A1 WO2019158068 A1 WO 2019158068A1
Authority
WO
WIPO (PCT)
Prior art keywords
push
information
area
store
preset
Prior art date
Application number
PCT/CN2019/074925
Other languages
English (en)
French (fr)
Inventor
黄瑞
沈丹
李素凌
Original Assignee
口口相传(北京)网络技术有限公司
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 口口相传(北京)网络技术有限公司 filed Critical 口口相传(北京)网络技术有限公司
Publication of WO2019158068A1 publication Critical patent/WO2019158068A1/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
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • 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
    • 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

  • the present disclosure relates to the field of electronic information, and in particular to a method and apparatus for pushing aggregated store information.
  • O2O Online To Offline
  • online offline/online to offline technology has developed rapidly, and this technology can perfectly combine online and offline.
  • the O2O platform can help users make decisions in advance (such as which store to go to, etc.), users can refer to multiple push stores pushed to the user terminal to make decisions. Therefore, pushing a reasonable push store to the user terminal is beneficial to enhance the user experience and increase User adhesion of the platform.
  • the online search for multiple stores of the same type or query multiple stores in the nearby area for comparison in this case, it is necessary to determine that multiple push stores are pushed to the user terminal. .
  • the inventors have found that the above-mentioned manner in the prior art has at least the following problem: in the above scenario, if the number of push shops pushed to the user terminal is small, or the geographic location corresponding to the store is pushed The information does not have a certain relevance. For example, if the distance is far away, the information available for the user is less referenced or the push shop does not have a reference value for the user, and the user's demand is often not satisfied, thereby reducing the user experience. In summary, there is no technical solution in the prior art that can solve the above problems well.
  • the present disclosure has been made in order to provide a method and apparatus for pushing aggregated store information that overcomes the above problems or at least partially solves the above problems.
  • a method for pushing aggregate store information including: acquiring geographic location information of each push store, determining an information aggregation area including a plurality of push stores according to the geographic location information; and determining that the information aggregation area includes Whether each of the push shops satisfies the preset aggregate push condition; if so, the aggregate store information is generated based on each push store included in the information aggregation area, and the aggregate store information is pushed to the user terminal.
  • a push device for collecting store information including: a geographic location information acquisition module, configured to acquire geographic location information of each push store; and an information aggregation region determining module, adapted to determine according to the geographic location information
  • the information gathering area includes a plurality of push shops; the determining module is adapted to determine whether each push shop included in the information gathering area satisfies a preset aggregate push condition; and the pushing module is adapted to determine each push shop included in the information gathering area
  • the preset aggregate push condition is satisfied, and the aggregate store information is generated based on each push store included in the information aggregation area, and the aggregate store information is pushed to the user terminal.
  • an electronic device includes: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface complete communication with each other through a communication bus;
  • the memory is configured to store at least one executable instruction, and the executable instruction causes the processor to perform an operation corresponding to the information pushing method as described above.
  • a non-transitory computer readable storage medium having stored therein at least one executable instruction that causes a processor to execute as described above
  • the information push method corresponds to the operation.
  • a computer program product comprising a computing program stored on the non-transitory computer readable storage medium described above.
  • geographic location information of each push store is acquired, and an information aggregation area including a plurality of push stores is determined according to the geographic location information; Whether each of the push shops satisfies the preset aggregate push condition; if so, the aggregate store information is generated based on each push store included in the information aggregation area, and the aggregate store information is pushed to the user terminal.
  • the aggregated store information including the plurality of push stores can be determined according to the geographic location of the push store, and the plurality of push shops having the relevance between the geographic locations are packaged and pushed to the user terminal, thereby improving the user experience.
  • FIG. 1 is a schematic flow chart of a method for pushing aggregated store information according to Embodiment 1 of the present disclosure
  • FIG. 2 is a schematic flowchart diagram of a method for pushing aggregated store information according to Embodiment 2 of the present disclosure
  • FIG. 3 is a schematic structural diagram of a push device for collecting store information according to Embodiment 3 of the present disclosure
  • FIG. 4 is a schematic structural diagram of an electronic device according to Embodiment 5 of the present disclosure.
  • FIG. 1 is a schematic flowchart diagram of a method for pushing aggregated store information according to Embodiment 1 of the present disclosure. As shown in Figure 1, the method includes:
  • Step S110 Acquire geographical location information of each push shop, and determine an information aggregation area including a plurality of push stores according to the geographical location information.
  • the push store can be further divided into a variety of store types, such as the type of restaurant, the type of clothing store, the type of cinema store, the type of early education store, and the like.
  • a restaurant-type push store for example, when a user downloads a store online, he or she wants to find a plurality of shops of the same type or a plurality of stores that are not far apart, and if the number of push shops pushed to the user terminal is small, or The geographical location information corresponding to the push shop does not have a certain relevance. If the distance is far away, the information available for the user is less or the push shop does not have reference value for the user, and the user's demand cannot be satisfied, thereby reducing the user.
  • a plurality of push shops with geographical location information close to each other can be packaged and pushed to the user terminal.
  • the information gathering area is determined according to the geographic location information of each push store, and the geographic location information of the push store may be latitude and longitude information or location information determined according to the map data.
  • each push store may be of the same type or different.
  • the type of the present disclosure is not limited thereto, and those skilled in the art can set according to actual needs.
  • the area shape, the area of the area, and the like of the information gathering area can be determined according to the distribution of the geographical position information of the plurality of push shops. In short, it is necessary to include as many push shops as possible in the information gathering area.
  • a maximum area area threshold and/or a minimum area area threshold of the information aggregation area are preset, and when the information aggregation area is determined according to the geographic location information of the plurality of push stores, the area of the information aggregation area may not be larger than the maximum area.
  • the area threshold, the minimum cannot be less than the minimum area area threshold.
  • Step S120 It is determined whether each of the push stores included in the information aggregation area satisfies the preset aggregate push condition.
  • the method of the embodiment needs to determine whether each push shop in the information aggregation area satisfies the push condition, for example, calculating every two items included in the information aggregation area according to the third-party map data.
  • the walking distance between the push shops determines whether the walking distance between each two push messages is less than a preset distance threshold.
  • Step S130 If it is determined that each push store included in the information aggregation area satisfies the preset aggregate push condition, the aggregate store information is generated according to each push store included in the information aggregation area, and the aggregate store information is pushed to the user terminal.
  • the walking distance between each two push shops included in the information gathering area and/or the corresponding walking time may be calculated according to the third-party map data, and then the walking distance between each two pushing stores is determined to be less than Predetermining the distance threshold, and/or determining whether the corresponding walking time between each two push stores is less than a preset time threshold, and if so, determining that each push store included in the information gathering area satisfies the preset aggregate push condition.
  • the geographical location information of each push store is acquired, and the information aggregation area including the plurality of push stores is determined according to the geographical location information; and whether each push store included in the information aggregation area is satisfied is satisfied.
  • the aggregated push condition is preset; if so, the aggregated store information is generated based on each push store included in the information gathering area, and the aggregated store information is pushed to the user terminal.
  • the aggregated store information including the plurality of push stores can be determined according to the geographic location of the push store, and the plurality of push shops having the relevance between the geographic locations are packaged and pushed to the user terminal to improve the user experience.
  • FIG. 2 is a schematic flowchart diagram of a method for pushing aggregated store information according to Embodiment 2 of the present disclosure. As shown in Figure 2, the method includes:
  • Step S210 Acquire geographical location information of each push shop separately.
  • the information pushing method in this embodiment can be applied to a scenario in which a plurality of information is pushed. Specifically, before the execution of this step, a plurality of push stores need to be determined in advance.
  • the following is an example of an APP that can provide users with various types of shop inquiry services as an example to determine how to implement multiple push stores:
  • the actual scores of the respective candidate stores are determined according to the normalized scores, the type preference scores, and/or the push balance scores of the respective candidate stores; and the plurality of push stores are selected from the respective candidate stores according to the actual scores of the respective candidate stores.
  • the normalization score is determined according to a preset normalization processing rule, and the type preference score is determined according to the period information and/or the location information, and the push balance score is determined according to the preset type push ratio.
  • the candidate store in this embodiment may be an isolated store, or may be a store located inside a large commercial circle.
  • the candidate store may be a restaurant of a catering type, a store of an early education type, or a store of a clothing department store type, which is not limited in the present disclosure.
  • the original score of the candidate store is determined according to a type scoring rule corresponding to the type of the candidate store.
  • the type of the candidate store includes a catering type, an early education type, a clothing type, and the like, and the specific application scenario of the push service is not limited by the disclosure, and can be set by a person skilled in the art according to actual needs.
  • the original score of the candidate store is determined according to a type scoring rule corresponding to the type of the candidate store, wherein the type scoring rules corresponding to the respective types of candidate stores are different, and the original score of each candidate store may be based on the user
  • the scores of the candidate stores are determined according to the corresponding type of scoring rules. For example, in a specific application, a recommendation model corresponding to different store types is constructed, and the user can score for each candidate store, and a large number of candidate stores are acquired.
  • the score data is input to the recommendation model corresponding to the corresponding store type by the score data of the candidate store to calculate the original score of the candidate store.
  • the total score interval is divided into a plurality of sub-intervals in advance, a sub-interval corresponding to the original score of the candidate store is determined, and the original score of the candidate store is normalized according to the score density of the sub-interval, and the candidate is obtained.
  • the normalized score of the store wherein the score density of each sub-interval is determined according to the number of candidate stores whose original score is located in the sub-interval and the total number of candidate stores.
  • the distribution interval of the original scores of each candidate store of the catering type is 0-0.3, and the original The scores are concentrated around 0.29.
  • the distribution range of the original scores of each candidate store of the early education type is 0.6-1, and the original score is concentrated around 0.7. Therefore, it is unreasonable to directly sort the candidate stores according to the original score.
  • This step normalizes the original scores of different types of candidate stores, and the obtained normalized scores are directly comparable, and the normalized scores of the candidate stores are evenly distributed within the score interval, in addition, the original score After normalization, there is order preservation.
  • the total score interval is divided into a plurality of sub-intervals, and the lengths of the plurality of sub-intervals may be divided according to the distribution of the original scores in the total score interval, or the length of the sub-intervals may be preset according to the length of the total score interval, for example, If the total score interval is 0-100, the length of the sub-interval can be set to 20, and the multiple sub-intervals are 0-20, 20-40, respectively. Of course, the total score interval and the sub-interval can be divided according to the actual situation. The setting is required, and the disclosure does not limit this.
  • determining a sub-interval corresponding to the original score of the candidate store and normalizing the original score of the candidate store according to the score density of the sub-interval, wherein the score density of each sub-interval is located in the sub-score according to the original score
  • the number of candidate stores in the interval and the total number of candidate stores included in the total score interval that is, the distribution rule of the original scores of each candidate store included in the type corresponding to the candidate store, such as the distribution interval range, density, etc.
  • the original score of the candidate store is normalized in accordance with the distribution law.
  • determining time period information corresponding to the current time determining a first preference score of the information type corresponding to the candidate store according to the time period information; and/or determining location information corresponding to the current location, determining according to the location information a second preference score of the information type corresponding to the candidate store; determining a type preference score of the type corresponding to the candidate store according to the first preference score and/or the second preference score.
