WO2020143351A1 - 区域综合推荐方法、电子设备及可读存储介质 - Google Patents

区域综合推荐方法、电子设备及可读存储介质 Download PDF

Info

Publication number
WO2020143351A1
WO2020143351A1 PCT/CN2019/121652 CN2019121652W WO2020143351A1 WO 2020143351 A1 WO2020143351 A1 WO 2020143351A1 CN 2019121652 W CN2019121652 W CN 2019121652W WO 2020143351 A1 WO2020143351 A1 WO 2020143351A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
recommendation
recommended
label
comprehensive
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2019/121652
Other languages
English (en)
French (fr)
Inventor
郝哲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sankuai Online Technology Co Ltd
Original Assignee
Beijing Sankuai Online Technology Co Ltd
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 Beijing Sankuai Online Technology Co Ltd filed Critical Beijing Sankuai Online Technology Co Ltd
Publication of WO2020143351A1 publication Critical patent/WO2020143351A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9537Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Definitions

  • the present invention relates to the technical field of data processing, and in particular to a comprehensive regional recommendation method, electronic device, and readable storage medium.
  • the present invention provides a method for regional comprehensive recommendation, an electronic device, and a readable storage medium to partially or completely solve the above-mentioned problems related to the regional comprehensive recommendation process in the prior art.
  • a regional comprehensive recommendation method including:
  • the comprehensive recommendation area is thermally rendered and displayed.
  • a regional comprehensive recommendation device including:
  • the recommended label combination acquisition module is used to obtain the recommended label combination input by the user
  • the integrated recommendation area search module is used to search for an integrated recommendation area corresponding to the recommended label combination based on the recommended label combination;
  • the heat map data confirmation module is used to determine the heat map data of the comprehensive recommendation area
  • the thermal rendering module is configured to thermally render and display the comprehensive recommended area based on the thermal map data.
  • an electronic device including:
  • a processor, a memory, and a computer program stored on the memory and capable of running on the processor are characterized in that, when the processor executes the program, the aforementioned regional comprehensive recommendation method is implemented.
  • a computer program including computer readable code, which, when run on a computing processing device, causes the computing processing device to perform the aforementioned regional comprehensive recommendation method.
  • a computer-readable medium in which the computer program according to the fourth aspect is stored.
  • the recommended label combination input by the user can be obtained; based on the recommended label combination, a comprehensive recommended region corresponding to the recommended label combination is searched; the heat map data of the integrated recommended region is determined; The heat map data thermally renders and displays the comprehensive recommended area.
  • FIG. 1 shows a flowchart of steps of a method for comprehensive regional recommendation according to an embodiment of the present invention
  • FIG. 2 shows a flowchart of steps of a method for comprehensive regional recommendation according to an embodiment of the present invention
  • FIG. 3 shows a schematic structural diagram of a region comprehensive recommendation device according to an embodiment of the present invention
  • FIG. 4 shows a schematic structural diagram of an area comprehensive recommendation device according to an embodiment of the present invention
  • FIG. 5 schematically shows a block diagram of a computing processing device for performing the method according to the invention.
  • Fig. 6 schematically shows a storage unit for holding or carrying program code implementing the method according to the invention.
  • the current search solution is acceptable in supporting a single target recommendation, but it is not effective in providing multiple types of comprehensive recommendations. For example, some users want to eat Western food, want to watch movies, and want to live in a high-star hotel. If it is difficult to retrieve the optimal combination separately, then the user is likely to abandon the plan; or some users have a certain tendency to the environment, like lively or clean, etc., and the current search scheme is still difficult to meet well These needs of users. To solve these problems, the embodiments of the present invention provide the following technical solutions.
  • FIG. 1 shows a flowchart of steps of a method for comprehensive regional recommendation in an embodiment of the present invention.
  • Step 110 Obtain the recommended label combination input by the user.
  • the input recommended label combination contains multiple labels.
  • the corresponding search platform can further provide multiple tags under the product of interest to the user, and then the user can select some of their preferred tags from the tags provided by the search platform, or It is to manually input other tags by itself, so that the currently selected tag combination of the corresponding user can be constructed by using the tags selected by the user and the tags manually input by the user.
  • Step 120 based on the recommended label combination, search for a comprehensive recommended area corresponding to the recommended label combination.
  • the comprehensive recommended area corresponding to the recommended label combination may be searched based on the recommended label combination.
  • the comprehensive recommendation area corresponding to the recommended label combination can be understood as that the corresponding comprehensive recommendation area includes each label that satisfies the corresponding recommended label combination or a business corresponding to part of the recommended label.
  • the merchants may include but not limited to at least one of attractions, hotels, restaurants, entertainment, etc.
  • the conditions that the comprehensive recommendation area corresponding to the recommended label combination needs to meet may be preset according to requirements, and this embodiment of the present invention is not limited.
  • Step 130 Determine the heat map data of the comprehensive recommendation area.
  • the heat map is a special highlight to display the page area and geographical area where the visitor is keen.
  • Heat maps refer to the use of heat spectrograms to show users' behavior on the website.
  • the places with large page views and large clicks are red, and the places with small page views and low clicks are colorless and blue.
  • the heat map data of the comprehensive recommendation area needs to be determined first.
  • the heat map data of the comprehensive recommendation area can be obtained by any available method, which is not limited in the embodiment of the present invention.
  • the heat map data may include but is not limited to real-time thermal data, thermal trend data, and so on.
  • the real-time thermal data can represent the current thermal situation of the comprehensive recommendation area, while the thermal trend data can represent the future thermal situation trend of the comprehensive recommendation area.
  • the heat map data can be obtained based on the real-time data and historical data of the content contained in the comprehensive recommendation area.
  • Step 140 Thermally render and display the comprehensive recommended area based on the heat map data.
  • the corresponding comprehensive recommendation area may be further thermally rendered and displayed based on the heat map data, then the user You can intuitively understand the comprehensive thermal conditions of each comprehensive recommended area.
  • the specific rendering method may be preset according to requirements, and this embodiment of the present invention is not limited.
  • the rendering mode can be set as: the higher the heat map data, the larger the wavelength of the rendering hue in the corresponding comprehensive recommendation area, and so on.
  • the recommended label combination input by the user can be obtained; based on the recommended label combination, a comprehensive recommended region corresponding to the recommended label combination is searched; the heat map data of the integrated recommended region is determined; The heat map data thermally renders and displays the comprehensive recommended area.
  • FIG. 2 shows a flowchart of steps of a method for comprehensive regional recommendation in an embodiment of the present invention.
  • Step 210 Obtain the recommended label combination input by the user.
  • Step 220 Determine an initial recommended area corresponding to the recommended label combination according to the label type and preset label priority of each label in the recommended label combination; the initial recommended area includes an alternative recommended area and/or eliminated Recommended area.
  • merchants can be divided into many different types, such as hotels, attractions, restaurants, entertainment, etc.
  • the user can enter tags for different businesses, so the tags in the recommended tag combination entered by the user can also be divided into different tag types, for example, the above can be determined for the merchant type corresponding to each tag
  • the label type of each label is currently in this embodiment of the present invention, and the label type of each label in the recommended label combination may also be determined based on other strategies, which is not limited in this embodiment of the present invention.
  • the tag type of each tag is determined for the type of business corresponding to each tag, then the type of product to be searched for by the corresponding tag can be determined according to each tag, that is, the type of merchant.
  • the label under hotel products can include “star”, such as “Samsung”, “four stars”, “five stars”, etc., including “brand”, such as “Hanting”, “Rujia”, etc.;
  • the label may include “cuisine”, such as “Sichuan cuisine”, “Lu cuisine”, “Cantonese cuisine”, etc., including “taste”, such as “spicy”, “sour”, “sweet”, etc.;
  • the label under the scenic spot product may include “Historic", “garden”, etc.;
  • the labels under entertainment products can include “group purchase", “leisure”, “singing", “playing ball”, etc.
  • the recommended label combination entered by the user includes labels such as "Samsung”, “Lu Cai”, and “Garden”, then it can be determined that the label types of each label are, in order, a hotel label, a catering label, and an attraction label.
  • the preset label priority may be set to be the label priority corresponding to the label type with a lower product quantity being higher.
  • the label priority may be additionally set according to requirements, and this embodiment of the present invention is not limited.
  • the label type of each label in the recommended label combination and the preset label priority can be used to determine and The initial recommended area corresponding to the recommended label combination.
  • a region containing businesses satisfying all the labels in the recommended label combination may be searched, or may only be included in the search If the area of the merchant that meets some of the tags in the recommended tag combination is met, then the area that contains the merchant that meets all the tags in the recommended tag combination can be called an alternative recommended area, while for the above area that contains only part of the recommended tag combination The area of the labelled merchant can be called the elimination recommendation area. Therefore, the initial recommendation area in the embodiment of the present invention may include an alternative recommendation area and/or a elimination recommendation area.
  • the label type includes at least one of an attraction label, a hotel label, a catering label, and an entertainment label;
  • the preset label priority includes the attraction label being a first level, a hotel The label is the second level, and the catering label and the entertainment label are the third level.
  • the label types in this embodiment of the present invention may include at least one of attraction labels, hotel labels, catering labels, and entertainment labels.
  • the preset label priority may include that the attraction label is at the first level, the hotel label is at the second level, and the catering label and entertainment label are at the third level.
  • the step 220 may further include:
  • Sub-step 221 acquiring the specified location of the user.
  • the specified position can be a reference point set by the corresponding user to determine the comprehensive recommendation area, for example, the user's specified position can be the center, and the matching of the recommended label combination of the corresponding user can be found from the near and far to match the corresponding recommended label combination Comprehensive recommended area, etc.
  • the specific designated location can be customized by the user, and this embodiment of the present invention is not limited. If the user does not set the designated location, the current location of the corresponding user can be directly used as the designated location.
  • Sub-step 222 based on the tag priority, centering on the specified location and using a preset search distance as a radius, to find a high-priority merchant that matches a high-priority tag.
  • Sub-step 224 in response to whether a merchant matching a label with a low priority level is found in the high-priority recommendation area, confirm that the high-priority recommendation area is a candidate recommendation area or a eliminated recommendation area.
  • the sub-step 224 may further include:
  • Sub-step 2241 in response to finding a merchant matching the label of the low priority level in the high priority recommendation area, confirming that the high priority recommendation area is an alternative recommendation area.
  • Sub-step 2242 in response to finding only a second-level merchant matching the second-level label in the high-priority recommendation area, determine a low-priority recommendation area based on the second-level merchant and the preset recommended area radius ;
  • Sub-step 2243 in response to finding only a third-rank merchant matching the third-rank label in the high-priority recommendation area, or finding no matching with other-rank labels in the high-priority recommendation area Merchants, confirm that the high-priority recommended area is a eliminated recommended area;
  • Sub-step 2244 in response to finding a merchant matching the third-level label in the low priority recommendation area, confirming that the combination of the high priority recommendation area and the low priority recommendation area is an alternative recommendation area;
  • Sub-step 2245 in response to finding no merchant matching the third-level label in the low priority recommendation area, confirm that the combination of the high priority recommendation area and the low priority recommendation area is a eliminated recommendation area.
  • the labels under each label type may be matched based on the priority of each label type from high to low. Therefore, after obtaining the designated position of the corresponding user, first of all, according to the label priority, the designated position as the center and the preset search distance as the radius can be used to find the high priority that matches the label of the high priority level in the recommended label combination
  • the ranking merchants in turn, can determine the high priority recommendation area based on the searched high priority ranking merchants and the preset recommended area radius.
  • the preset search distance and the recommended area radius can be preset according to requirements, and this embodiment of the present invention is not limited.
  • the specified location can be customized by the user according to the search requirements, and if the user does not set the specified location, the user's current location can be used as the specified location by default.
  • the label type corresponding to the high priority level can also be preset according to requirements, and this embodiment of the present invention is not limited.
  • the label type corresponding to the high priority level may be set to include the aforementioned attraction label, or may include the aforementioned attraction label and hotel label, and so on.
  • the high-priority recommendation area you can find businesses matching the low-priority label. If you find a business that matches at least one low-priority label in the high-priority recommendation area, you can confirm the corresponding high-priority in response.
  • the recommended area is an alternative recommended area; otherwise, it can be confirmed that the corresponding high-priority recommended area is a eliminated recommended area.
  • a merchant matching at least one label of each low priority level is found in the high priority recommendation area, then in response, it can be confirmed that the corresponding high priority recommendation area is one Alternative recommendation area; otherwise, the corresponding high priority recommendation area can be confirmed as a eliminated recommendation area; etc.
  • the label matching conditions corresponding to the specific candidate recommendation area and the elimination recommendation area may be preset according to requirements, and this embodiment of the present invention is not limited.
  • a business matching a certain low priority label in the high priority recommendation area can be understood as a business matching at least one label under the corresponding low priority level in the corresponding high priority recommendation area.
  • the above-mentioned low-priority label may include a label at a level other than the high-priority level in the recommended label combination.
  • the recommended label combination contains the above-mentioned labels "Five Stars”, “Hanting”, “Home”, “Lu Cai”, “Light Taste”, “Historic Site”, “Singing”, “Playing Ball”, etc. .
  • “Five Stars”, “Hanting” and “Home” are hotel labels
  • "Lu cuisine” and “light taste” are catering labels
  • "Historic Sites” are attractions labels
  • “Playing” and “Playing Balls” are entertainment labels.
  • the preset label priority is the attraction label is the first level
  • the hotel label is the second level
  • the catering label and the entertainment label are the third level
  • the first level is the high priority level
  • the other levels are all low priority levels.
  • a low-priority recommendation area may be determined based on the second-level merchant and the preset recommended area radius, and further Find a business matching the third-level label in the low-priority recommendation area, and if a business matching the third-level label is found in the low-priority recommendation area, confirm that the high-priority recommendation area and the low-priority
  • the combination of recommended areas is an alternative recommended area; and if no business matching the third-level label is found in the corresponding low-priority recommended area, you can confirm the corresponding high-priority recommended area and the corresponding low-priority recommended area.
  • the combination is the recommended area for elimination.
  • the high-priority recommended area is a eliminated recommended area.
  • two data lists may also be separately set for recording the elimination recommendation area and the candidate recommendation area.
  • the elimination list can be used to record elimination recommendation regions
  • the success list can be used to record candidate recommendation regions.
  • the eliminated recommendation area and the candidate recommendation area may also be recorded in order of the degree of fit.
  • the specified location is the center and the preset search distance is the radius, no high-priority merchant matching the high-priority label is found, or it is not in the recommended label combination Contains high-priority tags, then you can further use the specified location as the center and the preset search distance as the radius to find the second-level businesses that match the second-level tags, which can be based on the found second-level
  • the merchant and the preset recommended area radius determine the low-priority recommended area, and then no matter whether the third-level tag matching merchant is found in the low-priority recommended area, the low-priority recommended area can be used as the eliminated recommended area.
  • the specified location is the center and the preset search distance is the radius, no high-priority business matching the high-priority label and a second-level business matching the second-level label are found, or If the recommended label combination does not contain high-priority and second-level labels, you can also use the specified location as the center and the preset search distance as the radius to find third-level businesses that match the third-level labels.
  • the low-priority recommendation area can be determined based on the found third-level merchant and the preset recommended area radius, and then the low-priority recommendation area can also be used as the elimination recommendation area.
  • the above steps may not be performed in the embodiment of the present invention, and specific settings may be preset according to requirements, which is not limited in this embodiment of the present invention.
  • the retrieval failure can be reported.
  • Step 230 According to the recommended label combination and the number of labels in the recommended label combination that match the initial recommended area, determine a degree of fit between the initial recommended area and the recommended label combination.
  • the initial recommendation area with a high degree of matching with the recommended label combination needs to be used as the comprehensive recommendation area, which can improve the comprehensive recommendation area. accuracy. Therefore, in order to select the final comprehensive recommended area from the initial recommended areas, first determine the corresponding combination of each initial recommended area and the corresponding recommended label according to the recommended label combination and the number of labels in the recommended label combination that match each initial recommended area compatibility.
  • the fit of the corresponding initial recommended area and the corresponding recommended label combination can be determined; or the recommended label can be directly used
  • the specific determination method can be pre-set according to requirements, which is not limited in this embodiment of the present invention .
  • the step 230 may further include:
  • Sub-step 231 according to the ratio of the number of labels in the recommended label combination that belong to the same label type and match the initial recommendation area, and the total number of labels included in the label type, determine the single type fit of the label type .
  • the initial recommendation areas After the initial recommendation areas are determined, in order to select a comprehensive recommendation area with a high degree of fit with the corresponding recommended label combination from each initial recommendation area, it is necessary to determine the fit degree of each initial recommendation area with the recommended label combination.
  • the recommended label combination may contain multiple labels under different label types, and there may be products matching each label under different label types in an initial recommendation area, of course, there may be Some labels do not have corresponding products in an initial recommended area.
  • the ratio of the number of labels that belong to the same label type and match the initial recommendation area in the recommended label combination and the total number of labels included in the label type may be first taken in label type units To determine the single type fit of each label type in the corresponding initial recommendation area.
  • the label type a can be any label type.
