WO2021164131A1 - 地图展示方法、***、计算机设备和存储介质 - Google Patents
地图展示方法、***、计算机设备和存储介质 Download PDFInfo
- Publication number
- WO2021164131A1 WO2021164131A1 PCT/CN2020/087959 CN2020087959W WO2021164131A1 WO 2021164131 A1 WO2021164131 A1 WO 2021164131A1 CN 2020087959 W CN2020087959 W CN 2020087959W WO 2021164131 A1 WO2021164131 A1 WO 2021164131A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- target product
- attribute information
- score
- product information
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Definitions
- the embodiments of the present application relate to the field of map data processing in smart cities, and in particular, to a map display method and system.
- Map is a very convenient software that can quickly find the route to the destination in unfamiliar places, but the existing map just enters the place to be queried, shows the traffic route from the current location to the query location, and provides alternative routes , Only traffic routes.
- the inventor realizes that if you want to search for food near the destination through a map, you cannot see it intuitively, and you can only search near the destination, which is time-consuming and labor-intensive.
- the purpose of the embodiments of the present application is to provide a map display method and system, which can intuitively display required information on the map for the user to view.
- an embodiment of the present application provides a map display method, including:
- map data display instruction includes displayed destination information, radius range information, target product information, and crowd attribute information
- the drawing data is sent to the front end, so that the front end draws a plurality of data graphics according to the drawing data, and displays the data graphics.
- an embodiment of the present application also provides a map display system, including:
- the first acquisition module is configured to acquire map data display instructions, where the map data display instructions include displayed destination information, radius range information, target product information, and crowd attribute information;
- the second obtaining module is configured to obtain the longitude and latitude of the destination based on the destination information
- the third obtaining module is configured to obtain the longitude and latitude of the radius range of the destination according to the longitude and latitude of the destination and the radius range information;
- a screening module configured to screen the target product information and the crowd attribute information within the latitude and longitude range of the radius
- a cluster analysis module configured to perform a cluster analysis on the target product information and the crowd attribute information to obtain the mapping data corresponding to the target product information and the crowd attribute information;
- the drawing module is used to send the drawing data to the front end, so that the front end draws a plurality of data graphics according to the drawing data and displays the data graphics.
- cluster analysis module is also used for:
- the interest value is attenuated to obtain the drawing data of the target product information.
- an embodiment of the present application also provides a computer device, the computer device includes a memory and a processor, the memory stores a computer program that can run on the processor, and the computer program is When the processor is executed, the steps of the map display method as described above are implemented, wherein the map display method at least includes:
- map data display instruction includes displayed destination information, radius range information, target product information, and crowd attribute information
- the drawing data is sent to the front end, so that the front end draws a plurality of data graphics according to the drawing data, and displays the data graphics.
- an embodiment of the present application further provides a computer-readable storage medium, and a computer program is stored in the computer-readable storage medium, and the computer program can be executed by at least one processor to enable the At least one processor executes the steps of the map display method as described above, wherein the map display method at least includes:
- map data display instruction includes displayed destination information, radius range information, target product information, and crowd attribute information
- the drawing data is sent to the front end, so that the front end draws a plurality of data graphics according to the drawing data, and displays the data graphics.
- the map display method, system computer equipment, and storage medium provided by the embodiments of the application obtain drawing data corresponding to destination information, radius range information, target product information, and crowd attribute information through map data display instructions, and analyze the drawing data , And then send the analyzed drawing data to the front end, so that the front end draws multiple data graphics according to the drawing data, and displays the data graphics for the user to view.
- FIG. 1 is a flowchart of Embodiment 1 of the map display method of this application.
- Fig. 2 is a flowchart of the first embodiment of step S108 in Fig. 1 of the first embodiment of the application.
- FIG. 3 is a flowchart of the second embodiment of step S108 in FIG. 1 of the first embodiment of the application.
- FIG. 4 is a flowchart of the third embodiment of step S108 in FIG. 1 of the first embodiment of the application.
- FIG. 5 is a schematic diagram of program modules of Embodiment 2 of the map display system of this application.
- FIG. 6 is a schematic diagram of the hardware structure of the third embodiment of the computer equipment of this application.
- FIG. 1 shows a flow chart of the steps of the map display method according to the first embodiment of the present application. It can be understood that the flowchart in this method embodiment is not used to limit the order of execution of the steps. The following is an exemplary description with the server as the execution subject. details as follows.
- Step S100 Obtain a map data display instruction, where the map data display instruction includes displayed destination information, radius range information, target product information, and crowd attribute information.
- the map data display instruction is used to display information that the user needs to query at the destination.
- Destination information can be geographic attributes, including: POI (points of interest) distribution map, distribution of people flow in different time periods (working days), distribution of people flow in different time periods (including holidays), transportation facilities, landmark buildings
- POI points of interest
- the radius range information includes: centered on the latitude and longitude of the destination, the preset radius range for users to choose;
- the target product information includes: the interest and demand of the people around the destination in the target product, etc.;
- the crowd attribute information includes : Gender, age, educational background, wealth distribution, consumption value and product demand of the people around the destination.