  • the first preference score and/or the second preference score of the type corresponding to the candidate store are determined by analyzing current behavior data and/or historical behavior data of the user terminal.
  • the first preference score and the second preference score are determined according to the behavior data of the user terminal, that is, according to the behavior data of the user using the APP, and may indicate that the user is interested in the type of information corresponding to the candidate store.
  • the degree (degree of preference) in a colloquial manner, is to predict the degree of preference of the user for the type of the candidate store, and determine the first preference score and/or the second preference score to indicate the degree of preference.
  • the first preference score and the second preference score are determined according to the historical behavior data of the user terminal and the current behavior data of the user terminal. It should be noted that the disclosure determines the first preference score and the second preference score. The method is not limited.
  • the 24 hours a day can be divided into a plurality of time periods, for example, according to the peak of the work, the peak of the work, the meal time, and the like, which is not limited in the present disclosure.
  • the historical behavior data of a large number of user terminals is obtained, and which types of candidate stores that the user prefers to click on the APP in each time period can be analyzed, and the model is constructed according to the historical behavior data of the user terminal, and the majority of users can be predicted at the corresponding time.
  • this step predicts user preferences based on big data and time period information.
  • the foregoing prediction result is further corrected according to the historical behavior data of the user terminal and the current behavior data, and the historical behavior data of the user terminal itself is more representative of the behavior habit of the user using the APP, for example, on Monday. Up to 12 noon to 13:00 every Friday, I prefer to click on the candidate store of the catering type.
  • the candidate store that the user prefers the catering type at the current time can be predicted according to the above data, and correspondingly, the first preference score of the information type corresponding to each candidate store can be further determined.
  • the method fully combines the big data with the user's own behavior data to determine the first preference score of the type corresponding to the candidate store, so that the prediction result is more accurate and more suitable for the user's needs.
  • the second preference score is determined according to the location information.
  • the location information may be divided according to the business circle, the office building, the residential community, and the like, and the disclosure does not limit the disclosure, for example, a certain shopping mall and its surrounding area. The area is divided into a business district.
  • Types of candidate stores for example, when the user is located in a certain business circle, prefer to click on the candidate store of the clothing type, and build a model according to the historical behavior data of the user terminal, which can predict the preference of various information types when the majority of users are in certain positions.
  • this step is to predict user preferences based on big data and location information.
  • the foregoing prediction result is further corrected according to the historical behavior data of the user terminal and the current behavior data, and the historical behavior data of the user terminal itself is more representative of the behavior habit of the user using the APP, for example, the user terminal.
  • the location information is a candidate store that prefers to click the clothing type when the business circle is used.
  • the current behavior data of the user terminal is used in combination, for example, the user terminal currently clicks on the candidate store of the clothing type, and the current location information is the
  • the business circle can predict the current location that the user prefers the candidate store of the clothing type according to the above information, and correspondingly, the second preference score of the information type corresponding to each candidate store can be further determined.
  • the method fully combines the big data with the user's own data to determine the second preference score of the information type corresponding to the candidate store, so that the prediction result is more accurate and more suitable for the user's needs.
  • a preset type push ratio corresponding to the type is set for each type of store included in the diversified information. Obtaining the actual type push ratio of the type corresponding to the candidate store, and obtaining a push balance score of the candidate store of the type according to the difference between the preset type push ratio and the actual type push ratio of the type corresponding to the candidate store.
  • Equilibrium push is to ensure that each type of information has a certain push probability, preventing the formation of the Matthew effect, that is, the push rate of the candidate shop corresponding to the information type with a large actual push ratio is larger and larger, and the actual type push ratio is higher.
  • the push chances of candidate stores corresponding to small information types are getting smaller and smaller, resulting in push imbalance.
  • the push balance ratio is calculated according to the actual type push ratio and the preset type push ratio, and the push ratio of the candidate stores is adjusted to ensure that each candidate store corresponding to each type is balancedly pushed.
  • the push balance score can be calculated according to the following formula:
  • PV is the push balance score
  • tanh() is the hyperbolic tangent function
  • PVp is the preset type push ratio
  • PVh is the actual type push ratio
  • ieri is the sensitivity coefficient. In specific applications, it can be set to an integer, indicating when the actual type is pushed. When the ratio deviates from the preset type push ratio, the sensitivity of the attenuation of the push balance score is increased. The larger the value of réelle, the greater the degree of attenuation, and those skilled in the art can set according to actual needs.
  • the exposure equalization score is 0.5; the smaller the difference between the preset type push ratio and the actual type push ratio is, the larger the push balance score is; the preset type The greater the difference between the push ratio and the actual type push ratio, the smaller the push balance score.
  • the normalized score, the type preference score, and the weighted value corresponding to the push balance score are respectively determined, and the normalized score, the type preference score, and the push balance score are weighted according to each weight value to obtain an actual score of the candidate store.
  • the normalized score, the type preference score, and the push balance score of each candidate store are determined according to the above steps.
  • the weight values corresponding to the above three scores are set in advance, and the normalized score, the type preference score, and the score are calculated. Push the weighted sum of the equalization scores to get the actual score of the candidate store.
  • the above method for calculating the actual score of the candidate store is applicable to each candidate store corresponding to each type of information included in the diversified information, and can directly select each candidate corresponding to the different information type according to the obtained actual score.
  • the store performs a mixed sorting, and combines the data of the three dimensions to determine the actual scores of the candidate stores, so that the actual scores of the candidate stores of different information types are directly comparable.
  • the geographic location information of the push store may be latitude and longitude information or location information determined according to the map data, which is not limited by the disclosure.
  • Step S220 Calculate the distribution density of the push shop included in each area, and determine the area with the distribution density greater than the preset density threshold as the information aggregation area; wherein the area and/or the division mode of each area can be divided according to the preset area.
  • the rules are dynamically adjusted.
  • the information gathering area is determined according to the geographical location information of the push shop, and the area shape and the area of the information gathering area can be determined according to the distribution of the geographic location information of the plurality of push stores.
  • the information gathering area needs to be Includes as many push stores as possible.
  • the distribution density may be calculated according to the total number of push shops included in each area and the area of the corresponding area, and the area where the distribution density is greater than the preset density threshold is determined as the information aggregation area, and thus, in practical applications, An area may be roughly planned in advance, and then the distribution density of the push shop included in the area may be calculated, and the area range or the area of the information gathering area may be adjusted according to the distribution density and the preset density threshold, so that the final information gathering area is pushed into the shop.
  • the distribution density is greater than or equal to the preset density threshold.
  • Each area may be divided according to the characteristics of the area, for example, according to regional characteristics such as shopping malls, office buildings, shopping streets, food streets, residential areas, etc., or may be adjusted in real time according to actual conditions, for example, according to the location information of the user terminal. This disclosure does not limit this.
  • Step S230 It is determined whether each of the push shops included in the information aggregation area satisfies the preset aggregate push condition.
  • each push shop included in the information aggregation area satisfies a preset aggregate push condition according to the area radius of the information gathering area and/or the distance between each two push shops included in the information gathering area.
  • the distance between each two push shops included in the information gathering area specifically includes: a walking distance between each two push shops included in the information gathering area; and the walking distance is according to the bridge across the river included in the map. Overpasses, viaducts, and/or overpasses are determined.
  • the radius of the information gathering area it is determined whether the radius of the information gathering area is smaller than a preset radius threshold. If yes, each push shop included in the information gathering area satisfies a preset aggregate pushing condition. In general, if the radius of the aggregation area is smaller than the radius threshold, it indicates that the area of the information aggregation area is not large, and it is convenient for the user to reach the geographical location information corresponding to any one of the push stores.
  • the walking distance between each two push shops included in the information gathering area and/or the corresponding walking time may be calculated according to the third-party map data, and it is determined whether the walking distance between each two pushing stores is less than The distance threshold is set, or it is determined whether the corresponding walking time between each two push shops is less than a preset time threshold, and if so, it is determined that each push shop included in the information gathering area satisfies the preset aggregate push condition.
  • Step S240 If yes, package each push store included in the information gathering area into a gathered store information, and name the aggregated store information according to a preset naming rule; wherein the preset naming rules include: naming according to the place name and/or the building The aggregate store information is pushed to the user terminal.
  • each push store included in the information gathering area is packaged into a gathered store information, and the aggregated store information is named so that the user can directly recognize the In the area where the store is located, the name of the aggregated store information may be determined according to the name of the landmark building, and may be determined according to representative place names and/or building names in the information gathering area, for example, the name of the shopping mall, the name of the residential area, and the building The name, the landmark building name, and the like, and the named aggregate store information is pushed to the user terminal.
  • Step S250 If no, determine whether the information aggregation area satisfies the preset adjustment condition, and adjust the area range of the information aggregation area according to the preset adjustment condition when the content is satisfied, so that the adjusted information aggregation area satisfies the preset aggregation push condition. .
  • each of the push shops included in the information aggregation area does not satisfy the preset aggregation push condition, it is determined whether the information aggregation area satisfies the preset adjustment condition, and specifically, whether the information aggregation area is satisfied according to the area range and the area radius of the information aggregation area If the information aggregation area satisfies the preset adjustment condition, the area of the information aggregation area is adjusted, and the area of the information aggregation area may be expanded or reduced, that is, the information aggregation area is included. A plurality of push shops are provided, or push shops that do not satisfy the preset aggregate push conditions in the information aggregation area are removed until the respective push stores included in the adjusted information aggregation area satisfy the preset aggregate push conditions.
  • Step S260 Generate aggregate store information based on each push store included in the adjusted information gathering area, and push the aggregate store information to the user terminal.
  • the aggregated store information is named so that the user can directly recognize the area where the push store is located, and push the named aggregate store information to the user terminal.
  • the user terminal determines, according to the acquired user attribute information of the user terminal, the display status of each function portal corresponding to each type of push store according to a preset display rule.
  • Each type of push shop has multiple functions.
  • it is necessary to display corresponding function entries for example, for the shop type push message, with comments, reservations, orders, pay orders, and the like.
  • the function entry corresponding to the function, for the push message of the product type the function entry with the functions of commenting, viewing the product details, purchasing immediately, adding the shopping cart, etc., it is necessary to determine the display status of each function entry, so as to display each according to the display status.
  • Function entry For another example, in some cases, some of the function portals of a push shop need not be displayed.
  • there are functions such as reservation, order, pay, coupon, etc., when the user has arrived at the store.
  • the method determines the display status of each function portal corresponding to each type of push shop according to the preset display rule according to the acquired user attribute information of the user terminal.
  • the display status of the function portal includes: a hidden state, a visible state, a clickable state, a non-clickable state, a highlighted state, and/or a display order.
  • the user attribute information includes at least one of the following: current location data of the user terminal, current behavior data of the user terminal, and current time data.
  • the preset display rule includes at least one of the following:
  • Rule 1 Determine the location of the information corresponding to the push shop, and determine the display status of each function entry according to the distance between the current location data of the user terminal and the information location.