  • the average value of the single-type fit of each label type in the initial recommended area is obtained as the fit of the combination of the initial recommended area and the recommended label.
  • the average value of the single-type fit of each label type in the corresponding initial recommendation area may be further obtained as the corresponding The degree of fit between the initial recommended area of and the recommended label combination.
  • the fit degree between the initial recommended area A and the corresponding recommended label combination is (40 %+25%+83.3%)/3, which is 49.4%.
  • the weight of each label type can be set separately according to the requirements, and then the weighted average of the single type fit of each label type in the initial recommendation area can be obtained as the initial recommendation area’s The fit of the recommended label combination.
  • the weight of each label type can be preset according to requirements, and this embodiment of the present invention is not limited.
  • Step 240 Select a comprehensive recommended area from the initial recommended areas according to the number of candidate recommended areas in the initial recommended area and the fit degree of the combination of the initial recommended area and the recommended label.
  • each initial recommended area and the recommended label combination After determining the fit degree between each initial recommended area and the recommended label combination, it may be further based on the number of candidate recommended areas in the initial recommended area and the fit degree between the initial recommended area and the recommended label combination, from A comprehensive recommended area is selected from the initial recommended areas.
  • the candidate recommendation area in the initial recommendation area may include businesses that match the label types of all levels; while the elimination recommendation area only includes businesses that match the label types of some levels. Therefore, in order to enable the comprehensive recommendation area to meet the user's search needs, the alternative recommendation area can be preferentially used as the comprehensive recommendation area, but if there are fewer candidate recommendation areas for a certain combination of recommended labels, it is lower than the preset value, or even If no candidate recommendation area matching a certain recommended label combination is found, then the eliminated recommendation area with a high degree of fit with the corresponding recommended label combination can be considered as a comprehensive recommendation area, so it can be prepared according to the initial recommendation area Select the number of recommended areas and the degree of fit between the initial recommended area and the recommended label combination to select a comprehensive recommended area from the initial recommended areas.
  • the selection strategy of the specific comprehensive recommendation area may be preset according to requirements, and this embodiment of the present invention is not limited.
  • the preset value may be preset according to requirements, and this embodiment of the present invention is not limited.
  • the step 240 may further include:
  • Sub-step 241 in response to the number of candidate recommendation regions being greater than or equal to the first preset number, selecting from the candidate recommendation regions the first preset number of candidates with the highest degree of fit with the recommended label combination
  • the recommended area serves as the comprehensive recommended area.
  • Step 242 in response to the number of candidate recommendation regions being less than the first preset number and greater than or equal to 1, acquiring all the candidate recommendation regions as the comprehensive recommendation region.
  • step 243 in response to the number of candidate recommendation regions being zero, the elimination recommendation region with the highest degree of fit with the recommendation tag combination is selected from the elimination recommendation regions as the comprehensive recommendation region.
  • the final comprehensive recommended area after determining the initial recommended area, it is necessary to select the final comprehensive recommended area from the initial recommended areas according to the fit of each initial recommended area and the recommended label combination. Specifically, if there are more candidate recommendation areas in the initial recommendation area, it means that there are more optional recommendation areas that can meet the user's needs, so it is possible to preferentially select candidate recommendation areas that have a high degree of fit with the recommended label combination as the comprehensive recommendation Area, and if there are fewer alternative recommended areas, or even no alternative recommended areas, then there are fewer available options. At this time, all the alternative recommended areas can only be used as comprehensive recommended areas, or combined with recommended labels The elimination recommendation area with a high degree of fit is regarded as the comprehensive recommendation area. It can be seen that in this embodiment of the present invention, the final comprehensive recommendation area can be selected from the initial recommendation areas according to the number of candidate recommendation areas in the initial recommendation area.
  • the first preset number may be preset as a reference line, and if the number of candidate recommendation areas is greater than or equal to the first preset number, the first with the highest degree of fit with the recommended label combination may be selected from the candidate recommendation areas A preset number of candidate recommendation areas are used as comprehensive recommendation areas, and if the number of candidate recommendation areas is less than the first preset number and greater than or equal to 1, then all candidate recommendation areas can be acquired as comprehensive recommendation areas; If the number of recommended areas is zero, the eliminated recommended area with the highest degree of fit with the recommended label combination can be selected from the eliminated recommended areas as the comprehensive recommended area.
  • the first preset number may be preset according to requirements, and this embodiment of the present invention is not limited. For example, the first preset number can be set to 3, and so on.
  • the matching degree between the candidate recommendation area and the recommended label combination may be obtained first, and then whether the initial recommendation area includes the candidate recommendation Area, if the initial recommended area contains alternative recommended areas, you can eliminate the need to obtain the fit between the eliminated recommended area and the recommended label combination, and if the initial recommended area does not include the alternative recommended area, you can further obtain the eliminated recommended area and the recommendation The fit of the label combination. Therefore, it is possible to avoid an invalid operation for obtaining the degree of fit between the combination of the eliminated recommended area and the recommended label.
  • Step 250 Acquire thermal-related parameters in the comprehensive recommendation area.
  • thermal related parameters in each comprehensive recommendation area may be further obtained.
  • the thermal-related parameters may include any parameters that can directly or indirectly affect or reflect the current thermal conditions in the corresponding comprehensive recommendation area and can predict the future thermal conditions to a certain extent.
  • the thermal-related parameters may include, but are not limited to, traffic state parameters, positioning information parameters, consumption information parameters, merchant information parameters, and so on.
  • the thermal related parameters in the comprehensive recommendation area can be obtained by any available method, which is not limited in the embodiments of the present invention.
  • GPS Global Positioning System
  • positioning information in the comprehensive recommendation area can be obtained as positioning information parameters in the corresponding comprehensive recommendation area
  • traffic state parameters in the comprehensive recommendation area can be obtained from map products
  • the consumption information parameters of the corresponding comprehensive recommendation area can be obtained by obtaining the consumption information of all users in the consumption application terminal in the comprehensive recommendation area
  • the merchant information parameters of the corresponding comprehensive recommendation area can be obtained through merchant monitoring; and so on.
  • the thermal-related parameters include at least one of traffic state parameters, positioning information parameters, consumption information parameters, and merchant information parameters;
  • the heat map data includes real-time thermal data and/or Thermal trend data.
  • the traffic state parameters can include but are not limited to the traffic volume data in the comprehensive recommended area;
  • the positioning information parameters can include but are not limited to the number of terminal devices in the comprehensive recommended area that can be determined by positioning functions such as GPS, but cannot obtain no GPS Thermal information of positioning equipment;
  • consumption information parameters can include but are not limited to catering consumption information, hotel night volume, scenic area ticket sales volume, theater ticket sales volume, etc., and the above consumption information parameters can be converted to the current in the corresponding comprehensive recommendation area Popularity information;
  • business information parameters may include but are not limited to the current traffic data of the business, and so on.
  • Step 260 Determine the heat map data of the comprehensive recommendation area based on the thermal-related parameters.
  • the thermal-related parameters obtained through the above steps may directly or indirectly reflect the thermal condition of the comprehensive recommendation area, and may also reflect the future thermal condition of the comprehensive recommendation area.
  • the thermal situation can include information such as the popularity and popularity of people in the comprehensive recommendation area.
  • the heat map data of the corresponding comprehensive recommendation area can be determined based on the thermal related parameters of each comprehensive recommendation area.
  • the heat map data is data that can directly characterize the comprehensive thermal conditions of the comprehensive recommended area, which may include, but is not limited to, real-time thermal data that can characterize the current thermal conditions, thermal trend data that can characterize the future thermal conditions, and so on.
  • the corresponding relationship between the thermal related parameters and the heat map data or the calculation formula of the heat map data may be preset so as to be based on the heat power of each comprehensive recommendation area
  • the relevant parameters determine the heat map data of the corresponding comprehensive recommended area.
  • the heat map data may be set as a weighted sum of various thermal-related parameters, wherein the weights of the various thermal-related parameters may be preset according to requirements, which is not limited in this embodiment of the present invention.
  • the reference days of the heat map data are determined according to the current date and the preset reference period.
  • the information to be displayed in the comprehensive recommendation area obtained by this search may include the thermal condition for the required time, and for the thermal condition that has not yet been reached, it needs to be estimated based on historical data. Therefore, in order to determine the heat map data of the comprehensive recommendation area, first, the reference days need to be determined. Specifically, the reference days of the heat map data can be determined based on the current date and the preset reference period. The reference period therein may be preset according to requirements, and this embodiment of the present invention is not limited.
  • the current date is October 10, 2018, assuming that the preset reference period is one week, then you can determine that the heat map data can be referenced from October 3, 2018 to October 9, 2018, a total of Seven days.
  • Sub-step 262 Acquire the first thermal related parameter within a preset unit time corresponding to the predicted time point set by the user within the reference number of days.
  • the predicted time point may be the demand time point corresponding to the current recommended label combination set by the user, that is, the user's estimated consumption time point, and the specific time point may be preset according to the demand, which is not limited in this embodiment of the present invention;
  • the specific value in the unit time can also be preset according to requirements, and this embodiment of the present invention is not limited.
  • the preset unit time corresponding to the predicted time point can also be preset according to requirements, which is not limited in this embodiment of the present invention.
  • the predicted time point can be set to 8:30, and the preset unit time is 1 hour, and the preset unit time corresponding to the predicted time point can be a preset unit time starting from the predicted time point, for example, for the above
  • the predicted time point and the predicted unit time then the preset unit time corresponding to the predicted time point 8:30 is 8:30-9:30; or the preset unit time corresponding to the predicted time point can be set as the predicted time point Preset unit time, then the preset unit time corresponding to the predicted time point 8:30 at this time may be 8:00-9:00, and so on.
  • the first thermal-related parameters may include but are not limited to at least one of the above-mentioned traffic state parameters, positioning information parameters, consumption information parameters, and merchant information parameters.
  • the corresponding comprehensiveness can be further determined based on the first thermal-related parameters, the preset weight of each thermal-related parameter, and the preset first manual adjustment parameter Real-time thermal data for recommended areas.
  • the preset weight of each thermal-related parameter and the specific value of the first manual adjustment parameter can be preset according to requirements, which is not limited in this embodiment of the present invention.
  • the correspondence relationship between the first thermal-related parameters, the preset weights of the respective thermal-related parameters, and the first manual adjustment parameters, and the real-time thermal data can also be preset according to requirements, which is not limited in this embodiment of the present invention .
  • the first thermal-related parameters include the above-mentioned traffic state parameter X1, positioning information parameter Y1, consumption information parameter Z1, and business information parameter O1
  • the weights of the respective thermal-related parameters are ⁇ 1, ⁇ 2, ⁇ 3, and ⁇ 4
  • the first manual adjustment parameter is T1
  • the reference number of days is N, that is, the first thermal-related parameters in N preset unit times can be obtained. Then, the real-time thermal data at this time can be
  • Substep 264 Acquire the second thermal related parameter within a preset unit time before the predicted time point within the reference number of days.
  • the second thermal-related parameters may also include but are not limited to at least one of the above-mentioned traffic state parameters, positioning information parameters, consumption information parameters, and merchant information parameters, and refer to the preset unit time corresponding to the aforementioned predicted time point,
  • the preset unit time before the predicted time point can be a preset unit time with the predicted time point as the end point, or a preset unit time before the preset unit time where the predicted time point is located, etc.
  • the requirements are preset, and this embodiment of the present invention is not limited.
  • the preset unit time is 1 hour
  • the preset unit time before the prediction time point is a preset unit time with the prediction time point as the end point
  • the prediction time at this time The preset unit time before the point can be 7:30-8:30
  • the preset unit time before the predicted time point is a preset unit time before the preset unit time at the predicted time point
  • the predicted time The preset unit time at 8:30 is 8:00-9:00
  • the preset unit time before the predicted time at this time can be 7:00-8:00.
  • the first thermal-related parameter and the second thermal-related parameter may be thermal related parameters in two consecutive preset unit times in the same comprehensive recommendation area, and thus may be based on the first thermal-related parameter corresponding to the comprehensive recommendation area And the second thermal-related parameter, the preset weight of the thermal-related parameter, and the preset second manual adjustment parameter, to determine the thermal trend data of the corresponding comprehensive recommendation area.
  • the first thermal-related parameter and the second thermal-related parameter, the preset weight of the thermal-related parameter, and the correspondence between the preset second manual adjustment parameter and the thermal trend data can be pre-set according to the needs.
  • the embodiments of the invention are not limited.
  • the second manual adjustment parameter may also be preset according to requirements, which is not limited in this embodiment of the present invention.
  • the preset weights of the heat-related parameters used when acquiring the thermal trend data may be the same as the preset weights of the heat-related parameters when acquiring the real-time thermal data, of course, they may not be completely the same. Therefore, this embodiment of the present invention is also not limited.
  • the thermal trend data may be set as the weighted average of the ratio of each first thermal-related parameter and the corresponding second thermal-related parameter within the same reference day, and the sum of the second manual adjustment parameters.
  • the obtained second thermal related parameters also include traffic state parameter X2, positioning information parameter Y2, consumption information parameter Z2 and merchant information parameter O2, and the weights of the respective thermal related parameters are also ⁇ 1, ⁇ 2, ⁇ 3 and ⁇ 4,
  • the second manual adjustment parameter is T2
  • the reference number of days is N, that is, the first thermal related parameter in N preset unit times and the second thermal related parameter in N preset unit times can be obtained. Then, the thermal trend data at this time can be
  • Step 270 based on the heat map data, thermally render and display the comprehensive recommendation area.
  • the step 270 may further include:
  • Sub-step 271 based on the real-time thermal data, thermally render and display the comprehensive recommendation area.
  • thermal rendering and display can be performed directly in the corresponding comprehensive recommended area.
  • Sub-step 272 displaying the thermal trend data in the comprehensive recommendation area in a preset manner.
  • the thermal trend data in order to facilitate the user to intuitively understand the thermal change trend in the corresponding comprehensive recommendation area according to the thermal trend data displayed in the comprehensive recommendation area, the thermal trend data may be displayed in the comprehensive recommendation area in a preset manner.
  • the specific preset manner may be preset according to requirements, and this embodiment of the present invention is not limited.
  • the second preset value range can be preset according to requirements, which is not limited in this embodiment of the present invention.
  • the second preset value range can be set to 1, and so on.
  • thermal trend data that is determined to be an upward trend it can be represented in the corresponding comprehensive recommendation area by a small red upward arrow, and for the thermal trend data that is determined to be a downward trend, it can be displayed in the corresponding comprehensive recommendation by a green downward arrow It is displayed in the area, and there is no need to make any representation for the thermal trend data determined as a flat trend.
  • Step 280 when receiving the user's enlargement request for a partial area in the comprehensive recommendation area, obtain the merchant data of the merchant in the partial area that matches the recommended tag combination.
  • the comprehensive recommendation area can contain more content, which can include catering, entertainment, attractions, etc., and it can include the area of interest to the user, or it can contain the area of interest to the user, then if If the user wants to know more about a certain area in the comprehensive recommendation area, he can enlarge the area on the map, and in order to make the user more clearly understand the business data in the enlarged area that matches the combination of the recommended label input Then, upon receiving an enlargement request of the user for a partial area in the comprehensive recommendation area, the merchant data of the merchant in the partial area that matches the recommended tag combination may be obtained.
  • the merchant data can include any reference data that can characterize the relevant information of the merchant, such as, but not limited to, hotel inventory information, restaurant queuing information, theater remaining ticket amount, scenic spot remaining ticket amount, merchant rating information, merchant featured recommendation and merchant group purchase At least one of the information.
  • the above merchant data can be obtained by any available method, which is not limited in the embodiment of the present invention.
  • Step 290 Adjust the heat map data of the partial area according to the merchant data, and adjust the thermal rendering effect of the partial area based on the adjusted heat map data.
  • the heat map data of the partial area may be further adjusted according to the merchant data, and the partial area may be adjusted based on the adjusted heat map data Thermal rendering effect.
  • the thermal-related parameters of some areas can be adjusted according to the available data in the merchant data, thereby adjusting the real-time thermal data and/or thermal trend data of the partial areas, and further adjusting the thermal rendering effect of the corresponding partial areas, and so on.
  • the specific adjustment strategy may be pre-set according to requirements, and this embodiment of the present invention is not limited.
  • Step 2110 rendering the merchant data into the partial area.
  • the merchant data can also be directly rendered into the corresponding partial area, and preferably also The business data of each business can be rendered above the business icon of the corresponding business, so that the user can intuitively understand the real-time business data of the relevant business.
  • the merchant data may be displayed in a corresponding partial area in a table format, and so on.
  • the specific merchant data rendering method may be preset according to requirements, which is not limited in this embodiment of the present invention.
  • the merchant data may include but is not limited to at least one of hotel inventory information, restaurant queuing information, theater remaining ticket amount, scenic spot remaining ticket amount, and merchant rating information.
  • a recommended label combination input by a user can be obtained; based on the recommended label combination, a comprehensive recommended area corresponding to the recommended label combination is found; and the heat of the integrated recommended area is determined Figure data; thermally render and display the comprehensive recommended area based on the heat map data.