- the query information input by the user can be received through the input list, and then the map data display instruction can be obtained.
- the input list you can choose to search for product information and crowd attribute information, and you can also preset the radius information of the destination information to be queried to further narrow the query range.
- the list of destination information includes: landmark building name, landmark building's longitude and latitude coordinate points based on Baidu Map API, and external health fields, etc.;
- the list of crowd attribute information includes information such as gender, age, and external health fields.
- Step S102 Obtain the latitude and longitude of the destination based on the destination information.
- the map is called according to the destination information to determine the latitude and longitude of the destination. If the user gives the corresponding fuzzy destination information, the information includes "POI list” or "POI marked on the map", you can enter the POI details and click, and then query the POI ranking displayed on the map, the POI name will be displayed when the mouse is moved in The POI list and the POI marked in the map can be clicked, and the detailed data of this POI will be expanded when clicked; if the recommended location on the map is clicked, the map point of the recommended location will be changed to the destination, and the corresponding longitude and latitude will be obtained.
- Step S104 Obtain the latitude and longitude of the radius range of the destination according to the latitude and longitude of the destination and the radius range information.
- the radius range information is set in advance, indicating that the radius of the radius extending outward from the latitude and longitude of the destination as the center can be calculated from the latitude and longitude.
- Step S106 screening the target product information and the crowd attribute information within the latitude and longitude range of the radius range.
- the SQL statement to obtain the longitude and latitude of the destination information from the database.
- the longitude, latitude, and radius information (such as 10km) are used as input parameters. If the user selects more input in the list The conditions should also be passed in as an input.
- Call and start the SpringBoot framework based on http request to connect to the database; then route the request through servet to the corresponding processing layer for logical processing to obtain the corresponding routing address; according to the routing address, use SQL statements to query the corresponding target product information and crowd in the database Property information.
- Step S108 Perform cluster analysis on the target product information and the crowd attribute information to obtain drawing data corresponding to the target product information and the crowd attribute information.
- cluster analysis is performed on the target product information and the crowd attribute information to obtain drawing data that can be used for graphic drawing.
- step S108 includes:
- Step S108A1 Analyze the resident address and GPS portrait in the crowd attribute information to obtain a geographic location portrait, the geographic location portrait including a plurality of location tags.
- the geographic location portrait is obtained by analyzing the target user's activity range. It is generally divided into two parts: one is the resident portrait; the other is the GPS portrait. The two types of portraits are quite different. Resident portraits are easier to construct and the tags are relatively stable. GPS portraits need to be updated in real time. Permanent residence includes three levels: country, province, and city, and generally only refines to the city's granularity.
- the resident location mining is based on the user’s IP address information, and the user’s IP address is analyzed, corresponding to the corresponding city, and the resident city label can be obtained by collecting statistics on the city where the user’s IP appears.
- the user's resident city tag can not only be used to count the distribution of users in various regions, but also can identify business crowds, tourist crowds, etc. according to the user's travel trajectory between various cities.
- GPS data is generally collected from the mobile phone.
- the user uses the OneConnect App to authorize the App to obtain the user's GPS information and can obtain the user's GPS information.
- the agglomerated hierarchical clustering algorithm is used to analyze the resident address and the GPS profile. First, each resident address and the address label that needs to be clustered and the address label in the GPS profile are regarded as an atomic cluster, and then the multiple addresses are combined. A cluster of atoms is a larger and larger cluster, until all objects are in one cluster, or a certain end condition is met.
- the embodiment of the application adopts the minimum distance agglomerated hierarchical clustering algorithm flow:
- Step S108A2 Calculate the similarity coefficient between the location tag and the destination information according to the Manhattan distance.
- the location label and the destination information are converted into corresponding vectors, the distance between the vector of the location label and the vector of the destination information is calculated according to the Manhattan distance metric calculation formula, and the reciprocal of the smallest Manhattan distance is taken as the similarity coefficient.
- Step S108A3 judging whether the similarity coefficient is greater than a preset threshold.
- the drawing data is filtered by judging whether the similarity coefficient is greater than a preset threshold.
- Step S108A4 if the similarity coefficient is greater than the preset threshold, use the location label with the similarity coefficient greater than the preset threshold as the drawing data of the crowd attribute information; otherwise, the similarity coefficient is not greater than the preset threshold. Set the threshold to delete the position label.
- the smaller the Manhattan distance, the larger the reciprocal, that is, the larger the similarity coefficient, and the location tag with the similarity coefficient greater than the preset threshold is selected as the drawing data of the destination information.
- the second embodiment of step S108 includes:
- Step S108B1 Acquire complete user information in the crowd attribute information.
- the user portrait tag is obtained through information filled in by the user: such as QQ, facebook, etc., including user information such as age, gender, and income.