  • the current location data of the user terminal is obtained, the relationship between the location data corresponding to the push store and the current location data of the user terminal is determined, and the display state of each function portal corresponding to the push store is determined according to the relationship, and the above example is used.
  • the push store can be determined.
  • the corresponding reservation function entry and the coupon function entry are in a visible state or a clickable state or a highlighted state to indicate that the current user terminal can perform an operation of making a reservation and collecting a coupon; in addition, an order corresponding to the push store can be determined.
  • the function entry, the pay-to-function entry is a hidden state or a non-clickable state to indicate that the current user terminal cannot perform the operation of placing an order and paying the bill.
  • Rule 2 Determine the association relationship between each function entry corresponding to the push shop and the user behavior, and determine the display status of each function entry according to the association relationship and the current behavior data of the user terminal.
  • the relationship between each function entry and user behavior determines the display status of each function entry according to the association relationship and the current behavior data of the user terminal. For example, for a push message of a store type, corresponding to a plurality of function entries such as a reservation, a coupon, a spike, an order, a pay, and the like, and determining, according to current behavior data of the user terminal, that the user terminal currently performs an order operation, the When the reservation function entry of the push shop is not required to be displayed, it is necessary to display the function entry of the purchase order corresponding to the push shop for the user to operate.
  • Rule 3 Determine the information time corresponding to the push shop, and determine the display status of each function entry according to the interval between the current time data and the information time.
  • the rule determines the display status of each function entry based on the interval between the current time data and the information time corresponding to the push shop. For example, for a shop type push shop, the shop is open from 9:00 to 11:00 pm. The current time data corresponding to the user terminal is 9:00 in the morning. At this time, the user terminal can perform the operation of reservation and receiving the coupon, and then it can be determined that the display state of the function portal is set to the visible state or the clickable state, and the user terminal at this time If the order cannot be executed and the operation of the buy order is executed, the function entry corresponding to the order and the pay order is set to a hidden state or a non-clickable state.
  • the preset display rule is implemented by a preset prediction model; wherein the prediction model is trained according to the historical behavior data of the user terminal; the historical behavior data includes: comment data, reservation behavior data, and/or receiving preferential behavior data.
  • the historical behavior data of the user terminal can indicate the behavior habit of the user, construct a prediction model according to the historical behavior data of the user terminal, and use the prediction model to predict the current user's needs, that is, what function the current user needs to use, and further determine the corresponding function entry. Display status. For example, determining, according to the comment data of the user terminal, performing an operation of viewing a comment for the push shop user preference; or determining an operation for performing a reservation for the push shop user preference according to the reservation behavior data of the user terminal; or receiving the preferential behavior data according to the user terminal It is determined that the operation of collecting the coupon is performed for the push shop user preference. Then, the prediction model can be constructed according to the historical behavior data of the various user terminals, and the prediction model can be used to determine the display state of each function portal of the push message, thereby being more user-friendly and more user-friendly and intelligent.
  • the user terminal After determining the display status of each function entry corresponding to each type of push shop, the user terminal displays each function entry according to the display status, so that the user operates according to each function entry.
  • the display status of the function entry may indicate whether the function can be executed. For example, the visible status and the clickable status indicate that the corresponding function can be executed, the hidden status indicates that the function entry is not displayed, and the non-clickable status indicates that the function cannot be executed.
  • the function entry indicating that the status is the highlighted state may be a function entry corresponding to the function most needed by the current user predicted according to the historical behavior data; the display order may be determined according to the relationship between the functions, for example, for the shop type
  • the push function, the display order of the function entry is: spike, reservation, domain coupon, order, pay, and the order of presentation can be adjusted in real time according to the behavior data of the user terminal.
  • the geographic location information of each push store is obtained; the distribution density of the push store included in each area is calculated, and the area whose distribution density is greater than the preset density threshold is determined as information aggregation.
  • each area can be dynamically adjusted according to a preset area division rule; determining whether each push shop included in the information aggregation area satisfies a preset aggregation push condition; if yes, the information is gathered in the area
  • Each of the included push shops is packaged into an aggregated store information, and the aggregated store information is named according to a preset naming rule; wherein the preset naming rules include: pushing the aggregated store information to the user terminal according to the place name and/or the building naming; If not, it is determined whether the information aggregation area satisfies the preset adjustment condition, and when the content is satisfied, the area of the information aggregation area is adjusted according to the preset adjustment condition, so that the adjusted information aggregation area satisfies the preset aggregation push condition; Information gathering area Contained within the respective push store store information generating aggregate, the aggregate store information pushed to the user terminal.
  • the method can determine the aggregated store information including the plurality of push stores according to the geographic location of the push store, thereby packaging and pushing the plurality of push stores having the relevance of the geographic location to the user terminal to improve the user experience;
  • a plurality of push shops are determined in combination with factors such as transportation facilities and natural environment, so that the positions corresponding to each of the two push stores can be directly reached, and for the user, it is convenient for the user to reach the corresponding position of any push shop, saving The user's visit time; finally, the information gathering area can be adjusted according to the geographical location information of the push shop, so that the push shop pushed to the user terminal is the most reasonable and optimal.
  • step S220 and its steps can perform the step of pushing and pushing in step S220 and its steps for multiple types of push stores at the same time, so that the user can obtain multiple types together. And close to the push shop to meet the diverse needs.
  • the package push mode in step S220 and its steps may be performed separately for each type of push shop, so that the user can acquire the package push information of the shop of the type most interesting to the user.
  • the type of store that is packaged and pushed in step S220 and its steps may be determined in conjunction with the push balance score and/or type preference score for each type of store.
  • the type preference score of the store of the early education type is determined to be the highest according to the time and/or location of the user using the APP, and accordingly, the shop of the early education type is packaged and pushed in step S220 and its steps.
  • FIG. 3 is a schematic structural diagram of a push device for collecting store information according to Embodiment 3 of the present disclosure, the device includes:
  • the geographic location information obtaining module 31 is adapted to obtain geographic location information of each push store
  • the information aggregation area determining module 32 is adapted to determine an information aggregation area including a plurality of push stores according to the geographical location information;
  • the determining module 33 is adapted to determine whether each push shop included in the information gathering area satisfies a preset aggregate push condition
  • the push module 34 is adapted to, if it is determined that each of the push stores included in the information aggregation area satisfies the preset aggregate push condition, generate aggregate store information based on each push store included in the information aggregation area, and push the aggregate store information to the user terminal.
  • the information aggregation area determining module 32 is further adapted to:
  • the area and/or the division manner of each area can be dynamically adjusted according to the preset area division rule.
  • the determining module 33 is further adapted to:
  • the foregoing apparatus further includes:
  • the adjustment module 35 is adapted to determine whether the information aggregation area satisfies the preset adjustment condition when each push shop included in the information aggregation area does not satisfy the preset aggregation push condition, and gather information according to the preset adjustment condition when satisfied The area of the area is adjusted so that the adjusted information gathering area satisfies the preset aggregate push condition;
  • the push module 34 is further adapted to: generate aggregate store information based on each push store included in the adjusted information gathering area, and push the aggregate store information to the user terminal.
  • the distance between each two push stores included in the information gathering area specifically includes: a walking distance between each two push shops included in the information gathering area;
  • the walking distance is determined based on the cross-river bridges, overpasses, viaducts, and/or overpasses included in the map.
  • the geographic location information obtaining module 31 is further adapted to: respectively obtain geographic location information of each push store included in each information type.
  • the pushing module 34 is further configured to: package each push store included in the information gathering area into an aggregated store information, and name the aggregated store information according to a preset naming rule;
  • the preset naming rules include: naming according to place names and/or buildings.
  • the apparatus further includes: a push store determining module, configured to determine an actual score of each candidate store according to a normalized score, a type preference score, and/or a push balance score of each candidate store; according to an actual score of each candidate store Selecting a plurality of push stores from each of the candidate stores; wherein the normalized score is determined according to a preset normalization processing rule, the type preference score is determined according to the time period information and/or the location information, and the push balance score is pushed according to the preset type The ratio is determined.
  • a push store determining module configured to determine an actual score of each candidate store according to a normalized score, a type preference score, and/or a push balance score of each candidate store; according to an actual score of each candidate store Selecting a plurality of push stores from each of the candidate stores; wherein the normalized score is determined according to a preset normalization processing rule, the type preference score is determined according to the time period information and/or the location information, and the push balance score is pushed according to the preset
  • a fourth embodiment of the present application provides a non-transitory computer readable storage medium storing at least one executable instruction executable in any of the above method embodiments. Push method of gathering store information.
  • the executable instructions may specifically be used to cause the processor to perform the following operations:
  • the aggregated store information is generated based on each of the push stores included in the information aggregation area, and the aggregated store information is pushed to the user terminal.
  • FIG. 4 is a schematic structural diagram of an electronic device according to Embodiment 5 of the present disclosure, and the specific embodiment of the present disclosure does not limit the specific implementation of the electronic device.
  • the electronic device can include a processor 402, a communications interface 406, a memory 404, and a communications bus 408.
  • the processor 402, the communication interface 406, and the memory 404 complete communication with one another via the communication bus 408.
  • the communication interface 406 is configured to communicate with network elements of other devices such as clients or other servers.
  • the processor 402 is configured to execute the program 410, and specifically may perform the related steps in the foregoing embodiment of the information pushing method.
  • program 410 can include program code, the program code including computer operating instructions.
  • the processor 402 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present disclosure.
  • the one or more processors included in the electronic device may be the same type of processor, such as one or more CPUs; or may be different types of processors, such as one or more CPUs and one or more ASICs.
  • the memory 404 is configured to store the program 410.
  • Memory 404 may include high speed RAM memory and may also include non-volatile memory, such as at least one disk memory.
  • the program 410 can be specifically configured to cause the processor 402 to perform the following operations:
  • the aggregated store information is generated based on each of the push stores included in the information aggregation area, and the aggregated store information is pushed to the user terminal.
  • modules in the devices of the embodiments can be adaptively changed and placed in one or more devices different from the embodiment.
  • the modules or units or components of the embodiments may be combined into one module or unit or component, and further they may be divided into a plurality of sub-modules or sub-units or sub-components.
  • any combination of the features disclosed in the specification, including the accompanying claims, the abstract and the drawings, and any methods so disclosed, or All processes or units of the device are combined.
  • Each feature disclosed in this specification (including the accompanying claims, the abstract and the drawings) may be replaced by alternative features that provide the same, equivalent or similar purpose.
  • Various component embodiments of the present disclosure may be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof.
  • a microprocessor or digital signal processor may be used in practice to implement some or all of the functionality of some or all of the components of the information push device in accordance with embodiments of the present disclosure.
  • the present disclosure may also be implemented as a device or device program (eg, a computer program and a computer program product) for performing some or all of the methods described herein.
  • Such a program implementing the present disclosure may be stored on a computer readable medium or may be in the form of one or more signals. Such signals may be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Databases & Information Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