  • the initial recommendation area corresponding to the recommended label combination may also be determined according to the label type of each label in the recommended label combination and the preset label priority; the initial recommendation Areas include alternative recommended areas and/or eliminated recommended areas; based on the recommended label combination and the number of labels in the recommended label combination that match the initial recommended area, determine the initial recommended area and the recommended label combination The degree of fit; based on the number of candidate recommended areas in the initial recommended area, and the fit of the combination of the initial recommended area and the recommended label, select a comprehensive recommended area from the initial recommended areas.
  • the second-level merchant matching the second-level label determines the low-priority recommendation area based on the second-level merchant and the preset recommended area radius; in response to finding only the third A third-tier merchant with a matching label of the rank, or a merchant that does not find a match with a label of another rank in the high-priority recommendation area, confirms that the high-priority recommendation area is a eliminated recommendation area; A merchant matching the third-level label is found in the priority recommendation area, confirming that the combination of the high priority recommendation area and the low priority recommendation area is an alternative recommendation area; in response to not finding in the low priority recommendation area Go to the merchant that matches the label of the third level, and confirm that the combination of the high priority recommendation area and the low priority recommendation area is a eliminated recommendation area. Therefore, the accuracy of the comprehensive recommendation area can be further improved.
  • the third aspect in the embodiment of the present invention, it can also be determined according to the ratio of the number of labels in the recommended label combination that belong to the same label type and match the initial recommended area, and the total number of labels included in the label type
  • the single type fit degree of the label type; the average value of the single type fit degree of each tag type in the initial recommendation area is obtained as the fit degree of the combination of the initial recommendation area and the recommended label combination.
  • a first preset number of candidate recommendation regions with the highest degree of fit with the recommended tag combination are selected from the candidate recommendation regions As the comprehensive recommendation area; in response to the number of candidate recommendation areas being less than the first preset number and greater than or equal to 1, acquiring all the candidate recommendation areas as the comprehensive recommendation area; in response to the candidate The number of recommendation areas is zero, and the elimination recommendation area with the highest degree of matching with the recommendation tag combination is selected from the elimination recommendation areas as the comprehensive recommendation area. It can also improve the effect and accuracy of the comprehensive recommendation area.
  • the reference days of the heat map data may also be determined according to the current date and a preset reference period; acquired within the reference days and set by the user The first thermal-related parameter within a preset unit time corresponding to the predicted time point; based on the first thermal-related parameter, the preset weight of the thermal-related parameter, and the preset first manual adjustment parameter, determine the Real-time thermal data; acquiring a second thermal-related parameter within a preset unit time before the predicted time point within the reference number of days; based on the first thermal-related parameter and the second thermal-related parameter, The preset weight of the thermal related parameter and the preset second manual adjustment parameter determine the thermal trend data. Therefore, the accuracy of the heat map data can be improved, and the comprehensive recommendation effect of the region can be improved.
  • the merchant data of the merchant in the partial area that matches the recommended tag combination may also be obtained Adjusting the heat map data of the partial area according to the merchant data, and adjusting the thermal rendering effect of the partial area based on the adjusted heat map data; rendering the merchant data into the partial area. Therefore, it is convenient for the user to understand the business data of the region of interest more intuitively and in detail, thereby improving the comprehensive recommendation effect of the region.
  • a regional comprehensive recommendation device provided by an embodiment of the present invention is described in detail.
  • FIG. 3 shows a structural schematic diagram of a region comprehensive recommendation device in an embodiment of the present invention.
  • the device may specifically include the following modules:
  • the recommended label combination obtaining module 310 is used to obtain a recommended label combination input by a user.
  • the integrated recommendation area search module 320 is configured to search for an integrated recommendation area corresponding to the recommended label combination based on the recommended label combination.
  • the heat map data confirmation module 330 is used to determine the heat map data of the comprehensive recommendation area.
  • the thermal rendering module 340 is configured to thermally render and display the comprehensive recommended area based on the thermal map data.
  • the recommended label combination input by the user can be obtained; based on the recommended label combination, a comprehensive recommended region corresponding to the recommended label combination is searched; the heat map data of the integrated recommended region is determined; The heat map data thermally renders and displays the comprehensive recommended area. This has achieved the beneficial effect of improving the accuracy of multi-type comprehensive recommendations.
  • a regional comprehensive recommendation device provided by an embodiment of the present invention is described in detail.
  • FIG. 4 shows a schematic structural diagram of a region comprehensive recommendation device in an embodiment of the present invention.
  • the device may specifically include the following modules:
  • the recommended label combination obtaining module 410 is used to obtain a recommended label combination input by a user.
  • the integrated recommendation area search module 420 is configured to search for an integrated recommendation area corresponding to the recommended label combination based on the recommended label combination.
  • the comprehensive recommendation area search module 420 may further include:
  • the initial recommendation area confirmation sub-module 421 is used to determine the initial recommendation area corresponding to the recommended label combination according to the label type of each label in the recommended label combination and the preset label priority; Select recommended areas and/or eliminate recommended areas;
  • the matching degree confirmation sub-module 422 is used to determine the degree of fit between the initial recommended area and the recommended label combination according to the recommended label combination and the number of labels in the recommended label combination that match the initial recommended area;
  • the integrated recommendation area search sub-module 423 is used to select an integrated area from the initial recommendation area according to the number of candidate recommendation areas in the initial recommendation area and the fit of the combination of the initial recommendation area and the recommended label Recommended area.
  • the initial recommendation area confirmation submodule 421 may further include:
  • the designated location acquiring unit is configured to acquire the designated location of the user.
  • a high-priority business search unit used to find a high-priority business that matches a high-priority label with the specified location as the center and a preset search distance as the radius according to the label priority;
  • a high priority recommendation area confirmation unit configured to determine a high priority recommendation area based on the high priority level merchant and a preset recommended area radius
  • the recommended area judgment unit is configured to confirm that the high-priority recommended area is an alternative recommended area or a eliminated recommended area in response to whether a merchant matching a label with a low priority level is found in the high-priority recommended area;
  • the recommended area judgment unit may further include:
  • a first candidate recommendation area confirmation subunit configured to confirm that the high priority recommendation area is a candidate recommendation area in response to finding a merchant matching a label with a low priority level in the high priority recommendation area;
  • a low-priority recommendation area confirmation subunit for responding to finding only a second-level merchant matching a second-level label in the high-priority recommendation area, based on the second-level merchant and a preset recommended area radius To determine the low priority recommendation area;
  • the first elimination recommendation area confirmation subunit is used to respond to that only a third-level merchant matching the third-level label is found in the high-priority recommendation area, or is not found in the high-priority recommendation area Merchants that match labels of other levels, confirm that the high-priority recommended area is a eliminated recommended area;
  • the second alternative recommendation area confirmation subunit is used to confirm the combination of the high priority recommendation area and the low priority recommendation area in response to finding a merchant matching the third-level label in the low priority recommendation area Recommended alternative area;
  • the second elimination recommendation area confirmation unit is configured to confirm that the combination of the high-priority recommendation area and the low-priority recommendation area is in response to that no merchant matching the third-level label is found in the low-priority recommendation area Eliminate recommended areas.
  • the fitting degree confirmation submodule 422 may further include:
  • a single-type fit degree confirmation unit used to determine the label type according to the ratio of the number of labels in the recommended label combination that belong to the same label type and match the initial recommended area, and the total number of labels included in the label type Single type fit
  • the fit degree confirmation unit is configured to obtain an average value of a single type fit degree of each label type in the initial recommendation area as a fit degree of the combination of the initial recommendation area and the recommended label.
  • the comprehensive recommendation area search sub-module 423 may further include:
  • a first integrated recommendation area search unit configured to select the first with the highest degree of fit with the recommended label combination from the candidate recommendation areas in response to the number of candidate recommendation areas being greater than or equal to a first preset number
  • a preset number of candidate recommendation areas are used as the comprehensive recommendation area
  • a second integrated recommendation area search unit configured to obtain all the candidate recommendation areas as the comprehensive recommendation area in response to the number of candidate recommendation areas being less than the first preset number and greater than or equal to 1;
  • a third comprehensive recommendation area search unit used to select the elimination recommendation area with the highest degree of matching with the recommendation tag combination as the comprehensive recommendation from the elimination recommendation areas in response to the number of candidate recommendation areas being zero area.
  • the thermal-related parameter acquisition module 430 is configured to acquire thermal-related parameters in the comprehensive recommendation area.
  • the thermal-related parameters include at least one of traffic state parameters, positioning information parameters, consumption information parameters, and merchant information parameters;
  • the heat map data includes real-time thermal data and/or Thermal trend data.
  • the heat map data confirmation module 440 is configured to determine the heat map data of the comprehensive recommendation area based on the thermal related parameters.
  • the heat map data confirmation module 440 may further include:
  • the referenceable day number determination sub-module 441 is used to determine the referenceable number of days of the heat map data according to the current date and a preset referenceable period;
  • a first thermal-related parameter acquisition submodule 442 configured to acquire a first thermal-related parameter within a preset unit time corresponding to the predicted time point set by the user within the reference number of days;
  • the real-time thermal data determination submodule 443 is used to determine the real-time thermal data based on the first thermal-related parameter, the preset weight of the thermal-related parameter, and the preset first manual adjustment parameter;
  • a second thermal-related parameter acquisition submodule 444 configured to acquire a second thermal-related parameter within a preset unit time before the predicted time point within the reference number of days;
  • the thermal trend data acquisition sub-module 445 is used to determine the temperature based on the first thermal-related parameter and the second thermal-related parameter, the preset weight of the thermal-related parameter, and the preset second manual adjustment parameter Thermal trend data.
  • the thermal rendering module 450 is configured to thermally render and display the comprehensive recommended area based on the thermal map data.
  • the merchant data acquisition module 460 is configured to acquire merchant data of merchants matching the recommended tag combination in the partial area when receiving the user's enlargement request for the partial area in the comprehensive recommendation area.
  • the thermal rendering adjustment module 470 is configured to adjust the heat map data of the partial area according to the merchant data, and adjust the thermal rendering effect of the partial area based on the adjusted heat map data.
  • the merchant data rendering module 480 is configured to render the merchant data into the partial area.
  • a recommended label combination input by a user can be obtained; based on the recommended label combination, a comprehensive recommended area corresponding to the recommended label combination is found; and the heat of the integrated recommended area is determined Figure data; thermally render and display the comprehensive recommended area based on the heat map data.
  • the initial recommendation area corresponding to the recommended label combination may also be determined according to the label type of each label in the recommended label combination and the preset label priority; the initial recommendation Areas include alternative recommended areas and/or eliminated recommended areas; based on the recommended label combination and the number of labels in the recommended label combination that match the initial recommended area, determine the initial recommended area and the recommended label combination The degree of fit; based on the number of candidate recommended areas in the initial recommended area, and the fit of the combination of the initial recommended area and the recommended label, select a comprehensive recommended area from the initial recommended areas.
  • the second-level merchant matching the second-level label determines the low-priority recommendation area based on the second-level merchant and the preset recommended area radius; in response to finding only the third A third-tier merchant with a matching label of the rank, or a merchant that does not find a match with a label of another rank in the high-priority recommendation area, confirms that the high-priority recommendation area is a eliminated recommendation area; A merchant matching the third-level label is found in the priority recommendation area, confirming that the combination of the high priority recommendation area and the low priority recommendation area is an alternative recommendation area; in response to not finding in the low priority recommendation area Go to the merchant that matches the label of the third level, and confirm that the combination of the high priority recommendation area and the low priority recommendation area is a eliminated recommendation area. This can further improve the accuracy of the comprehensive recommendation area.
  • the third aspect in the embodiment of the present invention, it can also be determined according to the ratio of the number of labels in the recommended label combination that belong to the same label type and match the initial recommended area, and the total number of labels included in the label type
  • the single-type fit degree of the label type; the average value of the single-type fit degree of each tag type in the initial recommendation area is obtained as the fit degree of the initial recommendation area with the recommended label combination.
  • a first preset number of candidate recommendation regions with the highest degree of fit with the recommended tag combination are selected from the candidate recommendation regions As the comprehensive recommendation area; in response to the number of candidate recommendation areas being less than the first preset number and greater than or equal to 1, acquiring all the candidate recommendation areas as the comprehensive recommendation area; in response to the candidate The number of recommendation areas is zero, and the elimination recommendation area with the highest degree of matching with the recommendation tag combination is selected from the elimination recommendation areas as the comprehensive recommendation area. It can also improve the effect and accuracy of the comprehensive recommendation area.
  • the reference days of the heat map data may also be determined according to the current date and a preset reference period; acquired within the reference days and set by the user The first thermal-related parameter within a preset unit time corresponding to the predicted time point; based on the first thermal-related parameter, the preset weight of the thermal-related parameter, and the preset first manual adjustment parameter, determine the Real-time thermal data; acquiring a second thermal-related parameter within a preset unit time before the predicted time point within the reference number of days; based on the first thermal-related parameter and the second thermal-related parameter, The preset weight of the thermal related parameter and the preset second manual adjustment parameter determine the thermal trend data. Therefore, the accuracy of the heat map data can be improved, and the comprehensive recommendation effect of the region can be improved.
  • the merchant data of the merchant in the partial area that matches the recommended tag combination may also be obtained Adjusting the heat map data of the partial area according to the merchant data, and adjusting the thermal rendering effect of the partial area based on the adjusted heat map data; rendering the merchant data into the partial area. Therefore, it is convenient for the user to understand the business data of the region of interest more intuitively and in detail, thereby improving the comprehensive recommendation effect of the region.
  • An electronic device is also disclosed in the embodiments of the present invention, including:
  • a processor a memory, and a computer program stored on the memory and executable on the processor.
  • the processor executes the program, the aforementioned comprehensive regional recommendation method is implemented.
  • An readable storage medium is also disclosed in the embodiments of the present invention, and when the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the aforementioned method of comprehensive regional recommendation.
  • the description is relatively simple, and the relevant part can be referred to the description of the method embodiment.
  • the various component embodiments of the present invention may be implemented in hardware, or implemented in software modules running on one or more processors, or implemented in a combination thereof.
  • a microprocessor or a digital signal processor (DSP) may be used to implement some or all functions of some or all components in a computing processing device according to an embodiment of the present invention.
  • the present invention may also be implemented as a device or device program (eg, computer program and computer program product) for performing part or all of the method described herein.
  • Such a program implementing the present invention may be stored on a computer-readable medium, or may have the form of one or more signals.
  • Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.
  • FIG. 5 shows a computing processing device that can implement the method according to the present invention.
  • the computing processing device traditionally includes a processor 510 and a computer program product or computer readable medium in the form of a memory 520.
  • the memory 520 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM.
  • the memory 520 has a storage space 530 for program code 531 for performing any of the method steps described above.
  • the storage space 530 for program codes may include various program codes 531 for implementing various steps in the above method, respectively. These program codes can be read from or written into one or more computer program products.
  • Such computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks.
  • Such a computer program product is usually a portable or fixed storage unit as described with reference to FIG. 6.
  • the storage unit may have storage sections, storage spaces, and the like arranged similarly to the memory 520 in the computing processing device of FIG. 5.
  • the program code may be compressed in an appropriate form, for example.
  • the storage unit includes computer readable code 531', that is, code that can be read by, for example, a processor such as 510, which, when executed by a computing processing device, causes the computing processing device to perform the method described above The various steps.
  • modules in the device in the embodiment can be adaptively changed and set in one or more devices different from the embodiment.
  • the modules or units or components in the embodiments may be combined into one module or unit or component, and in addition, they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and/or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstract and drawings) and any method so disclosed may be adopted in any combination All processes or units of equipment are combined. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose.
  • the various component embodiments of the present invention may be implemented in hardware, or implemented in software modules running on one or more processors, or implemented in a combination thereof.
  • a microprocessor or a digital signal processor (DSP) may be used to implement some or all functions of some or all components in the regional comprehensive recommendation device according to an embodiment of the present invention.
  • DSP digital signal processor
  • the present invention may also be implemented as a device or device program (eg, computer program and computer program product) for performing part or all of the method described herein.
  • Such a program implementing the present invention may be stored on a computer-readable medium, or may have the form of one or more signals.
  • Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种区域综合推荐方法、电子设备及可读存储介质,所述方法包括:获取用户输入的推荐标签组合(110);基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域(120);确定所述综合推荐区域的热图数据(130);基于所述热图数据,对所述综合推荐区域进行热力渲染并显示(140)。所述方法解决了现有的搜索推荐方法在多种类型综合推荐方面的效果欠佳的技术问题。