一种聚集店铺信息的推送方法及装置，涉及电子信息领域，该方法包括：获取各个推送店铺的地理位置信息，根据地理位置信息确定包含多个推送店铺的信息聚集区域(S110)；判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件(S120)；若判断出信息聚集区域内包含的各个推送店铺满足预设聚集推送条件，根据信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将聚集店铺信息推送给用户终端(S130)。

Description

聚集店铺信息的推送方法及装置
相关申请的交叉参考
本申请要求于2018年2月13日提交中国专利局、申请号为201810149030.7、名称为“聚集店铺信息的推送方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及电子信息领域，具体涉及一种聚集店铺信息的推送方法及装置。
背景技术
近些年，O2O，即Online To Offline(在线离线/线上到线下)技术得到了飞速发展，该技术能够把线上和线下完美结合起来。O2O平台能够帮助用户提前做决策(比如去哪家店铺消费等)，用户可参考推送至用户终端的多条推送店铺做决策，因此，向用户终端推送合理的推送店铺有利于提升用户体验，增加平台的用户粘合度。例如，在一种场景中，用户在线下店铺进行消费之前，在线上查找多家同一类的店铺或者查询附近区域内的多家店铺进行比较，此时则需要确定多条推送店铺推送给用户终端。
但是，发明人在实现本公开的过程中，发现现有技术中的上述方式至少存在如下问题：在上述场景中，若向用户终端推送的推送店铺的数量较少、或者推送店铺对应的地理位置信息不具有一定的关联性，如相距较远，导致可供用户参考的信息较少或者推送店铺对于用户来说不具有参考价值，则往往不能满足用户的需求，进而降低用户体验。综上可知，现有技术中尚没有一种能够很好地解决上述问题的技术方案。
发明内容
鉴于上述问题，提出了本公开以便提供一种克服上述问题或者至少部分地解决上述问题的一种聚集店铺信息的推送方法及装置。
根据本公开的一个方面，提供了一种聚集店铺信息的推送方法，包括：获取各个推送店铺的地理位置信息，根据地理位置信息确定包含多个推送店铺的信息聚集区域；判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件；若是，根据信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将聚集店铺信息推送给用户终端。
根据本公开的一个方面，提供了一种聚集店铺信息的推送装置，包括：地理位置信息获取模块，适于获取各个推送店铺的地理位置信息；信息聚集区域确定模块，适于根据地理位置信息确定包含多个推送店铺的信息聚集区域；判断模块，适于判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件；推送模块，适于若判断出信息聚集区域内包含的各个推送店铺满足预设聚集推送条件，根据信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将聚集店铺信息推送给用户终端。
根据本公开的再一方面，提供了一种电子设备，包括：处理器、存储器、通信接口和通信总线，处理器、存储器和通信接口通过通信总线完成相互间的通信；
存储器用于存放至少一可执行指令，可执行指令使处理器执行如上述的信息推送方法对应的操作。
根据本公开的再一方面，提供了一种非易失性计算机可读存储介质，该非易失性计算机可读存储介质中存储有至少一可执行指令，可执行指令使处理器执行如上述的信息推送方法对应的操作。
根据本公开的再又一方面，还提供了一种计算机程序产品，该计算机程序产品包括存储在上述非易失性计算机可读存储介质上的计算程序。
综上所述，在本公开提供的聚集店铺信息的推送方法及装置中，获取各个推送店铺的地理位置信息，根据地理位置信息确定包含多个推送店铺的信息聚集区域；判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件；若是，根据信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将聚集店铺信息推送给用户终端。该方式能够根据推送店铺的地理位置确定包括多条推送店铺的聚集店铺信息，从而将地理位置之间具有关联性的多条推送店铺一并打包并推送给用户终端，提升了用户体验。
上述说明仅是本公开技术方案的概述，为了能够更清楚了解本公开的技术手段，而可依照说明书的内容予以实施，并且为了让本公开的上述和其它目的、特征和优点能够更明显易懂，以下特举本公开的具体实施方式。
附图说明
通过阅读下文优选实施方式的详细描述，各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出优选实施方式的目的，而并不认为是对本公开的限制。而且在整个附图中，用相同的参考符号表示相同的部件。在附图中：
图1示出了本公开实施例一提供的一种聚集店铺信息的推送方法的流程 示意图；
图2示出了本公开实施例二提供的一种聚集店铺信息的推送方法的流程示意图；
图3示出了本公开实施例三提供的一种聚集店铺信息的推送装置的结构示意图；
图4示出了根据本公开实施例五提供的一种电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整的传达给本领域的技术人员。
实施例一
图1示出了本公开实施例一提供的一种聚集店铺信息的推送方法的流程示意图。如图1所示，该方法包括：
步骤S110：获取各个推送店铺的地理位置信息，根据地理位置信息确定包含多个推送店铺的信息聚集区域。
其中，推送店铺可进一步划分为多种店铺类型，如餐饮店铺类型、服装店铺类型、影院店铺类型、早教店铺类型等。
以餐饮类型的推送店铺为例，往往用户在线下店铺进行消费时，想要寻找多家同一类的店铺或者相距不远的多家店铺，若向用户终端推送的推送店铺的数量较少、或者推送店铺对应的地理位置信息不具有一定的关联性，如相距较远，导致可供用户参考的信息较少或者推送店铺对于用户来说不具有参考价值，则不能满足用户的需求，进而降低用户体验。基于此，在本实施例的方法中，可以将地理位置信息相距较近的多个推送店铺打包起来，一并推送给用户终端。
具体地，根据各个推送店铺的地理位置信息确定信息聚集区域，推送店铺的地理位置信息可以是经纬度信息或者根据地图数据确定的位置信息，此外，各个推送店铺可以是相同类型的，也可以是不同类型的，本公开对此不作限定，本领域技术人员可根据实际需要进行设置。信息聚集区域的区域形状、区域面积等可根据多个推送店铺的地理位置信息的分布情况进行确定，总之，需要使信息聚集区域内包含尽可能多的推送店铺。
可选地，预先设置信息聚集区域的最大区域面积阈值和/或最小区域面积阈值，在根据多个推送店铺的地理位置信息确定信息聚集区域时，信息聚集 区域的区域面积最大不能大于该最大区域面积阈值，最小不能小于该最小区域面积阈值。需要说明的是，上述确定信息聚集区域的方法仅是本公开的示例，本公开不限于此。
步骤S120：判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件。
在实际应用中，可能存在两个推送店铺的地理位置信息之间相距不远，但由于交通设施、自然环境等因素导致两者之间的通行并不便利的情况，例如，两个地理位置信息之间相隔一定宽度的河流、或者两者分别位于高架桥的两头、或者两者之间的道路正在进行施工无法通过。因此，为了避免上述情况，本实施例的方法在确定了信息聚集区域了之后，需要判断信息聚集区域内各个推送店铺是否满足推送条件，例如根据第三方地图数据计算信息聚集区域内包含的每两个推送店铺之间的步行距离，判断每两个推送消息之间的步行距离是否小于预设距离阈值。
步骤S130：若判断出信息聚集区域内包含的各个推送店铺满足预设聚集推送条件，根据信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将聚集店铺信息推送给用户终端。
具体地，可根据信息聚集区域内包含的每两个推送店铺之间的距离，判断每两个推送店铺之间的距离是否小于预设阈值，若是，则信息聚集区域内包含的各个推送店铺满足预设聚集推送条件。实际应用中，还可根据第三方地图数据计算信息聚集区域内包含的每两个推送店铺之间的步行距离和/或对应的步行时间，则判断每两个推送店铺之间的步行距离是否小于预设距离阈值，和/或，判断每两个推送店铺之间对应的步行时间是否小于预设时间阈值，若是，则确定信息聚集区域内包含的各个推送店铺满足预设聚集推送条件。
根据本实施例所提供的聚集店铺信息的推送方法，获取各个推送店铺的地理位置信息，根据地理位置信息确定包含多个推送店铺的信息聚集区域；判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件；若是，根据信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将聚集店铺信息推送给用户终端。该方式能够根据推送店铺的地理位置确定包括多条推送店铺的聚集店铺信息，从而将地理位置之间具有关联性的多条推送店铺一并打包并推送给用户终端，提升用户体验。
实施例二
图2示出了本公开实施例二提供的一种聚集店铺信息的推送方法的流程示意图。如图2所示，该方法包括：
步骤S210：分别获取各个推送店铺的地理位置信息。
本实施例的信息推送方法可应用于多元化信息推送的场景中，具体地，在本步骤执行之前，需要预先确定多个推送店铺。下面以能够为用户提供多种类型的店铺查询业务的APP为例说明确定多个推送店铺的实现方式：