Description

区域综合推荐方法、电子设备及可读存储介质
本申请要求在2019年1月8日提交中国专利局、申请号为201910017354.X、发明名称为“区域综合推荐方法、装置、电子设备及可读存储介质”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
本发明涉及数据处理技术领域,具体涉及一种区域综合推荐方法、电子设备及可读存储介质。
背景技术
随着移动互联网与智能终端等技术的普及,餐厅、电影院、商铺、宾馆等传统服务也从线下服务发展到了线上服务。用户随时随地都可以通过在线搜索找到其想要的服务,并在线预订这些线上服务,也可以对这些服务体验评论、打分等。而且现有的搜索还可以根据用户需求为用户推荐相关的地点,以辅助用户进行选择。
发明内容
本发明提供一种区域综合推荐方法、电子设备及可读存储介质,以部分或全部解决现有技术中区域综合推荐过程相关的上述问题。
依据本发明第一方面,提供了一种区域综合推荐方法,包括:
获取用户输入的推荐标签组合;
基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域;
确定所述综合推荐区域的热图数据;
基于所述热图数据,对所述综合推荐区域进行热力渲染并显示。
根据本发明的第二方面,提供了一种区域综合推荐装置,包括:
推荐标签组合获取模块,用于获取用户输入的推荐标签组合;
综合推荐区域查找模块,用于基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域;
热图数据确认模块,用于确定所述综合推荐区域的热图数据;
热力渲染模块,用于基于所述热图数据,对所述综合推荐区域进行热力渲染并显示。
根据本发明的第三方面,提供了一种电子设备,包括:
处理器、存储器以及存储在所述存储器上并可在所述处理器上运行的计算机程序,其特征在于,所述处理器执行所述程序时实现前述的区域综合推 荐方法。
根据本发明的第四方面,提供了一种计算机程序,包括计算机可读代码,当所述计算机可读代码在计算处理设备上运行时,导致所述计算处理设备执行前述的区域综合推荐方法。
根据本发明的第五方面,提供了一种计算机可读介质,其中存储了如第四方面所述的计算机程序。
根据本发明的区域综合推荐方法,可以获取用户输入的推荐标签组合;基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域;确定所述综合推荐区域的热图数据;基于所述热图数据对所述综合推荐区域进行热力渲染并显示。由此解决了现有的区域综合推荐方法在多种类型综合推荐方面的效果欠佳的技术问题。
上述说明仅是本发明技术方案的概述,为了能够更清楚了解本发明的技术手段,而可依照说明书的内容予以实施,并且为了让本发明的上述和其它目的、特征和优点能够更明显易懂,以下特举本发明的具体实施方式。
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,而并不认为是对本发明的限制。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示出了根据本发明一个实施例的一种区域综合推荐方法的步骤流程图;
图2示出了根据本发明一个实施例的一种区域综合推荐方法的步骤流程图;
图3示出了根据本发明一个实施例的一种区域综合推荐装置的结构示意图;
图4示出了根据本发明一个实施例的一种区域综合推荐装置的结构示意图;
图5示意性地示出了用于执行根据本发明的方法的计算处理设备的框图;以及
图6示意性地示出了用于保持或者携带实现根据本发明的方法的程序代码的存储单元。
具体实施例
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。
目前的搜索方案在支持单一目标推荐方面尚可,而在提供多种类型综合推荐方面效果欠佳,例如:有些用户想吃西餐又想看电影还想住高星酒店。如分开检索又较难得到最优组合,那么用户很可能放弃该次计划;或者,有些用户对环境还有一定倾向,喜欢热闹或者清净,等等,而目前的搜索方案还难以很好地满足用户的这些需求。为了解决这些问题,本发明实施例提供了以下技术方案。
实施例一
详细介绍本发明实施例提供的一种区域综合推荐方法。
参照图1,示出了本发明实施例中一种区域综合推荐方法的步骤流程图。
步骤110,获取用户输入的推荐标签组合。
在实际应用中,如果用户需要搜索满足其多种需求的综合区域,那么用户在搜索相应的综合推荐区域时,首先则需要输入或者是选择其多种需求所对应的标签,进而可以获取得到用户输入的包含多个标签的推荐标签组合。
例如,用户在搜索时可以选择相关感兴趣产品,那么相应的搜索平台可以进一步提供多个在用户感兴趣产品下的标签,进而用户可以在搜索平台提供的标签中选中部分其偏好的标签,或者是自行手动输入其他标签,从而可以利用用户选定的标签以及用户手动输入的标签构建得到相应用户当前的推荐标签组合。
步骤120,基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域。
在确定了用户输入的推荐标签组合之后,则可以进一步基于推荐标签组合,查找与其推荐标签组合对应的综合推荐区域。
其中,与推荐标签组合对应的综合推荐区域,可以理解为在相应的综合推荐区域中包含满足相应的推荐标签组合中的各个标签或者是部分推荐标签对应的商家。其中的商家可以包括但不限于景点、酒店、餐饮、娱乐等中的至少一种。在本发明实施例中,可以根据需求预先设置与推荐标签组合对应的综合推荐区域需要满足的条件,对此本发明实施例不加以限 定。
步骤130,确定所述综合推荐区域的热图数据。
热图是以特殊高亮的形式显示访客热衷的页面区域和访客所在的地理区。热图是指用热谱图展示用户在网站上的行为。浏览量大、点击量大的地方呈红色,浏览量小、点击量少的地方呈无色、蓝色。为了针对综合推荐区域进行热力渲染,需要先确定综合推荐区域的热图数据。在本发明实施例中,可以通过任何可用方法获取综合推荐区域的热图数据,对此本发明实施例不加以限定。
例如,热图数据可以包括但不限于实时热力数据、热力趋势数据,等等。其中实时热力数据可以表征综合推荐区域的当前热力情况,而热力趋势数据则可以表征综合推荐区域的未来热力情况走势。具体的可以基于综合推荐区域中包含的内容的实时数据以及历史数据分别获取其热图数据。
步骤140,基于所述热图数据对所述综合推荐区域进行热力渲染并显示。
在确定各个综合推荐区域的热图数据之后,为了方便用户将热图数据与相应的综合推荐区域直观对应,还可以进一步基于热图数据对相应的综合推荐区域进行热力渲染并显示,那么用户则可以直观了解到各个综合推荐区域的综合热力情况。其中具体的渲染方式可以根据需求进行预先设置,对此本发明实施例不加以限定。例如,可以设置渲染方式为:热图数据越高,则相应综合推荐区域中的渲染色调的波长越大,等等。
根据本发明的区域综合推荐方法,可以获取用户输入的推荐标签组合;基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域;确定所述综合推荐区域的热图数据;基于所述热图数据对所述综合推荐区域进行热力渲染并显示。由此解决了现有的区域综合推荐方法在多种类型综合推荐方面的效果欠佳的技术问题。取得了提高多类型综合推荐准确性的有益效果。
实施例二
详细介绍本发明实施例提供的一种区域综合推荐方法。
参照图2,示出了本发明实施例中一种区域综合推荐方法的步骤流程图。
步骤210,获取用户输入的推荐标签组合。
步骤220,根据所述推荐标签组合中各标签的标签类型、预设的标签优先级,确定与所述推荐标签组合对应的初始推荐区域;所述初始推荐区域 包括备选推荐区域和/或淘汰推荐区域。
在实际应用中,商家可以分为多种不同的类型,例如酒店、景点、餐饮、娱乐,等等。那么用户在输入搜索的标签时,可以分别针对不同的商家输入标签,因此用户输入的推荐标签组合中的标签也可以分为不同的标签类型,例如上述的可以针对各标签对应的商家类型从而确定各个标签的标签类型,当前在本发明实施例中,也可以基于其他策略确定推荐标签组合中各个标签的标签类型,对此本发明实施例不加以限定。
而如果针对各标签对应的商家类型从而确定各个标签的标签类型,那么相应地,根据各标签即可确定具体相应的标签所要搜索的产品类型,也即商家类型。
例如:酒店产品下的标签可以包括“星级”,如“三星”、“四星”、“五星”等,包括“品牌”,如“汉庭”、“如家”等等;而餐饮产品下标签可以包括“菜系”,如“川菜”、“鲁菜”、“粤菜”等,包括“口味”,如“辣”、“酸”、“甜”等;而景点产品下的标签可以包括“古迹”,“园林”等;娱乐产品下的标签可以包括“团购”、“休闲”、“唱歌”、“打球”,等等。
那么,如果用户输入的推荐标签组合中包括“三星”、“鲁菜”、“园林”等标签,那么则可以确定各个标签的标签类型依次分别为酒店标签、餐饮标签、景点标签。
另外,在实际应用中,如果用户输入的推荐标签组合中包含不同标签类型的标签,那么在基于推荐标签组合进行综合推荐区域检索时,一般很少存在能够均衡地满足各个标签类型的区域,而且不同标签类型下对应的产品数量也会有所不同,那么如果按照各个标签类型对应的产品数量从低到高的顺序进行搜索,从而确定初始推荐区域,可以相对提高搜索速度。因此可以设置预设的标签优先级为对应产品数量越低的标签类型的标签优先级越高。当然,在本发明实施例中,也可以根据需求另外设置标签优先级,对此本发明实施例不加以限定。
那么在确定了推荐标签组合中各标签的标签类型,以及各标签类型的标签优先级,进而则可以根据所述推荐标签组合中各标签的标签类型、预设的标签优先级,确定与所述推荐标签组合对应的初始推荐区域。而且,在本发明实施例中,根据推荐标签组合中各标签的标签类型、预设的标签优先级,可能会搜索得到包含满足推荐标签组合中全部标签的商家的区域,也可能搜索得到只包含满足推荐标签组合中部分标签的商家的区域, 那么对于上述的包含满足推荐标签组合中全部标签的商家的区域,则可以称为备选推荐区域,而对于上述的只包含满足推荐标签组合中部分标签的商家的区域,则可以称为淘汰推荐区域。因此,在本发明实施例中的初始推荐区域可以包括备选推荐区域和/或淘汰推荐区域。
可选地,在本发明实施例中,所述标签类型包括景点标签,酒店标签、餐饮标签和娱乐标签中的至少一种;所述预设的标签优先级包括景点标签为第一等级,酒店标签为第二等级,餐饮标签与娱乐标签为第三等级。
如前述,在实际应用中用户在区域内搜索的产品一般是商家,具体的可以包括景点、酒店、餐饮、娱乐,等等。那么相应的则可以将标签类型划分为景点标签、酒店标签、餐饮标签、娱乐标签,因此在本发明实施例中的标签类型可以包括景点标签、酒店标签、餐饮标签和娱乐标签中的至少一种。
而且一般而言在一定区域内景点最少可选产品也最少,酒店其次,而餐饮和娱乐场所最多且可选产品也非常丰富。因此预设的标签优先级可以包括景点标签为第一等级,酒店标签为第二等级,餐饮标签与娱乐标签为第三等级。
可选地,在本发明实施例中,所述步骤220进一步可以包括:
子步骤221,获取所述用户的指定位置。
其中的指定位置可以为相应用户设定的用以确定综合推荐区域的参照点,例如可以用户的指定位置为中心,按照相应用户的推荐标签组合由近及远地查找与相应的推荐标签组合匹配的综合推荐区域,等等。具体的指定位置可以由用户进行自定义设置,对此本发明实施例不加以限定。而如果用户并未设置指定位置,则可以直接取相应用户的当前位置作为其指定位置。
子步骤222,根据所述标签优先级,以所述指定位置为中心,以预设搜索距离为半径,查找与高优先等级的标签匹配的高优先等级商家。
子步骤223,基于所述高优先等级商家以及预设的推荐区域半径,确定高优先推荐区域。
子步骤224,响应于在所述高优先推荐区域中是否查找到与低优先等级的标签匹配的商家,确认所述高优先推荐区域为备选推荐区域或淘汰推荐区域。
可选地,在本发明实施例中,所述子步骤224进一步可以包括:
子步骤2241,响应于在所述高优先推荐区域中查找到与低优先等级的标签匹配的商家,确认所述高优先推荐区域为备选推荐区域。
子步骤2242,响应于在所述高优先推荐区域中仅查找到与第二等级的标签匹配的第二等级商家,基于所述第二等级商家以及预设的推荐区域半径,确定低优先推荐区域;
子步骤2243,响应于在所述高优先推荐区域中仅查找到与第三等级的标签匹配的第三等级商家,或者是在所述高优先推荐区域中未查找到与其他等级的标签匹配的商家,确认所述高优先推荐区域为淘汰推荐区域;
子步骤2244,响应于在所述低优先推荐区域中查找到与第三等级的标签匹配的商家,确认所述高优先推荐区域与所述低优先推荐区域的组合为备选推荐区域;
子步骤2245,响应于在所述低优先推荐区域中未查找到与第三等级的标签匹配的商家,确认所述高优先推荐区域与所述低优先推荐区域的组合为淘汰推荐区域。
在本发明实施例中,为了提高推荐标签组合的匹配效率,可以基于各个标签类型的优先级从高到低的顺序对各个标签类型下的标签进行匹配。因此,在获取相应用户的指定位置之后,首先可以根据所述标签优先级,以所述指定位置为中心,以预设搜索距离为半径,查找与推荐标签组合中高优先等级的标签匹配的高优先等级商家,进而可以基于搜索到的高优先等级商家以及预设的推荐区域半径,确定高优先推荐区域。
其中的预设搜索距离和推荐区域半径可以根据需求进行预先设置,对此本发明实施例不加以限定。而且,其中的指定位置可以由用户根据搜索需求进行自定义设置,而如果用户未设置指定位置,则可以默认以用户的当前位置作为其指定位置。高优先等级对应的标签类型也可以根据需求进行预先设置,对此本发明实施例不加以限定。例如,可以设置高优先等级对应的标签类型包括上述的景点标签,或者可以包括上述的景点标签以及酒店标签,等等。
进而可以在高优先推荐区域内查找与低优先等级的标签匹配的商家,如果在高优先推荐区域中查找到与至少一个低优先等级的标签匹配的商家,那么作为响应则可以确认相应的高优先推荐区域为一个备选推荐区域;否则可以确认相应的高优先推荐区域为一个淘汰推荐区域。或者,在本发明实施例中,还可以设置如果在高优先推荐区域中查找到与每个低优先等级下的至少一个标签匹配的商家,那么作为响应则可以确认相应的高 优先推荐区域为一个备选推荐区域;否则可以确认相应的高优先推荐区域为一个淘汰推荐区域;等等。具体的备选推荐区域和淘汰推荐区域分别对应的标签匹配条件可以根据需求进行预先设置,对此本发明实施例不加以限定。
其中,在高优先推荐区域中查找到与某一低优先等级的标签匹配的商家,可以理解为在相应的高优先推荐区域内可以查找到与相应低优先等级下的至少一个标签匹配的商家。而且上述的低优先等级的标签可以包括推荐标签组合中除高优先等级之外的等级下的标签。
例如,假设对于推荐标签组合,包含有上述的标签“五星”、“汉庭”、“如家”、“鲁菜”、“口味清淡”、“古迹”、“唱歌”、“打球”,等等。其中的“五星”、“汉庭”、“如家”为酒店标签,“鲁菜”、“口味清淡”为餐饮标签,“古迹”为景点标签,“唱歌”、“打球”为娱乐标签。那么如果预设的标签优先级为景点标签为第一等级,酒店标签为第二等级,餐饮标签与娱乐标签为第三等级,且第一等级为高优先等级,其他等级均为低优先等级。
那么则可以指定位置为中心,以预设搜索距离为半径,查找与“古迹”匹配的高优先等级商家,进而可以基于所述高优先等级商家以及预设的推荐区域半径,确定高优先推荐区域E1,进而在高优先推荐区域E1中查找与酒店标签、餐饮标签与娱乐标签匹配的商家。那么如果在高优先推荐区域E1中分别查找到与“五星”、“汉庭”、“如家”中的任意一个匹配的商家,与“鲁菜”、“口味清淡”中的任意一个匹配的商家,以及“唱歌”、“打球”中的任意一个匹配的商家,则可以确认此时在高优先推荐区域E1中查找到与低优先等级的标签匹配的商家,进而可以认定相应的高优先推荐区域E1为备选推荐区域。
而如果在所述高优先推荐区域中仅查找到与第二等级的标签匹配的第二等级商家,则可以基于所述第二等级商家以及预设的推荐区域半径,确定低优先推荐区域,进而在低优先推荐区域中查找与第三等级的标签匹配的商家,如果在所述低优先推荐区域中查找到与第三等级的标签匹配的商家,确认所述高优先推荐区域与所述低优先推荐区域的组合为备选推荐区域;而如果在相应的低优先推荐区域中未查找到与第三等级的标签匹配的商家,则可以确认相应的高优先推荐区域与相应的低优先推荐区域的组合为淘汰推荐区域。
另外,如果在所述高优先推荐区域中仅查找到与第三等级的标签匹配 的第三等级商家,或者是在所述高优先推荐区域中未查找到与低优先等级的标签匹配的商家,同样可以确认所述高优先推荐区域为淘汰推荐区域。
而且,在本发明实施例中,还可以分别设置两个数据列表用于记录淘汰推荐区域和备选推荐区域。其中,淘汰列表可以用于记录淘汰推荐区域,成功列表可以用于记录备选推荐区域。另外,如果获取了各个淘汰推荐区域和备选推荐区域与相应的推荐标签组合的契合度,那么还可以按照契合度从高到低的顺序分别记录淘汰推荐区域和备选推荐区域。
进一步地,如果在子步骤222中,以所述指定位置为中心,以预设搜索距离为半径,未查找到与高优先等级的标签匹配的高优先等级商家,或者是在推荐标签组合中不包含高优先等级的标签,那么还可以进一步以所述指定位置为中心,以预设搜索距离为半径,查找与第二等级的标签匹配的第二等级商家,进而可以基于查找到的第二等级商家以及预设的推荐区域半径,确定低优先推荐区域,然后不管在低优先推荐区域中是否查找到第三等级标签匹配的商家,都可以将低优先推荐区域作为淘汰推荐区域。而如果以所述指定位置为中心,以预设搜索距离为半径,未查找到与高优先等级的标签匹配的高优先等级商家,以及与第二等级的标签匹配的第二等级商家,或者是在推荐标签组合中不包含高优先等级和第二等级的标签,那么则还可以所述指定位置为中心,以预设搜索距离为半径,查找与第三等级的标签匹配的第三等级商家,进而可以基于查找到的第三等级商家以及预设的推荐区域半径,确定低优先推荐区域,进而可以将低优先推荐区域同样作为淘汰推荐区域。当然,在本发明实施例中也可以不执行上述步骤,具体的可以根据需求进行预先设置,对此本发明实施例不加以限定。
而且,如果以所述指定位置为中心,以预设搜索距离为半径,按照上述步骤未查找到与全部等级的标签匹配的商家,则可以反馈检索失败。
步骤230,根据所述推荐标签组合,以及所述推荐标签组合中与所述初始推荐区域匹配的标签数量,确定所述初始推荐区域与所述推荐标签组合的契合度。
如前述,在实际应用中可能会搜索到多个与推荐标签匹配的初始推荐组合,很明显需要将其中与推荐标签组合契合度高的初始推荐区域作为综合推荐区域,从而可以提高综合推荐区域的准确性。因此,为了从初始推荐区域中选出最终的综合推荐区域,首先根据根据推荐标签组合,以及推荐标签组合中与各个初始推荐区域匹配的标签数量,确定相应各个初始推荐区域与相应推荐标签组合的契合度。
具体的,可以根据推荐标签组合中与某一初始推荐区域匹配的标签数量占相应推荐标签组合中标签总数的比例,确定相应初始推荐区域与相应推荐标签组合的契合度;或者是直接以推荐标签组合中与某一初始推荐区域匹配的标签数量,确定相应初始推荐区域与相应推荐标签组合的契合度;等等,具体的确定方法可以根据需求进行预先设置,对此本发明实施例不加以限定。
可选地,在本发明实施例中,所述步骤230进一步可以包括:
子步骤231,根据所述推荐标签组合中属于同一标签类型且与所述初始推荐区域匹配的标签数量,与所述标签类型包含的总标签数量的比值,确定所述标签类型的单一类型契合度。