具体地，根据各个候选店铺的归一化得分、类型偏好得分和/或推送均衡得分，确定各个候选店铺的实际得分；根据各个候选店铺的实际得分，从各个候选店铺中选择多个推送店铺。其中，上述的归一化得分根据预设的归一化处理规则确定，类型偏好得分根据时段信息和/或位置信息确定，推送均衡得分根据预设类型推送比例确定。其中，本实施例中的候选店铺可以是孤立的店铺，也可以是位于大型商圈内部的店铺。并且，候选店铺既可以是餐饮类型的店铺，也可以是早教类型的店铺，还可以是服装百货类型的店铺，本公开对此不做限定。
下面详细介绍各个推送店铺的确定方式：
首先，分别针对每个候选店铺，根据与该候选店铺的类型相对应的类型评分规则确定该候选店铺的原始得分。其中，候选店铺的类型包括餐饮类型、早教类型、服装类型等，具体取决于推送业务的具体应用场景，本公开对此不作限定，本领域技术人员可根据实际需要进行设置。
根据与该候选店铺的类型相对应的类型评分规则确定该候选店铺的原始得分，其中，各种类型的候选店铺相对应的类型评分规则各不相同，每个候选店铺的原始得分可以是根据用户对候选店铺的评分按照对应的类型评分规则进行确定的，例如，具体应用中，构建与不同的店铺类型相对应的推荐模型，并且用户可以针对各个候选店铺进行评分，则获取大量的候选店铺的评分数据，将候选店铺的评分数据输入至对应的店铺类型所对应的推荐模型进行计算得到该候选店铺的原始得分。
其次，预先将总得分区间划分为多个子区间，确定与该候选店铺的原始得分相对应的子区间，根据该子区间的得分密度对该候选店铺的原始得分进行归一化处理，得到该候选店铺的归一化得分，其中，各个子区间的得分密度根据原始得分位于该子区间内的候选店铺的数量以及候选店铺的总量确定。
上述利用推荐模型计算得到原始得分的示例中，不同类型的候选店铺的原始得分之间不具有可比性，举例来说，餐饮类型的各个候选店铺的原始得分的分布区间为0-0.3，且原始得分集中在0.29左右，早教类型的各个候选店铺的原得分的分布区间为0.6-1，且原始得分集中在0.7左右，因此，直接根据原始得分对各个候选店铺进行排序推荐是不合理的。
本步骤针对不同类型的候选店铺的原始分数进行归一化处理，得到的归一化得分具有直接可比性，并且各个候选店铺的归一化得分在得分区间内是均匀分布的，此外，原始得分进行归一化处理之后具有保序性。
具体地，首先，将总得分区间划分为多个子区间，可根据总得分区间中原始得分的分布情况划分多个子区间的长度，也可以根据总得分区间的长度预先设定子区间的长度，例如若总得分区间为0-100，则可将子区间的长度设为20，则多个子区间分别为0-20、20-40……，当然，总得分区间以及子区间的划分方式可以根据实际需要进行设定，本公开对此不作限定。然后，确定与该候选店铺的原始得分相对应的子区间，根据该子区间的得分密度对该候选店铺的原始得分进行归一化处理，其中，各个子区间的得分密度根据原始得分位于该子区间内的候选店铺的数量以及总得分区间包含的候选店铺的总量确定，也即分析该候选店铺所对应的类型中包含的各个候选店铺的原始得分的分布规律，如分布区间范围、密度等，结合分布规律对该候选店铺的原始得分进行归一化处理。
然后，确定与当前时间相对应的时段信息，根据该时段信息确定该候选店铺所对应的信息类型的第一偏好分值；和/或确定与当前位置相对应的位置信息，根据该位置信息确定该候选店铺所对应的信息类型的第二偏好分值；根据第一偏好分值和/或第二偏好分值确定该候选店铺所对应的类型的类型偏好得分。
具体地，通过分析用户终端的当前行为数据和/或历史行为数据，确定该候选店铺所对应的类型的第一偏好分值和/或第二偏好分值。
其中，第一偏好分值以及第二偏好分值是根据用户终端的行为数据确定的，也即根据用户使用APP的行为数据确定的，可以表示用户对该候选店铺所对应的信息类型的感兴趣的程度(偏好程度)，通俗地来讲，该步骤即是预测用户对该候选店铺对应的类型的偏好程度，确定第一偏好分值和/或第二偏好分值来表示偏好程度。具体可以根据用户终端的历史行为数据、用户终端的当前行为数据确定第一偏好分值以及第二偏好分值，需要说明的是，本公开对确定第一偏好分值以及第二偏好分值的方式不作限定。
针对第一偏好分值，实际应用中，可以将一天24小时划分为多个时段，例如根据上班高峰期、下班高峰期、用餐时间等等进行划分，本公开对此不作限定。首先，获取大量的用户终端的历史行为数据，可以分析出用户在各个时间段内偏好点击APP的哪些类型的候选店铺，根据用户终端的历史行为数据构建模型，可以预测出广大用户在对应的时间段内对各种类型的偏好程度，通俗地来讲，该步骤即是根据大数据及时段信息对用户偏好进行预测。 然后，针对每一个用户终端，根据该用户终端的历史行为数据以及当前行为数据进一步对上述预测结果进行修正，该用户终端自身的历史行为数据更能够代表用户使用APP的行为习惯，例如，在周一至周五每天的中午12点到13点更加偏好点击餐饮类型的候选店铺，此外，结合用户终端实时的当前行为数据，例如，用户终端当前点击的也是餐饮类型的候选店铺，并且当前时间为中午12点，则可以根据上述数据预测出当前时刻该用户更加偏好餐饮类型的候选店铺，对应地，则可以进一步确定各个候选店铺所对应的信息类型的第一偏好分值。又如，在周六或周日的时候用户更加偏好点击早教类型的候选店铺等。综上所述，该方式充分结合大数据与用户自己的行为数据确定候选店铺对应的类型的第一偏好分值，使得预测结果更加准确，更加贴合用户的需求。
针对第二偏好分值，根据位置信息确定第二偏好得分，实际应用中，可以根据商圈、写字楼、居民小区等等划分位置信息，本公开对此不作限定，例如将某个商场及其周边区域划分为一个商圈。与上述根据时段信息确定该候选店铺所对应的信息类型的第一偏好分值的方法类似，首先，获取大量的用户终端的历史行为数据，可以分析出用户位于某个位置时偏好点击APP的哪些类型的候选店铺，例如，用户位于某商圈时，偏好点击服装类型的候选店铺，则根据用户终端的历史行为数据构建模型，可以预测出广大用户处于某些位置时对各种信息类型的偏好程度，通俗地来讲，该步骤即是根据大数据及位置信息对用户偏好进行预测。然后，针对每一个用户终端，根据该用户终端的历史行为数据以及当前行为数据进一步对上述预测结果进行修正，用户终端自身的历史行为数据更能够代表用户使用APP的行为习惯，例如，该用户终端的位置信息为商圈时更加偏好点击服装类型的候选店铺，此外，结合用该用户终端实时的当前行为数据，例如，用户终端当前点击的也是服装类型的候选店铺，且当前的位置信息为该商圈，则可以根据上述信息预测出当前位置该用户更加偏好服装类型的候选店铺，对应地，则可以进一步确定各个候选店铺所对应的信息类型的第二偏好分值。综上所述，该方式充分结合大数据与用户自己的数据确定候选店铺对应的信息类型的第二偏好分值，使得预测结果更加准确，更加贴合用户的需求。
根据上述步骤确定了第一偏好分值和/或第二偏好分值，进一步可单独将第一偏好分值或者第二偏好分值确定为该候选店铺所对应的类型的类型偏好得分；也可以将第一偏好分值以及第二偏好分值的和确定为该候选店铺所对应的类型的类型偏好得分；也可以将第一偏好分值以及第二偏好分值的乘积确定为该候选店铺所对应的类型的类型偏好得分；也可以分别为第一偏好分 值以及第二偏好分值确定权重值，将两者的加权之和确定为该候选店铺所对应的类型的类型偏好得分，本公开对此不做限制，本领域技术人员可根据实际需要进行设置。
其次，分别针对多元化信息中包含的每种类型的店铺，设置与该类型相对应的预设类型推送比例。获取该候选店铺所对应的类型的实际类型推送比例，根据该候选店铺所对应的类型的预设类型推送比例与实际类型推送比例之间的差值，得到该类型的候选店铺的推送均衡得分。
均衡推送是为了保证每种信息类型都具有一定的推送几率，防止形成马太效应，即实际类型推送比例较大的信息类型对应的候选店铺的推送几率越来越大，而实际类型推送比例较小的信息类型对应的候选店铺的推送几率越来越小，导致推送失衡。
本步骤根据实际类型推送比例以及预设类型推送比例计算推送均衡得分对候选店铺的推送比例进行调整，保证平衡推送各个类型对应的各个候选店铺。
实际应用中，推送均衡得分具体可以根据如下公式进行计算：
PV＝{tanh[a(PVp-PVh)]+1}/2
PV为推送均衡得分，tanh()为双曲正切函数，PVp为预设类型推送比例，PVh为实际类型推送比例，а为敏感系数，具体应用中可将其设置为整数，表示当实际类型推送比例偏离预设类型推送比例时，推送均衡得分的衰减的敏感度，а的数值越大表示衰减程度越大，本领域技术人员可根据实际需要进行设置。
根据上述公式可知，当预设类型推送比例与实际类型推送比例相等时，曝光均衡得分为0.5；预设类型推送比例与实际类型推送比例的差值越小，推送均衡得分越大；预设类型推送比例与实际类型推送比例的差值越大，推送均衡得分越小。
然后，分别确定归一化得分、类型偏好得分以及推送均衡得分所对应的权重值，根据各个权重值对归一化得分、类型偏好得分以及推送均衡得分进行加权，得到该候选店铺的实际得分。
根据上述步骤确定了各个候选店铺的归一化得分、类型偏好得分以及推送均衡得分，本实施例的方法中，预先设置以上三种得分对应的权重值，计算归一化得分、类型偏好得分以及推送均衡得分的加权之和，得到候选店铺的实际得分。
综上所述，上述计算候选店铺的实际得分的方法适用于多元化信息中包 含的每一种信息类型所对应的各个候选店铺，并且可直接根据得到的实际得分对不同信息类型对应的各个候选店铺进行混合排序，结合三个维度的数据确定候选店铺的实际得分，使得不同信息类型的候选店铺的实际得分具有直接可比性。
最后，根据多元化信息中包含的每种信息类型所对应的每个候选店铺的实际得分进行混合排序，得到多条推送店铺，在将多条推送店铺进行推送的步骤之前，分别获取各个推送店铺的地理位置信息，推送店铺的地理位置信息可以是经纬度信息或者根据地图数据确定的位置信息，本公开对此不作限定。
步骤S220：分别计算各个区域内包含的推送店铺的分布密度，将分布密度大于预设密度阈值的区域确定为信息聚集区域；其中，各个区域的区域面积和/或划分方式能够根据预设区域划分规则进行动态调整。
该步骤即是根据推送店铺的地理位置信息确定信息聚集区域，信息聚集区域的区域形状、区域面积等可根据多个推送店铺的地理位置信息的分布情况进行确定，总之，需要使信息聚集区域内包含尽可能多的推送店铺。