在确定了初始推荐区域之后,为了从各初始推荐区域中选择与相应的推荐标签组合契合度较高的综合推荐区域,则需要确定各个初始推荐区域与推荐标签组合的契合度。而且,由于推荐标签组合中可能包含多个不同标签类型下的标签,而且某一初始推荐区域中可能存在与不同标签类型下的各个标签都匹配的产品,当然也可能存在根据部分标签类型下的部分标签在某一初始推荐区域中不存在相应的产品。
因此,在本发明实施例中,可以首先以标签类型为单位,根据推荐标签组合中属于同一标签类型且与所述初始推荐区域匹配的标签数量,与所述标签类型包含的总标签数量的比值,确定相应的初始推荐区域中各个标签类型的单一类型契合度。
例如,可以设置单一类型契合度=标签类型a中与初始推荐区域匹配的个数/标签类型a包含的总标签数量。其中的标签类型a可以为任意一种标签类型。
例如,假设对于推荐标签组合中包含的标签中有5个景点标签,4个餐饮标签,0个酒店标签和6个娱乐标签,而如果在某一初始推荐区域A中查找到与上述的2个景点标签匹配的景点产品,查找到与上述的1个餐饮标签匹配的餐饮产品,查找到与上述的5个娱乐标签匹配的娱乐产品,那么则可以分别得到各个标签类型的单一类型契合度分别如下:
景点标签的单一类型契合度=2/5=40%;
餐饮标签的单一类型契合度=1/4=25%;
娱乐标签的单一类型契合度=5/6=83.3%;
而由于推荐标签组合中不包含酒店标签,那么则可以不考虑酒店标签的单一类型契合度。
子步骤232,获取所述初始推荐区域中各个标签类型的单一类型契合度的平均值作为所述初始推荐区域与所述推荐标签组合的契合度。
在确定各个标签类型的单一类型契合度之后,为了确定相应的初始推荐区域与推荐标签组合的契合度,则可以进一步获取相应的初始推荐区域中各个标签类型的单一类型契合度的平均值作为相应的初始推荐区域与所述推荐标签组合的契合度。
例如,对于上述的推荐标签组合,以及推荐标签组合中的各个标签类型在初始推荐区域A中的单一类型契合度,那么则可以得到初始推荐区域A与相应的推荐标签组合的契合度为(40%+25%+83.3%)/3,即为49.4%。
当然,在本发明实施例中,根据需求还可以分别设置各个标签类型的权重,进而可以获取初始推荐区域中各个标签类型的单一类型契合度的加权平均值作为所述初始推荐区域的与所述推荐标签组合的契合度。其中各个标签类型的权重可以根据需求进行预先设置,对此本发明实施例不加以限定。
步骤240,根据所述初始推荐区域中备选推荐区域的数量,以及所述初始推荐区域与所述推荐标签组合的契合度,从所述初始推荐区域中选定综合推荐区域。
在确定了各个初始推荐区域与推荐标签组合的契合度之后,则可以进一步根据所述初始推荐区域中备选推荐区域的数量,以及所述初始推荐区域与所述推荐标签组合的契合度,从所述初始推荐区域中选定综合推荐区域。
而且如上述可知,初始推荐区域中的备选推荐区域中可以包含与各等级的标签类型都存在匹配的商家;而在淘汰推荐区域中则只包含部分等级的标签类型匹配的商家。因此,为了使综合推荐区域能够满足用户的检索需求,可以优先将备选推荐区域作为综合推荐区域,但是如果针对某一推荐标签组合的备选推荐区域较少,低于预设数值,甚至是没有查找到与某一推荐标签组合匹配的备选推荐区域,那么则可以考虑将与相应的推荐标签组合契合度较高的淘汰推荐区域作为综合推荐区域,因此可以根据所述初始推荐区域中备选推荐区域的数量,以及所述初始推荐区域与所述推荐标签组合的契合度,从所述初始推荐区域中选定综合推荐区域。具体的综合推荐区域的选定策略可以根据需求进行预先设置,对此本发明实施例不加以限定。其中的预设数值可以根据需求进行预先设置,对此本发明实施例不加以限定。
可选地,在本发明实施例中,所述步骤240进一步可以包括:
子步骤241,响应于所述备选推荐区域的数量大于等于第一预设数量,从所述备选推荐区域中选取与所述推荐标签组合的契合度最高的第一预设数量的备选推荐区域作为所述综合推荐区域。
步骤242,响应于所述备选推荐区域的数量小于第一预设数量且大于等于1,获取全部的所述备选推荐区域作为所述综合推荐区域。
步骤243,响应于所述备选推荐区域的数量为零,从所述淘汰推荐区域中选取与所述推荐标签组合的契合度最高的淘汰推荐区域作为所述综合推荐区域。
在本发明实施例中,在确定得到初始推荐区域之后,则需要根据各个初始推荐区域与推荐标签组合的契合度,从初始推荐区域中选出最终的综合推荐区域。具体的,如果初始推荐区域中的备选推荐区域较多,则说明能够满足用户需求的可选推荐区域较多,因此可以优先选择与推荐标签组合契合度较高的备选推荐区域作为综合推荐区域,而如果备选推荐区域较少,甚至没有备选推荐区域,那么可选项则较少,此时则只能将全部的备选推荐区域都作为综合推荐区域,或者是将与推荐标签组合的契合度较高的淘汰推荐区域作为综合推荐区域。由此可见,在本发明实施例中可以根据初始推荐区域中备选推荐区域的数量,从初始推荐区域中选出最终的综合推荐区域。
具体的,可以预先设置第一预设数量作为基准线,如果备选推荐区域的数量大于等于第一预设数量,则可以从备选推荐区域中选取与推荐标签组合的契合度最高的第一预设数量的备选推荐区域作为综合推荐区域,而如果备选推荐区域的数量小于第一预设数量且大于等于1,则可以获取全部的备选推荐区域作为综合推荐区域;而如果备选推荐区域的数量为零,则可以从淘汰推荐区域中选取与推荐标签组合的契合度最高的淘汰推荐区域作为综合推荐区域。其中的第一预设数量可以根据需求进行预先设置,对此本发明实施例不加以限定。例如,可以设置第一预设数量为3,等等。
另外,在本发明实施例中,在获取各个初始推荐区域与推荐标签组合的契合度时,可以先获取备选推荐区域与推荐标签组合的契合度,进而判断初始推荐区域中是否包含备选推荐区域,如果初始推荐区域中包含备选推荐区域,则可以无需获取淘汰推荐区域与推荐标签组合的契合度,而如果初始推荐区域中不包含备选推荐区域,则可以进一步获取淘汰推荐区域与推荐标签组合的契合度。从而可以避免获取淘汰推荐区域与推荐标签组 合的契合度的无效操作。
步骤250,获取所述综合推荐区域中的热力相关参数。
在实际应用中,由于各个区域的人员或车辆等都是流动的,而且不同时间段同一区域的人流量可能会有很大不同。对于用户而言,其考虑是否去某一综合推荐区域时,也会相应考虑相应的综合推荐区域的人流量等等情况。
因此,在本发明实施例中,在确定了综合推荐区域之后,为了同时向用户展示各个综合推荐区域的人流量等热图数据,还可以进一步获取各个综合推荐区域中的热力相关参数。其中的热力相关参数可以包括任何可以直接或间接影响或反映相应的综合推荐区域内当前热力情况,并可一定程度上预测未来热力情况的参数。例如,热力相关参数可以包括但不限于交通状态参数、定位信息参数、消费信息参数、商家信息参数,等等。
而且,在本发明实施例中,可以通过任何可用方法获取综合推荐区域中的热力相关参数,对此本发明实施例不加以限定。例如,可以通过获取综合推荐区域内的GPS(Global Positioning System,全球定位系统)定位信息,作为相应综合推荐区域内的定位信息参数;可以通过地图类产品中获取综合推荐区域内的交通状态参数,可以通过获取消费类应用程序端所有用户在综合推荐区域的消费信息,进而获取相应综合推荐区域的消费信息参数;可以通过商家监控获取相应综合推荐区域中的商家信息参数;等等。
可选地,在本发明实施例中,所述热力相关参数包括交通状态参数、定位信息参数、消费信息参数和商家信息参数中的至少一种;所述热图数据包括实时热力数据和/或热力趋势数据。
其中的交通状态参数可以包括但不限于综合推荐区域内的车流量数据;定位信息参数可以包括但不限于综合推荐区域内的可通过GPS等定位功能确定位置的终端设备数量,但无法获取无GPS定位设备的热力信息;消费信息参数可以包括但不限于餐饮消费信息,酒店间夜量,景区售票量,影院售票量等,而上述的消费信息参数都可以转换为相应的综合推荐区域内的当前人流热度信息;商家信息参数可以包括但不限于商家当前的人流量数据,等等。
步骤260,基于所述热力相关参数确定所述综合推荐区域的热图数据。
如前述,经上述步骤获取的热力相关参数可以直接或间接地反映综合推荐区域的热力情况,也可以反映综合推荐区域未来的热力情况。其中的 热力情况可以包括综合推荐区域的人流热度、受欢迎程度等信息。
但是热力相关参数具体所包含的参数类目较多,那么用户在基于热力相关参数选择综合推荐区域时,还需要自行综合考量各个热力相关参数,不够直观且比较耗时,那么为了用户能够直接了解各个综合推荐区域的热力情况,可以将基于各个综合推荐区域的热力相关参数确定相应的综合推荐区域的热图数据。其中的热图数据为可以直接表征综合推荐区域的综合热力情况的数据,具体的可以包括但不限于可以表征当前热力情况的实时热力数据、可以表征未来热力情况走势的热力趋势数据,等等。
在本发明实施例中,为了得到各个综合推荐区域的热图数据,可以预先设置热力相关参数与热图数据之间的对应关系,或者是热图数据计算公式,从而基于各个综合推荐区域的热力相关参数确定相应综合推荐区域的热图数据。
例如,可以设置热图数据为各个热力相关参数的加权和,其中各个热力相关参数的权重则可以根据需求进行预先设置,对此本发明实施例不加以限定。
子步骤261,根据当前日期以及预设的可参考周期,确定所述热图数据的可参考天数。
在实际应用中,用户想要搜索满足其需求的商家或产品等,还可以设定针对本次搜索的需求时间,也即用户预计的消费时间,而且用户的需求时间一般是尚未到达的时间,那么针对本次搜索得到的综合推荐区域中需要展示的信息可以包括针对需求时间的热力情况,那么针对尚未达到的时间点的热力情况,则需要基于历史数据进行估算。因此为了确定综合推荐区域的热图数据,则首先需要确定可参考天数,具体的可以基于当前日期以及预设的可参考周期,确定热图数据的可参考天数。其中的可参考周期可以根据需求进行预先设定,对此本发明实施例不加以限定。
例如,如果当前日期为2018年10月10日,假设预设的可参考周期是一周,那么则可以确定热图数据的可参考天数为2018年10月3日-2018年10月9日,共七天。
子步骤262,获取在所述可参考天数内,在所述用户设定的预测时间点对应的预设单位时间内的第一热力相关参数。
其中的预测时间点可以为用户设定的当前推荐标签组合对应的需求时间点,也即用户预计的消费时间点,具体的可以根据需求进行预先设置,对此本发明实施例不加以限定;预设单位时间内的具体取值也可以根据需 求进行预先设置,对此本发明实施例不加以限定。而且,预测时间点对应的预设单位时间也可以根据需求进行预先设置,对此本发明实施例有不加以限定。
例如,可以设置预测时间点为8:30,预设单位时间为1小时,而预测时间点对应的预设单位时间可以为以预测时间点为起始时间的一个预设单位时间,例如对于上述的预测时间点和预测单位时间,那么预测时间点8:30对应的预设单位时间为8:30-9:30;或者也可以设置预测时间点对应的预设单位时间为预测时间点所在的预设单位时间,那么此时上述的预测时间点8:30对应的预设单位时间可以为8:00-9:00,等等。
而为了估算所在预测时间点时的实时热力数据,则需要获取在所述可参考天数内,在所述用户设定的预测时间点对应的预设单位时间内的第一热力相关参数。而且,第一热力相关参数可以包括但不限于上述的交通状态参数、定位信息参数、消费信息参数和商家信息参数中的至少一种。
子步骤263,基于所述第一热力相关参数,所述热力相关参数的预设权重,以及预设的第一人工调整参数,确定所述实时热力数据。
在得到综合推荐区域中可参考天数内的第一热力相关参数之后,则可以进一步基于第一热力相关参数,各个热力相关参数的预设权重,以及预设的第一人工调整参数,确定相应综合推荐区域的实时热力数据。
其中的各个热力相关参数的预设权重,以及第一人工调整参数的具体取值可以根据需求进行预先设置,对此本发明实施例不加以限定。而且,第一热力相关参数,各个热力相关参数的预设权重,以及第一人工调整参数,与实时热力数据之间的对应关系也可以根据需求进行预先设置,对此本发明实施例不加以限定。
例如,可以设置第一热力相关参数,各个热力相关参数的预设权重,以及第一人工调整参数与实时热力数据之间的对应关系,实时热力数据为各个第一热力相关参数在预设单位时间内的加权平均值与第一人工调整参数之和。假设获取得到的第一热力相关参数包括了上述的交通状态参数X1、定位信息参数Y1、消费信息参数Z1和商家信息参数O1,而且各个热力相关参数的权重依次为λ1、λ2、λ3和λ4,第一人工调整参数为T1,可参考天数为N,也即可以获取N个预设单位时间内的第一热力相关参数。那么,此时实时热力数据可以为
Figure PCTCN2019121652-appb-000001
子步骤264,获取在所述可参考天数内,在所述预测时间点之前的预设 单位时间内的第二热力相关参数。
而为了对预测时间点时的热力变化趋势进行预测,那么则需要获取在相应的可参考天数内,在预测时间点之前的预设单位时间内的第二热力相关参数。其中第二热力相关参数也可以包括但不限于上述的交通状态参数、定位信息参数、消费信息参数和商家信息参数中的至少一种,而且参照于前述的预测时间点对应的预设单位时间,预测时间点之前的预设单位时间可以为以预测时间点为结束点的一个预设单位时间,或者是预测时间点所在预设单位时间之前的一个预设单位时间等等,具体的也可以根据需求进行预先设置,对此本发明实施例不加以限定。
例如,对于上述的预测时间点8:30,预设单位时间1小时,如果预测时间点之前的预设单位时间为以预测时间点为结束点的一个预设单位时间,那么此时的预测时间点之前的预设单位时间可以为7:30-8:30,而如果预测时间点之前的预设单位时间为预测时间点所在预设单位时间之前的一个预设单位时间,那么此时预测时间点8:30所在的预设单位时间为8:00-9:00,而此时的预测时间点之前的预设单位时间则可以为7:00-8:00。
子步骤265,基于所述第一热力相关参数和所述第二热力相关参数,所述热力相关参数的预设权重,以及预设的第二人工调整参数,确定所述热力趋势数据。
从上述可知,第一热力相关参数和所述第二热力相关参数可以为同一综合推荐区域中先后两个预设单位时间内的热力相关参数,因此可以基于综合推荐区域对应的第一热力相关参数和第二热力相关参数,热力相关参数的预设权重,以及预设的第二人工调整参数,确定相应综合推荐区域的热力趋势数据。其中,第一热力相关参数和第二热力相关参数,热力相关参数的预设权重,以及预设的第二人工调整参数与热力趋势数据之间的对应关系可以根据需求进行预先设置,对此本发明实施例不加以限定。第二人工调整参数也可以根据需求进行预先设置,对此本发明实施例不加以限定。而且,在获取热力趋势数据时所用的热力相关参数的预设权重,和获取实时热力数据时的热力相关参数的预设权重可以相同,当然也可以不完全相同,具体的可以根据需求进行预先设置,对此本发明实施例也不加以限定。
例如,可以设置热力趋势数据为在同一参考天数内的各个第一热力相关参数和相应的第二热力相关参数的比值的加权平均值,与第二人工调整参数的和值。假设获取得到的第二热力相关参数同样包括了交通状态参数 X2、定位信息参数Y2、消费信息参数Z2和商家信息参数O2,而且各个热力相关参数的权重同样依次为λ1、λ2、λ3和λ4,假设第二人工调整参数为T2,可参考天数为N,也即可以获取N个预设单位时间内的第一热力相关参数,以及N个预设单位时间内的第二热力相关参数。那么,此时热力趋势数据可以为
Figure PCTCN2019121652-appb-000002
步骤270,基于所述热图数据,对所述综合推荐区域进行热力渲染并显示。
可选地,在本发明实施例中,所述步骤270进一步可以包括:
子步骤271,基于所述实时热力数据,对所述综合推荐区域进行热力渲染并显示。
对于上述的实时热力数据数据,则可以直接在相应的综合推荐区域进行热力渲染并显示。
子步骤272,通过预设方式在所述综合推荐区域中显示所述热力趋势数据。
对于热力趋势数据,为了方便用户根据综合推荐区域中显示的热力趋势数据直观了解相应的综合推荐区域内的热力变化趋势,可以通过预设方式在所述综合推荐区域中显示所述热力趋势数据。具体的预设方式可以根据需求进行预先设置,对此本发明实施例不加以限定。
例如,可以设置如果基于上述热力趋势数据公式获取的热力趋势数据大于第二预设数值范围,则可以认为未来的热力变化趋势为上升趋势,而如果热力趋势数据小于第二预设数值范围,则可以认为未来的热力变化趋势为下降趋势,而如果热力趋势数据属于第二预设数值范围,则可以认为未来的热力变化趋势为持平趋势。其中的第二预设数值范围则可以根据需求进行预先设置,对此本发明实施例不加以限定。例如,对于上述的热力趋势数据公式,可以设置第二预设数值范围为1,等等。而对于确定为上升趋势的热力趋势数据,则可以红色向上小箭头在相应的综合推荐区域中进行表示,对于确定为下降趋势的热力趋势数据,则可以用绿色向下小箭头在相应的综合推荐区域中进行表示,对于确定为持平趋势的热力趋势数据,则可以不做任何表示。
步骤280,当接收到所述用户针对所述综合推荐区域中部分区域的放大请求,获取所述部分区域内与所述推荐标签组合匹配的商家的商家数据。
另外,在实际应用中,综合推荐区域中可以包含较多的内容,其中可 以有餐饮、娱乐、景点等等,而且其中可以包括用户感兴趣的区域,也可以包含用户不感兴趣的区域,那么如果用户对综合推荐区域中的某一部分区域想进行进一步了解,可在地图上对该部分区域进行放大,而且为了方便用户更清楚地了解其放大的部分区域中与其输入的推荐标签组合匹配的商家数据,则可以在接收到所述用户针对所述综合推荐区域中部分区域的放大请求,获取所述部分区域内与所述推荐标签组合匹配的商家的商家数据。
其中的商家数据可以包括任何能够表征商家相关信息的参考数据,例如可以包括但不限于酒店库存信息、餐厅排队信息、影院剩余票量、景区剩余票量、商家评分信息、商家特色推荐和商家团购信息中的至少一种。而且,在本发明实施例中,可以通过任何可用方法获取上述的商家数据,对此本发明实施例不加以限定。
当然,在本发明实施例中,根据需求也可以设置获取部分区域中全部商家的商家数据,对此本发明实施例不加以限定。
步骤290,根据所述商家数据调整所述部分区域的热图数据,并基于调整后的热图数据调整所述部分区域的热力渲染效果。
在获取得到商家数据之后,为了提高用户方法的部分区域的热力渲染准确性,还可以进一步根据商家数据调整所述部分区域的热图数据,并基于调整后的热图数据调整所述部分区域的热力渲染效果。例如,可以根据商家数据中的可用数据调整部分区域的热力相关参数,从而调整部分区域的实时热力数据和或热力趋势数据,进一步地调整相应的部分区域的热力渲染效果,等等。具体的调整策略可以根据需求进行预先设置,对此本发明实施例不加以限定。
步骤2110,将所述商家数据渲染到所述部分区域中。
而且,为了方便用户准确获取其选定放大的部分区域中商家的商家数据,帮助用户更好的判断相应商家的人流情况,还可以直接将商家数据渲染到相应的部分区域中,而且优选地还可以将各个商家的商家数据渲染到相应商家的商家图标上方,从而可以方便用户直观了解相关商家的实时商家数据。或者,可以将商家数据以表格形式显示在相应的部分区域中,等等,具体的商家数据渲染方式可以根据需求进预先设置,对此本发明实施例不加以限定。其中,所述商家数据可以包括但不限于酒店库存信息、餐厅排队信息、影院剩余票量、景区剩余票量和商家评分信息中的至少一种。