分布密度具体可以根据各个区域内包含的推送店铺的总数量以及对应区域的区域面积进行计算，将分布密度大于预设密度阈值的区域确定为信息聚集区域，由此可知，在实际应用中，也可以预先大致规划一个区域，然后计算该区域内包含的推送店铺的分布密度，根据分布密度以及预设密度阈值调整信息聚集区域的区域范围或者区域面积，使得最终确定的信息聚集区域内推送店铺的分布密度大于或者等于预设密度阈值。其中，各个区域可根据区域的特征进行划分，例如根据商场、写字楼、购物街、美食街、居民小区等区域特征进行划分，也可以根据实际情况进行实时调整，例如根据用户终端的位置信息进行调整，本公开对此不作限定。
步骤S230：判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件。
具体地，根据信息聚集区域的区域半径和/或信息聚集区域内包含的每两个推送店铺之间的距离，判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件。其中，信息聚集区域内包含的每两个推送店铺之间的距离具体包括：信息聚集区域内包含的每两个推送店铺之间的步行距离；并且，步行距离根据地图中包含的跨河桥梁、立交桥、高架桥、和/或过街天桥确定。
根据信息聚集区域的半径，判断信息聚集区域的半径是否小于预设半径阈值，若是，则信息聚集区域内包含的各个推送店铺满足预设聚集推送条件。通俗地来讲，若聚集区域的半径小于半径阈值，则表明该信息聚集区域的区 域范围不大，对于用户来说，到达任何一个推送店铺对应的地理位置信息都是比较便利的。
根据信息聚集区域内包含的每两个推送店铺之间的距离，判断每两个推送店铺之间的距离是否小于预设阈值，若是，则信息聚集区域内包含的各个推送店铺满足预设聚集推送条件。实际应用中，可根据第三方地图数据计算信息聚集区域内包含的每两个推送店铺之间的步行距离和/或对应的步行时间，则判断每两个推送店铺之间的步行距离是否小于预设距离阈值，或者，判断每两个推送店铺之间对应的步行时间是否小于预设时间阈值，若是，则确定信息聚集区域内包含的各个推送店铺满足预设聚集推送条件。
步骤S240：若是，将信息聚集区域内包含的各个推送店铺打包为一个聚集店铺信息，并按照预设命名规则对聚集店铺信息进行命名；其中，预设命名规则包括：根据地名和/或建筑物命名，将聚集店铺信息推送给用户终端。
若判断出信息聚集区域内包含的各个推送店铺满足预设聚集推送条件，则将信息聚集区域内包含的各个推送店铺打包为一个聚集店铺信息，并为聚集店铺信息命名，以便用户能够直接识别出推送店铺的所在的区域，聚集店铺信息的名称可以根据地标建筑的名称进行确定，具体可以根据信息聚集区域内具有代表性的地名和/或建筑名确定，例如，商场名称、居民小区名称、大厦名称、地标建筑名称等等，将命名后的聚集店铺信息推送给用户终端。
步骤S250：若否，判断信息聚集区域是否满足预设调整条件，并在满足时根据预设调整条件对信息聚集区域的区域范围进行调整，以使调整后的信息聚集区域满足预设聚集推送条件。
若判断出信息聚集区域内包含的各个推送店铺不满足预设聚集推送条件，则判断信息聚集区域是否满足预设调整条件，具体可根据信息聚集区域的区域范围、区域半径判断信息聚集区域是否满足预设调整条件，若信息聚集区域满足预设调整条件，则对信息聚集区域的区域范围进行调整，具体可将信息聚集区域的区域范围进行扩大或者缩小，也即，使信息聚集区域内包含更多的推送店铺，或者去除信息聚集区域内的不满足预设聚集推送条件的推送店铺，直到调整之后的信息聚集区域内包含的各个推送店铺满足预设聚集推送条件。
步骤S260：根据调整后的信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将聚集店铺信息推送给用户终端。
根据上述步骤对信息聚集区域进行调整，直到调整后的信息聚集区域内包含的各个推送店铺满足预设聚集推送条件，则将调整之后的信息聚集区域内包含的各个推送店铺打包为一个聚集店铺信息，进一步为聚集店铺信息命 名，以便用户能够直接识别出推送店铺的所在的区域，将命名后的聚集店铺信息推送给用户终端。
可选地，用户终端在接收到推送店铺之后，根据获取到的用户终端的用户属性信息，按照预设展示规则确定与每种类型的推送店铺相对应的各个功能入口的展示状态。
每种类型的推送店铺对应有多个功能，相应地，对推送店铺进行展示时，需要展示对应的各个功能入口，例如对于店铺类型的推送消息，具有评论、预约、下单、买单等多种功能对应的功能入口，对于商品类型的推送消息，具有评论、查看商品详情、立即购买、加入购物车等多种功能的功能入口，则需要确定各个功能入口的展示状态，以根据展示状态展示各个功能入口。再如，在一些情况下，一个推送店铺的部分功能入口无需进行展示，例如，对于店铺类型的推送店铺，具有预约、下单、买单、抢优惠券等功能入口，在用户已经到店的情况下，则无需展示该条推送店铺的预约的功能入口，或者根据用户终端的行为数据判断出该用户终端已经执行过下单操作，则此时无需显示该条推送店铺的预约以及下单的功能入口。该方式在确定了推送店铺之后，根据获取到的用户终端的用户属性信息，按照预设展示规则确定与每种类型的推送店铺相对应的各个功能入口的展示状态。
其中，功能入口的展示状态包括：隐藏状态、可见状态、可点击状态、不可点击状态、高亮显示状态、和/或展示次序。
其中，用户属性信息包括以下中的至少一个：用户终端的当前位置数据、用户终端的当前行为数据以及当前时间数据。
则预设展示规则包括以下中的至少一个：
规则一：确定与推送店铺相对应的信息位置，根据用户终端的当前位置数据与信息位置之间的距离确定各个功能入口的展示状态。
具体地，获取到用户终端的当前位置数据，判断推送店铺对应的位置数据与用户终端的当前位置数据之间的关系，根据该关系确定推送店铺相对应的各个功能入口的展示状态，沿用上述示例，当用户终端的当前位置与推送店铺对应的位置距离较远时，此时用户终端可以执行预约、领取优惠券的操作，而不能执行下单以及买单的操作，因此，可以确定该条推送店铺对应的预约功能入口以及优惠券功能入口为可见状态或者可点击状态或者高亮显示状态，以表明当前用户终端可以执行预约、领取优惠券的操作；此外，可以确定该条推送店铺对应的下单功能入口、买单功能入口为隐藏状态或者不可点击状态，以表明当前用户终端不能执行下单、买单的操作。
规则二：确定与推送店铺相对应的各个功能入口与用户行为之间的关联 关系，根据关联关系以及用户终端的当前行为数据确定各个功能入口的展示状态。
各个功能入口与用户行为之间的关联关系，也就是各个功能与用户行为之间的关联关系，根据关联关系以及用户终端的当前行为数据确定各个功能入口的展示状态。例如，对于一条店铺类型的推送消息，对应有预约、领取优惠券、秒杀、下单、买单等多个功能入口，根据用户终端的当前行为数据确定用户终端当前执行了下单的操作，则此时该推送店铺的预约功能入口就无需展示，而需要展示该条推送店铺对应的买单的功能入口，以供用户进行操作。
规则三：确定与推送店铺相对应的信息时间，根据当前时间数据与信息时间之间的间隔确定各个功能入口的展示状态。
该规则根据当前的时间数据与推送店铺相对应的信息时间之间的间隔，确定各个功能入口的展示状态，例如，针对店铺类型的推送店铺，该店铺的营业时间为晚上9点至11点，用户终端对应的当前时间数据为早上9点，则此时用户终端可执行预约以及领取优惠券的操作，则可以确定将功能入口的展示状态设置为可见状态或者可点击状态，而此时用户终端不能执行下单以及买单的操作，则将下单、买单对应的功能入口设置为隐藏状态或者不可点击状态。
优选地，预设展示规则通过预设的预测模型实现；其中，预测模型根据用户终端的历史行为数据训练得到；历史行为数据包括：评论数据、预约行为数据、和/或领取优惠行为数据。
用户终端的历史行为数据可以表明用户的行为习惯，根据用户终端的历史行为数据构建预测模型，利用预测模型可以预测当前用户的需求，也即，当前用户需要使用什么功能，进一步确定对应的功能入口的展示状态。例如，根据用户终端的评论数据判断出针对推送店铺用户偏好执行查看评论的操作；或者根据用户终端的预约行为数据判断出针对推送店铺用户偏好执行预约的操作；或者根据用户终端的领取优惠行为数据判断出针对推送店铺用户偏好执行领取优惠券的操作。则可以根据上述各种用户终端的历史行为数据构建预测模型，利用预测模型来确定推送消息的各个功能入口的展示状态，通过该方式，能够更加贴合用户的需求，更加人性化及智能化。
在确定了每种类型的推送店铺相对应的各个功能入口的展示状态之后，则用户终端根据展示状态展示各个功能入口，以便用户根据各个功能入口进行操作。其中，功能入口的展示状态可以表明是否能够执行该功能，例如，可见状态以及可点击状态表明对应的功能能够被执行，隐藏状态则表明不显 示该功能入口，不可点击状态表明该功能不能被执行；显示状态为高亮显示状态的功能入口可以为根据历史行为数据预测出的当前用户最需要的功能所对应的功能入口；展示次序可以根据各个功能之间的关系进行确定，例如，对于店铺类型的推送功能，功能入口的展示次序为：秒杀、预约、领域优惠券、下单、买单，并且展示次序是可以根据用户终端的行为数据进行实时调整的。
根据本实施例所提供的聚集店铺信息的推送方法，获取各个推送店铺的地理位置信息；分别计算各个区域内包含的推送店铺的分布密度，将分布密度大于预设密度阈值的区域确定为信息聚集区域；其中，各个区域的区域面积和/或划分方式能够根据预设区域划分规则进行动态调整；判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件；若是，将信息聚集区域内包含的各个推送店铺打包为一个聚集店铺信息，并按照预设命名规则对聚集店铺信息进行命名；其中，预设命名规则包括：根据地名和/或建筑物命名，将聚集店铺信息推送给用户终端；若否，判断信息聚集区域是否满足预设调整条件，并在满足时根据预设调整条件对信息聚集区域的区域范围进行调整，以使调整后的信息聚集区域满足预设聚集推送条件；根据调整后的信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将聚集店铺信息推送给用户终端。该方式能够根据推送店铺的地理位置确定包含多条推送店铺的聚集店铺信息，从而将地理位置之间具有关联性的多条推送店铺一并打包并推送给用户终端，提升用户体验；其次，能够结合交通设施、自然环境等因素确定多条推送店铺，使得每两个推送店铺对应的位置之间均可直达，并且对于用户来说，用户到达任一推送店铺对应的位置都是便利的，节省了用户的探店时间；最后，能够根据推送店铺的地理位置信息调整信息聚集区域，以使推送给用户终端的推送店铺为最合理的、最优的。