第一方面,根据本发明的区域综合推荐方法,可以获取用户输入的推荐标签组合;基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域;确定所述综合推荐区域的热图数据;基于所述热图数据对所述综合推荐区域进行热力渲染并显示。由此解决了现有的区域综合推荐方法在多种类型综合推荐方面的效果欠佳的技术问题。取得了提高多类型综合推荐效果的有益效果。
第二方面,在本发明实施例中,还可以根据所述推荐标签组合中各标签的标签类型、预设的标签优先级,确定与所述推荐标签组合对应的初始推荐区域;所述初始推荐区域包括备选推荐区域和/或淘汰推荐区域;根据所述推荐标签组合,以及所述推荐标签组合中与所述初始推荐区域匹配的标签数量,确定所述初始推荐区域与所述推荐标签组合的契合度;根据所述初始推荐区域中备选推荐区域的数量,以及所述初始推荐区域与所述推荐标签组合的契合度,从所述初始推荐区域中选定综合推荐区域。并且,获取所述用户的指定位置;根据所述标签优先级,以所述指定位置为中心,以预设搜索距离为半径,查找与高优先等级的标签匹配的高优先等级商家;基于所述高优先等级商家以及预设的推荐区域半径,确定高优先推荐区域;响应于在所述高优先推荐区域中是否查找到与低优先等级的标签匹配的商家,确认所述高优先推荐区域为备选推荐区域或淘汰推荐区域。以及,响应于在所述高优先推荐区域中查找到与低优先等级的标签匹配的商家,确认所述高优先推荐区域为备选推荐区域;响应于在所述高优先推荐区域中仅查找到与第二等级的标签匹配的第二等级商家,基于所述第二等级商家以及预设的推荐区域半径,确定低优先推荐区域;响应于在所述高优先推荐区域中仅查找到与第三等级的标签匹配的第三等级商家,或者是在所述高优先推荐区域中未查找到与其他等级的标签匹配的商家,确认所述高优先推荐区域为淘汰推荐区域;响应于在所述低优先推荐区域中查找到与第三等级的标签匹配的商家,确认所述高优先推荐区域与所述低优先推荐区域的组合为备选推荐区域;响应于在所述低优先推荐区域中未查找到与第三等级的标签匹配的商家,确认所述高优先推荐区域与所述低优先推荐区域的组合为淘汰推荐区域。从而可以进一步提高综合推荐区域的准确性。
第三方面,在本发明实施例中,还可以根据所述推荐标签组合中属于同一标签类型且与所述初始推荐区域匹配的标签数量,与所述标签类型包含的总标签数量的比值,确定所述标签类型的单一类型契合度;获取所述 初始推荐区域中各个标签类型的单一类型契合度的平均值作为所述初始推荐区域与所述推荐标签组合的契合度。并且,响应于所述备选推荐区域的数量大于等于第一预设数量,从所述备选推荐区域中选取与所述推荐标签组合的契合度最高的第一预设数量的备选推荐区域作为所述综合推荐区域;响应于所述备选推荐区域的数量小于第一预设数量且大于等于1,获取全部的所述备选推荐区域作为所述综合推荐区域;响应于所述备选推荐区域的数量为零,从所述淘汰推荐区域中选取与所述推荐标签组合的契合度最高的淘汰推荐区域作为所述综合推荐区域。同样可以提高综合推荐区域的效果以及准确性。
第四方面,在本发明实施例中,还可以根据当前日期以及预设的可参考周期,确定所述热图数据的可参考天数;获取在所述可参考天数内,在所述用户设定的预测时间点对应的预设单位时间内的第一热力相关参数;基于所述第一热力相关参数,所述热力相关参数的预设权重,以及预设的第一人工调整参数,确定所述实时热力数据;获取在所述可参考天数内,在所述预测时间点之前的预设单位时间内的第二热力相关参数;基于所述第一热力相关参数和所述第二热力相关参数,所述热力相关参数的预设权重,以及预设的第二人工调整参数,确定所述热力趋势数据。从而可以提高热图数据的准确性,以及提高区域综合推荐效果。
第五方面,在本发明实施例中,还可以当接收到所述用户针对所述综合推荐区域中部分区域的放大请求,获取所述部分区域内与所述推荐标签组合匹配的商家的商家数据;根据所述商家数据调整所述部分区域的热图数据,并基于调整后的热图数据调整所述部分区域的热力渲染效果;将所述商家数据渲染到所述部分区域中。从而可以方便用户更直观详细地了解其感兴趣区域的商家数据,进而提高区域综合推荐效果。
对于方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本发明实施例并不受所描述的动作顺序的限制,因为依据本发明实施例,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作并不一定是本发明实施例所必须的。
实施例三
详细介绍本发明实施例提供的一种区域综合推荐装置。
参照图3,示出了本发明实施例中一种区域综合推荐装置的结构示意图。所述装置,具体可以包括如下模块:
推荐标签组合获取模块310,用于获取用户输入的推荐标签组合。
综合推荐区域查找模块320,用于基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域。
热图数据确认模块330,用于确定所述综合推荐区域的热图数据。
热力渲染模块340,用于基于所述热图数据,对所述综合推荐区域进行热力渲染并显示。
根据本发明的区域综合推荐方法,可以获取用户输入的推荐标签组合;基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域;确定所述综合推荐区域的热图数据;基于所述热图数据对所述综合推荐区域进行热力渲染并显示。由此取得了提高多类型综合推荐准确性的有益效果。
实施例四
详细介绍本发明实施例提供的一种区域综合推荐装置。
参照图4,示出了本发明实施例中一种区域综合推荐装置的结构示意图。所述装置,具体可以包括如下模块:
推荐标签组合获取模块410,用于获取用户输入的推荐标签组合。
综合推荐区域查找模块420,用于基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域。
其中,所述综合推荐区域查找模块420进一步可以包括:
初始推荐区域确认子模块421,用于根据所述推荐标签组合中各标签的标签类型、预设的标签优先级,确定与所述推荐标签组合对应的初始推荐区域;所述初始推荐区域包括备选推荐区域和/或淘汰推荐区域;
契合度确认子模块422,用于根据所述推荐标签组合,以及所述推荐标签组合中与所述初始推荐区域匹配的标签数量,确定所述初始推荐区域与所述推荐标签组合的契合度;
综合推荐区域查找子模块423,用于根据所述初始推荐区域中备选推荐区域的数量,以及所述初始推荐区域与所述推荐标签组合的契合度,从所述初始推荐区域中选定综合推荐区域。
可选地,在本发明实施例中,所述初始推荐区域确认子模块421进一步可以包括:
指定位置获取单元,用于获取所述用户的指定位置。
高优先商家查找单元,用于根据所述标签优先级,以所述指定位置为中心,以预设搜索距离为半径,查找与高优先等级的标签匹配的高优先等 级商家;
高优先推荐区域确认单元,用于基于所述高优先等级商家以及预设的推荐区域半径,确定高优先推荐区域;
推荐区域判断单元,用于响应于在所述高优先推荐区域中是否查找到与低优先等级的标签匹配的商家,确认所述高优先推荐区域为备选推荐区域或淘汰推荐区域;
可选地,在本发明实施例中,所述推荐区域判断单元,进一步可以包括:
第一备选推荐区域确认子单元,用于响应于在所述高优先推荐区域中查找到与低优先等级的标签匹配的商家,确认所述高优先推荐区域为备选推荐区域;
低优先推荐区域确认子单元,用于响应于在所述高优先推荐区域中仅查找到与第二等级的标签匹配的第二等级商家,基于所述第二等级商家以及预设的推荐区域半径,确定低优先推荐区域;
第一淘汰推荐区域确认子单元,用于响应于在所述高优先推荐区域中仅查找到与第三等级的标签匹配的第三等级商家,或者是在所述高优先推荐区域中未查找到与其他等级的标签匹配的商家,确认所述高优先推荐区域为淘汰推荐区域;
第二备选推荐区域确认子单元,用于响应于在所述低优先推荐区域中查找到与第三等级的标签匹配的商家,确认所述高优先推荐区域与所述低优先推荐区域的组合为备选推荐区域;
第二淘汰推荐区域确认单元,用于响应于在所述低优先推荐区域中未查找到与第三等级的标签匹配的商家,确认所述高优先推荐区域与所述低优先推荐区域的组合为淘汰推荐区域。
可选地,在本发明实施例中,所述契合度确认子模块422,进一步可以包括:
单一类型契合度确认单元,用于根据所述推荐标签组合中属于同一标签类型且与所述初始推荐区域匹配的标签数量,与所述标签类型包含的总标签数量的比值,确定所述标签类型的单一类型契合度;
契合度确认单元,用于获取所述初始推荐区域中各个标签类型的单一类型契合度的平均值作为所述初始推荐区域与所述推荐标签组合的契合度。
可选地,在本发明实施例中,所述综合推荐区域查找子模块423进一步 可以包括:
第一综合推荐区域查找单元,用于响应于所述备选推荐区域的数量大于等于第一预设数量,从所述备选推荐区域中选取与所述推荐标签组合的契合度最高的第一预设数量的备选推荐区域作为所述综合推荐区域;
第二综合推荐区域查找单元,用于响应于所述备选推荐区域的数量小于第一预设数量且大于等于1,获取全部的所述备选推荐区域作为所述综合推荐区域;
第三综合推荐区域查找单元,用于响应于所述备选推荐区域的数量为零,从所述淘汰推荐区域中选取与所述推荐标签组合的契合度最高的淘汰推荐区域作为所述综合推荐区域。
热力相关参数获取模块430,用于获取所述综合推荐区域中的热力相关参数。
可选地,在本发明实施例中,所述热力相关参数包括交通状态参数、定位信息参数、消费信息参数和商家信息参数中的至少一种;所述热图数据包括实时热力数据和/或热力趋势数据。
热图数据确认模块440,用于基于所述热力相关参数确定所述综合推荐区域的热图数据。
其中,所述热图数据确认模块440,进一步可以包括:
可参考天数确定子模块441,用于根据当前日期以及预设的可参考周期,确定所述热图数据的可参考天数;
第一热力相关参数获取子模块442,用于获取在所述可参考天数内,在所述用户设定的预测时间点对应的预设单位时间内的第一热力相关参数;
实时热力数据确定子模块443,用于基于所述第一热力相关参数,所述热力相关参数的预设权重,以及预设的第一人工调整参数,确定所述实时热力数据;
第二热力相关参数获取子模块444,用于获取在所述可参考天数内,在所述预测时间点之前的预设单位时间内的第二热力相关参数;
热力趋势数据获取子模块445,用于基于所述第一热力相关参数和所述第二热力相关参数,所述热力相关参数的预设权重,以及预设的第二人工调整参数,确定所述热力趋势数据。
热力渲染模块450,用于基于所述热图数据对所述综合推荐区域进行热力渲染并显示。
商家数据获取模块460,用于当接收到所述用户针对所述综合推荐区域 中部分区域的放大请求,获取所述部分区域内与所述推荐标签组合匹配的商家的商家数据。
热力渲染调整模块470,用于根据所述商家数据调整所述部分区域的热图数据,并基于调整后的热图数据调整所述部分区域的热力渲染效果。
商家数据渲染模块480,用于将所述商家数据渲染到所述部分区域中。
第一方面,根据本发明的区域综合推荐方法,可以获取用户输入的推荐标签组合;基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域;确定所述综合推荐区域的热图数据;基于所述热图数据对所述综合推荐区域进行热力渲染并显示。由此取得了提高多类型综合推荐效果的有益效果。
第二方面,在本发明实施例中,还可以根据所述推荐标签组合中各标签的标签类型、预设的标签优先级,确定与所述推荐标签组合对应的初始推荐区域;所述初始推荐区域包括备选推荐区域和/或淘汰推荐区域;根据所述推荐标签组合,以及所述推荐标签组合中与所述初始推荐区域匹配的标签数量,确定所述初始推荐区域与所述推荐标签组合的契合度;根据所述初始推荐区域中备选推荐区域的数量,以及所述初始推荐区域与所述推荐标签组合的契合度,从所述初始推荐区域中选定综合推荐区域。并且,获取所述用户的指定位置;根据所述标签优先级,以所述指定位置为中心,以预设搜索距离为半径,查找与高优先等级的标签匹配的高优先等级商家;基于所述高优先等级商家以及预设的推荐区域半径,确定高优先推荐区域;响应于在所述高优先推荐区域中是否查找到与低优先等级的标签匹配的商家,确认所述高优先推荐区域为备选推荐区域或淘汰推荐区域。以及,响应于在所述高优先推荐区域中查找到与低优先等级的标签匹配的商家,确认所述高优先推荐区域为备选推荐区域;响应于在所述高优先推荐区域中仅查找到与第二等级的标签匹配的第二等级商家,基于所述第二等级商家以及预设的推荐区域半径,确定低优先推荐区域;响应于在所述高优先推荐区域中仅查找到与第三等级的标签匹配的第三等级商家,或者是在所述高优先推荐区域中未查找到与其他等级的标签匹配的商家,确认所述高优先推荐区域为淘汰推荐区域;响应于在所述低优先推荐区域中查找到与第三等级的标签匹配的商家,确认所述高优先推荐区域与所述低优先推荐区域的组合为备选推荐区域;响应于在所述低优先推荐区域中未查找到与第三等级的标签匹配的商家,确认所述高优先推荐区域与所述低优先推荐区域的组合为淘汰推荐区域。从而可以进一步提高综合推荐区域的 准确性。
第三方面,在本发明实施例中,还可以根据所述推荐标签组合中属于同一标签类型且与所述初始推荐区域匹配的标签数量,与所述标签类型包含的总标签数量的比值,确定所述标签类型的单一类型契合度;获取所述初始推荐区域中各个标签类型的单一类型契合度的平均值作为所述初始推荐区域的与所述推荐标签组合的契合度。并且,响应于所述备选推荐区域的数量大于等于第一预设数量,从所述备选推荐区域中选取与所述推荐标签组合的契合度最高的第一预设数量的备选推荐区域作为所述综合推荐区域;响应于所述备选推荐区域的数量小于第一预设数量且大于等于1,获取全部的所述备选推荐区域作为所述综合推荐区域;响应于所述备选推荐区域的数量为零,从所述淘汰推荐区域中选取与所述推荐标签组合的契合度最高的淘汰推荐区域作为所述综合推荐区域。同样可以提高综合推荐区域的效果以及准确性。
第四方面,在本发明实施例中,还可以根据当前日期以及预设的可参考周期,确定所述热图数据的可参考天数;获取在所述可参考天数内,在所述用户设定的预测时间点对应的预设单位时间内的第一热力相关参数;基于所述第一热力相关参数,所述热力相关参数的预设权重,以及预设的第一人工调整参数,确定所述实时热力数据;获取在所述可参考天数内,在所述预测时间点之前的预设单位时间内的第二热力相关参数;基于所述第一热力相关参数和所述第二热力相关参数,所述热力相关参数的预设权重,以及预设的第二人工调整参数,确定所述热力趋势数据。从而可以提高热图数据的准确性,以及提高区域综合推荐效果。
第五方面,在本发明实施例中,还可以当接收到所述用户针对所述综合推荐区域中部分区域的放大请求,获取所述部分区域内与所述推荐标签组合匹配的商家的商家数据;根据所述商家数据调整所述部分区域的热图数据,并基于调整后的热图数据调整所述部分区域的热力渲染效果;将所述商家数据渲染到所述部分区域中。从而可以方便用户更直观详细地了解其感兴趣区域的商家数据,进而提高区域综合推荐效果。
本发明实施例中还公开了一种电子设备,包括:
处理器、存储器以及存储在所述存储器上并可在所述处理器上运行的计算机程序,所述处理器执行所述程序时实现前述的区域综合推荐方法。
本发明实施例中还公开了一种可读存储介质,当所述存储介质中的指令由电子设备的处理器执行时,使得电子设备能够执行前述的区域综合推 荐方法。
对于装置实施例而言,由于其与方法实施例基本相似,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。
本发明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)来实现根据本发明实施例的计算处理设备中的一些或者全部部件的一些或者全部功能。本发明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)。这样的实现本发明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。
例如,图5示出了可以实现根据本发明的方法的计算处理设备。该计算处理设备传统上包括处理器510和以存储器520形式的计算机程序产品或者计算机可读介质。存储器520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。存储器520具有用于执行上述方法中的任何方法步骤的程序代码531的存储空间530。例如,用于程序代码的存储空间530可以包括分别用于实现上面的方法中的各种步骤的各个程序代码531。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。这些计算机程序产品包括诸如硬盘,紧致盘(CD)、存储卡或者软盘之类的程序代码载体。这样的计算机程序产品通常为如参考图6所述的便携式或者固定存储单元。该存储单元可以具有与图5的计算处理设备中的存储器520类似布置的存储段、存储空间等。程序代码可以例如以适当形式进行压缩。通常,存储单元包括计算机可读代码531’,即可以由例如诸如510之类的处理器读取的代码,这些代码当由计算处理设备运行时,导致该计算处理设备执行上面所描述的方法中的各个步骤。
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,本发明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发明的内容,并且上面对特定语言所做的描述是为了披露本发明的最佳实施方式。
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,本发明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发明方面中的一个或多个,在上面对本发明的示例性实施例的描述中,本发明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:即所要求保护的本发明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,发明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发明的单独实施例。
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发明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。
本发明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)来实现根据本发明实施例的区域综合推荐设备中的一些或者全部部件的一些或者全部功能。本发明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)。这样的实现本发明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发明进行说明而不是对本发明进行限制,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。本发明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 (12)