另外，本领域技术人员能够理解的是，本实施例中的方式既可以同时针对多种类型的推送店铺执行步骤S220及其步骤中的打包推送方式，以便用户能够一并获取到多种类型、且相距较近的推送店铺，从而满足多元化的需求。或者，也可以分别针对每种类型的推送店铺执行步骤S220及其步骤中的打包推送方式，以便用户能够获取到自身最感兴趣的类型的店铺的打包推送信息。例如，可以结合各个类型店铺的推送均衡得分和/或类型偏好得分来确定在步骤S220及其步骤中打包推送何种类型的店铺。举例而言，假设根据用户使用APP的时间和/或地点确定早教类型的店铺的类型偏好得分最高，则相应地，在步骤S220及其步骤中打包推送早教类型的店铺。
实施例三
图3示出了本公开实施例三提供的一种聚集店铺信息的推送装置的结构示意图，该装置包括：
地理位置信息获取模块31，适于获取各个推送店铺的地理位置信息；
信息聚集区域确定模块32，适于根据地理位置信息确定包含多个推送店铺的信息聚集区域；
判断模块33，适于判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件；
推送模块34，适于若判断出信息聚集区域内包含的各个推送店铺满足预设聚集推送条件，根据信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将聚集店铺信息推送给用户终端。
可选地，信息聚集区域确定模块32进一步适于：
分别计算各个区域内包含的推送店铺的分布密度，将分布密度大于预设密度阈值的区域确定为信息聚集区域；
其中，各个区域的区域面积和/或划分方式能够根据预设区域划分规则进行动态调整。
可选地，判断模块33进一步适于：
根据信息聚集区域的区域半径和/或信息聚集区域内包含的每两个推送店铺之间的距离，判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件。
可选地，上述装置进一步包括：
调整模块35，适于当判断出信息聚集区域内包含的各个推送店铺不满足预设聚集推送条件时，判断信息聚集区域是否满足预设调整条件，并在满足时根据预设调整条件对信息聚集区域的区域范围进行调整，以使调整后的信息聚集区域满足预设聚集推送条件；
则推送模块34进一步适于：根据调整后的信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将聚集店铺信息推送给用户终端。
可选地，信息聚集区域内包含的每两个推送店铺之间的距离具体包括：信息聚集区域内包含的每两个推送店铺之间的步行距离；
并且，步行距离根据地图中包含的跨河桥梁、立交桥、高架桥、和/或过街天桥确定。
可选地，地理位置信息获取模块31进一步适于：分别获取每种信息类型中包含的各个推送店铺的地理位置信息。
可选地，推送模块34进一步适于：将信息聚集区域内包含的各个推送店 铺打包为一个聚集店铺信息，并按照预设命名规则对聚集店铺信息进行命名；
其中，预设命名规则包括：根据地名和/或建筑物命名。
可选地，装置进一步包括：推送店铺确定模块，适于根据各个候选店铺的归一化得分、类型偏好得分和/或推送均衡得分，确定各个候选店铺的实际得分；根据各个候选店铺的实际得分，从各个候选店铺中选择多个推送店铺；其中，归一化得分根据预设的归一化处理规则确定，类型偏好得分根据时段信息和/或位置信息确定，推送均衡得分根据预设类型推送比例确定。
关于上述各个模块的具体结构和工作原理可参照方法实施例中相应部分的描述，此处不再赘述。
实施例四
本申请实施例四提供了一种非易失性计算机可读存储介质，该非易失性计算机可读存储介质存储有至少一可执行指令，该计算机可执行指令可执行上述任意方法实施例中的聚集店铺信息的推送方法。
可执行指令具体可以用于使得处理器执行以下操作：
获取各个推送店铺的地理位置信息，根据地理位置信息确定包含多个推送店铺的信息聚集区域；
判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件；
若是，根据信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将聚集店铺信息推送给用户终端。
实施例五
图4示出了根据本公开实施例五的一种电子设备的结构示意图，本公开具体实施例并不对电子设备的具体实现做限定。
如图4所示，该电子设备可以包括：处理器(processor)402、通信接口(Communications Interface)406、存储器(memory)404、以及通信总线408。
其中：
处理器402、通信接口406、以及存储器404通过通信总线408完成相互间的通信。
通信接口406，用于与其它设备比如客户端或其它服务器等的网元通信。
处理器402，用于执行程序410，具体可以执行上述信息推送方法实施例中的相关步骤。
具体地，程序410可以包括程序代码，该程序代码包括计算机操作指令。
处理器402可能是中央处理器CPU，或者是特定集成电路ASIC (Application Specific Integrated Circuit)，或者是被配置成实施本公开实施例的一个或多个集成电路。电子设备包括的一个或多个处理器，可以是同一类型的处理器，如一个或多个CPU；也可以是不同类型的处理器，如一个或多个CPU以及一个或多个ASIC。
存储器404，用于存放程序410。存储器404可能包含高速RAM存储器，也可能还包括非易失性存储器(non-volatile memory)，例如至少一个磁盘存储器。
程序410具体可以用于使得处理器402执行以下操作：
获取各个推送店铺的地理位置信息，根据地理位置信息确定包含多个推送店铺的信息聚集区域；
判断信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件；
若是，根据信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将聚集店铺信息推送给用户终端。
在此提供的算法和显示不与任何特定计算机、虚拟系统或者其它设备固有相关。各种通用系统也可以与基于在此的示教一起使用。根据上面的描述，构造这类系统所要求的结构是显而易见的。此外，本公开也不针对任何特定编程语言。应当明白，可以利用各种编程语言实现在此描述的本公开的内容，并且上面对特定语言所做的描述是为了披露本公开的最佳实施方式。
在此处所提供的说明书中，说明了大量具体细节。然而，能够理解，本公开的实施例可以在没有这些具体细节的情况下实践。在一些实例中，并未详细示出公知的方法、结构和技术，以便不模糊对本说明书的理解。
类似地，应当理解，为了精简本公开并帮助理解各个公开方面中的一个或多个，在上面对本公开的示例性实施例的描述中，本公开的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而，并不应将该公开的方法解释成反映如下意图：即所要求保护的本公开要求比在每个权利要求中所明确记载的特征更多的特征。更确切地说，如下面的权利要求书所反映的那样，公开方面在于少于前面公开的单个实施例的所有特征。因此，遵循具体实施方式的权利要求书由此明确地并入该具体实施方式，其中每个权利要求本身都作为本公开的单独实施例。
本领域那些技术人员可以理解，可以对实施例中的设备中的模块进行自适应性地改变并且把它们设置在与该实施例不同的一个或多个设备中。可以把实施例中的模块或单元或组件组合成一个模块或单元或组件，以及此外可以把它们分成多个子模块或子单元或子组件。除了这样的特征和/或过程或者单元中的至少一些是相互排斥之外，可以采用任何组合对本说明书(包括伴 随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述，本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。
此外，本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征，但是不同实施例的特征的组合意味着处于本公开的范围之内并且形成不同的实施例。例如，在下面的权利要求书中，所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
本公开的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本公开实施例的信息推送装置中的一些或者全部部件的一些或者全部功能。本公开还可以实现为用于执行这里所描述的方法的一部分或者全部的设备或者装置程序(例如，计算机程序和计算机程序产品)。这样的实现本公开的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
应该注意的是上述实施例对本公开进行说明而不是对本公开进行限制，并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。单词“包含”不排除存在未列在权利要求中的元件或步骤。位于元件之前的单词“一”或“一个”不排除存在多个这样的元件。本公开可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。