  1. 一种区域综合推荐方法,包括:
    获取用户输入的推荐标签组合;
    基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域;
    确定所述综合推荐区域的热图数据;
    基于所述热图数据,对所述综合推荐区域进行热力渲染并显示。
  2. 根据权利要求1所述的方法,所述基于所述推荐标签组合,查找与所述推荐标签组合对应的综合推荐区域的步骤,包括:
    根据所述推荐标签组合中各标签的标签类型、预设的标签优先级,确定与所述推荐标签组合对应的初始推荐区域;所述初始推荐区域包括备选推荐区域和/或淘汰推荐区域;
    根据所述推荐标签组合,以及所述推荐标签组合中与所述初始推荐区域匹配的标签数量,确定所述初始推荐区域与所述推荐标签组合的契合度;
    根据所述初始推荐区域中备选推荐区域的数量,以及所述初始推荐区域与所述推荐标签组合的契合度,从所述初始推荐区域中选定综合推荐区域。
  3. 根据权利要求2所述的方法,所述根据所述推荐标签组合中的标签类型、预设的标签优先级,确定与所述推荐标签组合对应的初始推荐区域的步骤,包括:
    获取所述用户的指定位置;
    根据所述标签优先级,以所述指定位置为中心,以预设搜索距离为半径,查找与高优先等级的标签匹配的高优先等级商家;
    基于所述高优先等级商家以及预设的推荐区域半径,确定高优先推荐区域;
    响应于在所述高优先推荐区域中是否查找到与低优先等级的标签匹配的商家,确认所述高优先推荐区域为备选推荐区域或淘汰推荐区域。
  4. 根据权利要求3所述的方法,所述响应于在所述高优先推荐区域中是否查找到与低优先等级的标签匹配的商家,确认所述高优先推荐区域为备选推荐区域或淘汰推荐区域的步骤,包括:
    响应于在所述高优先推荐区域中查找到与低优先等级的标签匹配的商家,确认所述高优先推荐区域为备选推荐区域;
    响应于在所述高优先推荐区域中仅查找到与第二等级的标签匹配的第二等级商家,基于所述第二等级商家以及预设的推荐区域半径,确定低优先推荐区域;
    响应于在所述高优先推荐区域中仅查找到与第三等级的标签匹配的第三等级商家,或者是在所述高优先推荐区域中未查找到与其他等级的标签匹配的商家,确认所述高优先推荐区域为淘汰推荐区域;
    响应于在所述低优先推荐区域中查找到与第三等级的标签匹配的商家,确认所述高优先推荐区域与所述低优先推荐区域的组合为备选推荐区域;
    响应于在所述低优先推荐区域中未查找到与第三等级的标签匹配的商家,确认所述高优先推荐区域与所述低优先推荐区域的组合为淘汰推荐区域。
  5. 根据权利要求2所述的方法,所述根据所述推荐标签组合,以及所述推荐标签组合中与所述初始推荐区域匹配的标签数量,确定所述初始推荐区域与所述推荐标签组合的契合度的步骤,包括:
    根据所述推荐标签组合中属于同一标签类型且与所述初始推荐区域匹配的标签数量,与所述标签类型包含的总标签数量的比值,确定所述标签类型的单一类型契合度;
    获取所述初始推荐区域中各个标签类型的单一类型契合度的平均值作为所述初始推荐区域与所述推荐标签组合的契合度。
  6. 根据权利要求2所述的方法,所述根据所述初始推荐区域中备选推荐区域的数量,以及所述初始推荐区域与所述推荐标签组合的契合度,从所述初始推荐区域中选定综合推荐区域的步骤,包括:
    响应于所述备选推荐区域的数量大于等于第一预设数量,从所述备选推荐区域中选取与所述推荐标签组合的契合度最高的第一预设数量的备选推荐区域作为所述综合推荐区域;
    响应于所述备选推荐区域的数量小于第一预设数量且大于等于1,获取全部的所述备选推荐区域作为所述综合推荐区域;
    响应于所述备选推荐区域的数量为零,从所述淘汰推荐区域中选取与所述推荐标签组合的契合度最高的淘汰推荐区域作为所述综合推 荐区域。
  7. 根据权利要求1所述的方法,所述方法还包括:获取所述综合推荐区域中的热力相关参数;
    所述确定所述综合推荐区域的热图数据的步骤,包括:基于所述热力相关参数确定所述综合推荐区域的热图数据;
    所述热力相关参数包括交通状态参数、定位信息参数、消费信息参数和商家信息参数中的至少一种;所述热图数据包括实时热力数据和/或热力趋势数据。
  8. 根据权利要求7所述的方法,所述基于所述热力相关参数确定所述综合推荐区域的热图数据的步骤,包括:
    根据当前日期以及预设的可参考周期,确定所述热图数据的可参考天数;
    获取在所述可参考天数内,在所述用户设定的预测时间点对应的预设单位时间内的第一热力相关参数;
    基于所述第一热力相关参数,所述热力相关参数的预设权重,以及预设的第一人工调整参数,确定所述实时热力数据;
    获取在所述可参考天数内,在所述预测时间点之前的预设单位时间内的第二热力相关参数;
    基于所述第一热力相关参数和所述第二热力相关参数,所述热力相关参数的预设权重,以及预设的第二人工调整参数,确定所述热力趋势数据。
  9. 根据权利要求1所述的方法,在所述基于所述热图数据对所述综合推荐区域进行热力渲染并显示的步骤之后,还包括:
    当接收到所述用户针对所述综合推荐区域中部分区域的放大请求,获取所述部分区域内与所述推荐标签组合匹配的商家的商家数据;
    根据所述商家数据调整所述部分区域的热图数据,并基于调整后的热图数据调整所述部分区域的热力渲染效果;
    将所述商家数据渲染到所述部分区域中。
  10. 一种电子设备,包括:
    处理器、存储器以及存储在所述存储器上并可在所述处理器上运行的计算机程序,其特征在于,所述处理器执行所述计算机程序时实现如权利要求1-9中的任一项所述的区域综合推荐方法。
  11. 一种计算机程序,包括计算机可读代码,当所述计算机可读代码在计算处理设备上运行时,导致所述计算处理设备执行根据权利要求1-9中的任一个所述的区域综合推荐方法。
  12. 一种计算机可读介质,其中存储了如权利要求12所述的计算机程序。
PCT/CN2019/121652 2019-01-08 2019-11-28 区域综合推荐方法、电子设备及可读存储介质 Ceased WO2020143351A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910017354.X 2019-01-08
CN201910017354.XA CN109857931B (zh) 2019-01-08 2019-01-08 区域综合推荐方法、装置、电子设备及可读存储介质

Publications (1)

Publication Number Publication Date
WO2020143351A1 true WO2020143351A1 (zh) 2020-07-16

Family

ID=66894219

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/121652 Ceased WO2020143351A1 (zh) 2019-01-08 2019-11-28 区域综合推荐方法、电子设备及可读存储介质

Country Status (2)

Country Link
CN (1) CN109857931B (zh)
WO (1) WO2020143351A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109857931B (zh) * 2019-01-08 2021-07-09 北京三快在线科技有限公司 区域综合推荐方法、装置、电子设备及可读存储介质
CN113742584A (zh) * 2021-08-31 2021-12-03 胡之乐 一种基于大数据的文化旅游智能推广方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103955479A (zh) * 2014-04-02 2014-07-30 北京百度网讯科技有限公司 电子地图的实现方法及装置
US20140229539A1 (en) * 2013-02-13 2014-08-14 Jason Daniel Powers System and method for tag-based social networking
CN106202186A (zh) * 2016-06-27 2016-12-07 百度在线网络技术(北京)有限公司 基于人工智能的服务推荐方法和装置
CN106708829A (zh) * 2015-07-31 2017-05-24 腾讯科技(深圳)有限公司 一种数据推荐方法及推荐系统
CN109857931A (zh) * 2019-01-08 2019-06-07 北京三快在线科技有限公司 区域综合推荐方法、装置、电子设备及可读存储介质

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003208444A (ja) * 2002-01-15 2003-07-25 Minolta Co Ltd ファイル検索プログラムおよび該プログラムを記録する記録媒体
CN100541131C (zh) * 2004-08-25 2009-09-16 株式会社电装 项目搜索设备
US20070098257A1 (en) * 2005-10-31 2007-05-03 Shesha Shah Method and mechanism for analyzing the color of a digital image
JP2011257918A (ja) * 2010-06-08 2011-12-22 Sony Corp コンテンツ推薦装置およびコンテンツ推薦方法
CN104123332B (zh) * 2014-01-24 2018-11-09 腾讯科技(深圳)有限公司 搜索结果的显示方法及装置
CN103914553A (zh) * 2014-04-14 2014-07-09 百度在线网络技术(北京)有限公司 搜索方法和搜索引擎
CN104484477B (zh) * 2014-12-29 2018-05-22 广州视源电子科技股份有限公司 一种电子地图搜索方法、装置及系统
CN104537106B (zh) * 2015-01-15 2019-02-19 新华网股份有限公司 基于电子地图的搜索方法及装置
CN105787092A (zh) * 2016-03-16 2016-07-20 浙江大学 一种基于区域化的多关键字地图搜索方法
CN107154969B (zh) * 2017-04-27 2022-04-19 腾讯科技(深圳)有限公司 目的地点推荐方法及装置
CN107992602A (zh) * 2017-12-14 2018-05-04 北京百度网讯科技有限公司 搜索结果展示方法和装置
CN109146746A (zh) * 2018-07-31 2019-01-04 湖北智旅云科技有限公司 一种基于gis技术的景区大数据运营管理平台

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140229539A1 (en) * 2013-02-13 2014-08-14 Jason Daniel Powers System and method for tag-based social networking
CN103955479A (zh) * 2014-04-02 2014-07-30 北京百度网讯科技有限公司 电子地图的实现方法及装置
CN106708829A (zh) * 2015-07-31 2017-05-24 腾讯科技(深圳)有限公司 一种数据推荐方法及推荐系统
CN106202186A (zh) * 2016-06-27 2016-12-07 百度在线网络技术(北京)有限公司 基于人工智能的服务推荐方法和装置
CN109857931A (zh) * 2019-01-08 2019-06-07 北京三快在线科技有限公司 区域综合推荐方法、装置、电子设备及可读存储介质

Also Published As

Publication number Publication date
CN109857931A (zh) 2019-06-07
CN109857931B (zh) 2021-07-09

Similar Documents

Publication Publication Date Title
JP6059192B2 (ja) 特定地域在庫検索用のメタデータ使用
US20190340537A1 (en) Personalized Match Score For Places
US10163146B2 (en) Method and system for displaying location based dining recommendation labels in a reduced image area of an interface
WO2016177022A1 (zh) 一种信息处理方法、终端及服务器、计算机存储介质
CN109978723A (zh) 旅游规划方法、装置、计算机设备及存储介质
US11709881B2 (en) Visual menu
US11062374B2 (en) Continuum-based selection of product choice
US20170069000A1 (en) Quality visit measure for controlling computer response to query associated with physical location
JP2010009315A (ja) 推薦店舗提示システム
CN114969524A (zh) 信息搜索方法、装置、设备及介质
CN107710246A (zh) 用以促进描述位置的用户图像的提交的系统和方法
WO2020143351A1 (zh) 区域综合推荐方法、电子设备及可读存储介质
JP7136717B2 (ja) 情報処理装置、情報処理方法、及びプログラム
CN114936319A (zh) 信息处理方法、装置、设备、存储介质及程序产品
US20100094543A1 (en) Systems And Methods For Providing Geography-Based Tours
US20090164454A1 (en) System and method for searching venues based on similarity values
CN104063437B (zh) 一种基于电子地图的服务信息发布和搜索装置以及方法
US10123094B1 (en) Location-based movie identification systems and methods
CN107969157A (zh) 向用户提供内容项目
WO2017127961A1 (zh) 餐饮app平台的排序方法及系统
JP7023920B2 (ja) 情報処理装置、情報処理方法、および情報処理プログラム
US20200005220A1 (en) Method and system for recruiting candidates
CN121009225A (zh) 交互方法及交互装置
TW202613928A (zh) 廣告自動投放裝置及方法
CN120670636A (zh) 兴趣标签确定方法和装置

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: 19908831

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: 19908831

Country of ref document: EP

Kind code of ref document: A1