Claims (19)

  1. 一种聚集店铺信息的推送方法，包括：
    获取各个推送店铺的地理位置信息，根据所述地理位置信息确定包含多个推送店铺的信息聚集区域；
    判断所述信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件；
    若是，根据所述信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将所述聚集店铺信息推送给用户终端。
  2. 根据权利要求1所述的方法，其中，所述根据所述地理位置信息确定包含多个推送店铺的信息聚集区域的步骤具体包括：
    分别计算各个区域内包含的推送店铺的分布密度，将分布密度大于预设密度阈值的区域确定为信息聚集区域；
    其中，各个区域的区域面积和/或划分方式能够根据预设区域划分规则进行动态调整。
  3. 根据权利要求1或2所述的方法，其中，判断所述信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件的步骤具体包括：
    根据所述信息聚集区域的区域半径和/或所述信息聚集区域内包含的每两个推送店铺之间的距离，判断所述信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件。
  4. 根据权利要求3所述的方法，其中，当判断出所述信息聚集区域内包含的各个推送店铺不满足预设聚集推送条件时，所述方法进一步包括：
    判断所述信息聚集区域是否满足预设调整条件，并在满足时根据所述预设调整条件对所述信息聚集区域的区域范围进行调整，以使调整后的信息聚集区域满足所述预设聚集推送条件；
    根据所述调整后的信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将所述聚集店铺信息推送给用户终端。
  5. 根据权利要求3或4所述的方法，其中，所述信息聚集区域内包含的每两个推送店铺之间的距离具体包括：所述信息聚集区域内包含的每两个推送店铺之间的步行距离；
    并且，所述步行距离根据地图中包含的跨河桥梁、立交桥、高架桥、和/或过街天桥确定。
  6. 根据权利要求1-5任一所述的方法，其中，所述获取各个推送店铺的地理位置信息的步骤具体包括：分别获取每种信息类型中包含的各个推送店铺的地理位置信息。
  7. 根据权利要求1-6任一所述的方法，其中，所述根据所述信息聚集区域内包含的各个推送店铺生成聚集店铺信息的步骤具体包括：
    将所述信息聚集区域内包含的各个推送店铺打包为一个聚集店铺信息，并按照预设命名规则对所述聚集店铺信息进行命名；
    其中，所述预设命名规则包括：根据地名和/或建筑物命名。
  8. 根据权利要求1-7任一所述的方法，其中，所述获取各个推送店铺的地理位置信息的步骤之前，进一步包括：
    根据各个候选店铺的归一化得分、类型偏好得分和/或推送均衡得分，确定各个候选店铺的实际得分；根据所述各个候选店铺的实际得分，从各个候选店铺中选择多个推送店铺；
    其中，所述归一化得分根据预设的归一化处理规则确定，所述类型偏好得分根据时段信息和/或位置信息确定，所述推送均衡得分根据预设类型推送比例确定。
  9. 一种聚集店铺信息的推送装置，包括：
    地理位置信息获取模块，适于获取各个推送店铺的地理位置信息；
    信息聚集区域确定模块，适于根据所述地理位置信息确定包含多个推送店铺的信息聚集区域；
    判断模块，适于判断所述信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件；
    推送模块，适于若判断出所述信息聚集区域内包含的各个推送店铺满足预设聚集推送条件，根据所述信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将所述聚集店铺信息推送给用户终端。
  10. 根据权利要求9所述的装置，其中，所述信息聚集区域确定模块进一步适于：
    分别计算各个区域内包含的推送店铺的分布密度，将分布密度大于预设密度阈值的区域确定为信息聚集区域；
    其中，各个区域的区域面积和/或划分方式能够根据预设区域划分规则进行动态调整。
  11. 根据权利要求9或10所述的装置，其中，所述判断模块进一步适于：
    根据所述信息聚集区域的区域半径和/或所述信息聚集区域内包含的每两个推送店铺之间的距离，判断所述信息聚集区域内包含的各个推送店铺是否满足预设聚集推送条件。
  12. 根据权利要求11所述的装置，其中，所述装置进一步包括：
    调整模块，适于当判断出所述信息聚集区域内包含的各个推送店铺不满足预设聚集推送条件时，判断所述信息聚集区域是否满足预设调整条件，并在满足时根据所述预设调整条件对所述信息聚集区域的区域范围进行调整，以使调整后的信息聚集区域满足所述预设聚集推送条件；
    则所述推送模块进一步适于：根据所述调整后的信息聚集区域内包含的各个推送店铺生成聚集店铺信息，将所述聚集店铺信息推送给用户终端。
  13. 根据权利要求11或12所述的装置，其中，所述信息聚集区域内包含的每两个推送店铺之间的距离具体包括：所述信息聚集区域内包含的每两个推送店铺之间的步行距离；
    并且，所述步行距离根据地图中包含的跨河桥梁、立交桥、高架桥、和/或过街天桥确定。
  14. 根据权利要求9-13任一所述的装置，其中，所述地理位置信息获取模块进一步适于：分别获取每种信息类型中包含的各个推送店铺的地理位置信息。
  15. 根据权利要求9-14任一所述的装置，其中，所述推送模块进一步适于：将所述信息聚集区域内包含的各个推送店铺打包为一个聚集店铺信息，并按照预设命名规则对所述聚集店铺信息进行命名；
    其中，所述预设命名规则包括：根据地名和/或建筑物命名。
  16. 根据权利要求9-15任一所述的装置，其中，所述装置进一步包括：
    推送店铺确定模块，适于根据各个候选店铺的归一化得分、类型偏好得分和/或推送均衡得分，确定各个候选店铺的实际得分；根据所述各个候选店铺的实际得分，从各个候选店铺中选择多个推送店铺；
    其中，所述归一化得分根据预设的归一化处理规则确定，所述类型偏好得分根据时段信息和/或位置信息确定，所述推送均衡得分根据预设类型推送比例确定。
  17. 一种电子设备，包括：处理器、存储器、通信接口和通信总线，所述处理器、所述存储器和所述通信接口通过所述通信总线完成相互间的通信；
    所述存储器用于存放至少一可执行指令，所述可执行指令使所述处理器执行如权利要求1-8中任一项所述的聚集店铺信息的推送方法对应的操作。
  18. 一种非易失性计算机可读存储介质，所述非易失性计算机可读存储介质中存储有至少一可执行指令，所述可执行指令使处理器执行如权利要求1-8中任一项所述的聚集店铺信息的推送方法对应的操作。
  19. 一种计算机程序产品，其中，所述计算机程序产品包括存储在非易失性计算机存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使所述计算机执行如权利要求1-8中任一项所述的聚集店铺信息的推送方法对应的操作。
PCT/CN2019/074925 2018-02-13 2019-02-13 聚集店铺信息的推送方法及装置 WO2019158068A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810149030.7A CN108280748A (zh) 2018-02-13 2018-02-13 聚集店铺信息的推送方法及装置
CN201810149030.7 2018-02-13

Publications (1)

Publication Number Publication Date
WO2019158068A1 true WO2019158068A1 (zh) 2019-08-22

Family

ID=62808528

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/074925 WO2019158068A1 (zh) 2018-02-13 2019-02-13 聚集店铺信息的推送方法及装置

Country Status (2)

Country Link
CN (1) CN108280748A (zh)
WO (1) WO2019158068A1 (zh)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108280748A (zh) * 2018-02-13 2018-07-13 口口相传(北京)网络技术有限公司 聚集店铺信息的推送方法及装置
CN109409938A (zh) * 2018-09-30 2019-03-01 拉卡拉支付股份有限公司 商圈圈定方法和装置
CN111325595B (zh) * 2018-12-17 2023-07-14 阿里巴巴(深圳)技术有限公司 用户权益信息展示方法、装置及电子设备
CN110033310A (zh) * 2019-03-08 2019-07-19 阿里巴巴集团控股有限公司 商区管理系统及方法
CN111914123B (zh) * 2019-05-08 2023-08-18 百度在线网络技术（北京）有限公司 信息推广方法、装置、电子设备和存储介质
CN110378758A (zh) * 2019-06-06 2019-10-25 浙江口碑网络技术有限公司 店铺展示信息的处理方法、装置及设备
CN112182425B (zh) * 2019-07-05 2024-07-09 阿里巴巴集团控股有限公司 页面信息处理方法、装置及电子设备
CN110348909A (zh) * 2019-07-16 2019-10-18 百度在线网络技术（北京）有限公司 店铺评价的获取方法、装置、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150120722A1 (en) * 2013-10-31 2015-04-30 Telefonica Digital Espana, S.L.U. Method and system for providing multimedia content recommendations
CN104951551A (zh) * 2015-06-26 2015-09-30 深圳市腾讯计算机系统有限公司 一种数据分类方法及系统
CN107124476A (zh) * 2017-07-04 2017-09-01 百度在线网络技术（北京）有限公司 信息推送方法和装置
CN107395680A (zh) * 2017-06-23 2017-11-24 口碑控股有限公司 店铺群信息推送和输出方法及装置、设备
CN108280748A (zh) * 2018-02-13 2018-07-13 口口相传(北京)网络技术有限公司 聚集店铺信息的推送方法及装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106649331B (zh) * 2015-10-29 2020-09-11 阿里巴巴集团控股有限公司 商圈识别方法及设备
CN106056413A (zh) * 2016-06-06 2016-10-26 四川大学 基于时空偏好的兴趣点推荐方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150120722A1 (en) * 2013-10-31 2015-04-30 Telefonica Digital Espana, S.L.U. Method and system for providing multimedia content recommendations
CN104951551A (zh) * 2015-06-26 2015-09-30 深圳市腾讯计算机系统有限公司 一种数据分类方法及系统
CN107395680A (zh) * 2017-06-23 2017-11-24 口碑控股有限公司 店铺群信息推送和输出方法及装置、设备
CN107124476A (zh) * 2017-07-04 2017-09-01 百度在线网络技术（北京）有限公司 信息推送方法和装置
CN108280748A (zh) * 2018-02-13 2018-07-13 口口相传(北京)网络技术有限公司 聚集店铺信息的推送方法及装置

Also Published As

Publication number Publication date
CN108280748A (zh) 2018-07-13

Similar Documents

Publication Publication Date Title
WO2019158068A1 (zh) 聚集店铺信息的推送方法及装置
JP6768894B2 (ja) マーケティング上のモバイル広告供給に関するシステムと方法
WO2019158069A1 (zh) 服务功能入口的展示方法及装置
CN108460631B (zh) 多元化信息的混合推送方法及装置
US8055282B1 (en) Providing path-based search information
US20220207063A1 (en) Broker mediated geospatial information service
KR101634773B1 (ko) 캘린더를 이용한 스케쥴 관리시스템 및 스케쥴 관리방법
US20200104333A1 (en) Information recommending method and device
CN107734456B (zh) 一种用于推荐服务信息的方法与设备
JP2019508766A (ja) 地理的エリアのヒートマップを生成するシステム、方法、およびデバイス
JP5560026B2 (ja) 地図表示装置、地図表示方法及び地図表示プログラム
CN111949834A (zh) 选址方法和选址平台
US11134359B2 (en) Systems and methods for calibrated location prediction
KR20110124782A (ko) 스폰서형 랜드마크 및 위치 라벨들을 전송하기 위한 시스템 및 방법
JP7285521B2 (ja) 類似のモバイル装置を予測するためのシステムと方法
JP6767952B2 (ja) 推定装置、推定方法および推定プログラム
JP7328198B2 (ja) ナビゲーションに用いられる方法、装置、デバイス及び媒体
WO2021081767A1 (zh) 位置点确定方法、装置、电子设备及计算机可读介质
JP7017865B2 (ja) 判定装置、判定方法及び判定プログラム
WO2021133997A1 (en) Systems and methods for calibrated location prediction
Baban et al. High betweeness nodes and crowded intersections: An experimental assessment by means of simulation
CN110766493B (zh) 业务对象提供方法、服务器、电子设备、存储介质
WO2023149900A1 (en) Systems and methods for identifying high traffic zones and suggesting alternative destinations to users
JP2020047058A (ja) 特定装置、特定方法及び特定プログラム

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: 19753699

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: 19753699

Country of ref document: EP

Kind code of ref document: A1