- Step S108B2 clustering the complete user information to obtain a user portrait tag of the complete user information.
- the acquired crowd attribute information is processed to make the displayed image more accurate, including the creation of user portrait tags.
- Step S108B3 input the incomplete user information and the user portrait tags in the crowd attribute information into the tag diffusion model to improve the incomplete user information and obtain drawing data corresponding to the crowd attribute information.
- the user data obtained by the video website is counted. Assuming that about 30% of the users fill in the user information when registering, the user information of the 30% of the users is used as the training set. However, the features of watching movies are sparse features, and the accuracy of the user information filled in by registered users is not high. The parts with higher accuracy (such as complete user information) can be extracted from the 30% sample set for training as training data.
- the model is trained to build a label diffusion model.
- the tag diffusion model can predict the gender of the user by using the watched movie list.
- the prediction model can be MLlib, LR, FM, linear SVM, GBDT and other models, and the label diffusion model is obtained after training. Furthermore, it is possible to make auxiliary predictions based on the user's viewing time, browser, and viewing duration of the movie.
- step S108 includes:
- Step S108C1 clustering according to the group attribute information to obtain an interest label system of the group attribute information, and the interest label system includes a plurality of label words.
- the interest label system can extract, label, and count core information from the massive amount of behavior data of users.
- Cluster keywords treat a category of keywords as a tag, or split articles under a category. For example, like "hot pot" hashtags between keywords and categories, you can use text topic clustering to complete the construction of hashtags. That is, the content modeling of the "category-topic-keyword" three-layer tag system from rough to detailed for historically browsed articles has been completed.
- the interest label system includes the classification, themes and keywords of the target product, clustering analysis of the topics of each classification, and association with the keywords.
- Step S104C2 Calculate the interest value of each tag word and the target product information.
- the formula for calculating the interest value of the tag system is:
- score j+1 ⁇ score j +C ⁇ weight
- the interest value can be expressed as the user clicks on the target product, and all tags of the target product of the user are added to the user's interest by one.
- step S108C3 the interest value is attenuated to obtain the drawing data of the target product information.
- the attenuating the interest value includes:
- score i+1 ⁇ score i +C ⁇ weight(0 ⁇ 1), where score i+1 and score i represent the first interest value that attenuates interest according to the number of times, ⁇ represents the attenuation factor, and weight represents The weight value of the tag word, i represents the number of times, each time the previous score is attenuated, and the final score will converge to a stable value.
- ⁇ 0.9, the score will be infinitely close to 10;
- score day+1 score day ⁇ ⁇ (0 ⁇ 1), where score day+1 and score day represent the second interest value that attenuates interest according to time, day represents period, and ⁇ represents attenuation factor;
- the interest value includes the first interest value and the second interest value.
- the interest value decay can ensure that the earlier interest will become very weak after a period of time, while the recent interest will have a greater weight. According to factors such as the speed of user interest changes, user activity and other factors, interest can also be attenuated on a weekly, monthly, or hourly level.
- step S110 the analyzed drawing data is sent to the front end, so that the front end draws a plurality of data graphics according to the drawing data, and displays the data graphics.
- drawing data is drawn into data graphics by calling echarts through the front end; the drawn data graphics are not limited to: bar graphs, bubble graphs, doughnut graphs, and so on.
- the data graphics include: display the "geographical attributes" and "crowd attributes” information; through this chart, you can intuitively see the data after the query information has been analyzed by big data. Informing the user of the subsidiary information of the information inquired is convenient and efficient, and improves the query speed and the accuracy of the results.
- the drawing data when the drawing data is sent to the front end, a mark is drawn on the map for the drawing data, so that the format of the drawing data conforms to the format received by the front end.
- Special processing of the data that is, if the incoming Baidu map data is stored in the database, the metadata in the database is converted to Baidu map data.
- the conversion step includes formula conversion, and multiple copies of data are stored in the bottom layer. And so on.
- the Gaode map directly transfers the Baidu map data, there may be data omissions, and special processing is required, such as calculating the latitude and longitude offset to obtain more accurate data.
- the left and right linkage display data graphics can be realized.
- the map API can be adjusted to highlight and draw the thermal range circle on the map.
- you click on the coordinate point of the map it will be highlighted according to the Index index and the input list, so as to realize the visual linkage.
- the user analyzes according to the multiple data graphs to determine whether the destination is a destination address, if it is, then generates a corresponding traffic route, if not, then further inputs query information for re-planning.
- FIG. 5 shows a schematic diagram of the program modules of the second embodiment of the map display system of the present application.
- the map display system 20 may include or be divided into one or more program modules.
- the one or more program modules are stored in a storage medium and executed by one or more processors to complete the present invention. Apply and implement the above-mentioned map display method.
- the program module referred to in the embodiments of the present application refers to a series of computer program instruction segments capable of completing specific functions, and is more suitable for describing the execution process of the map display system 20 in the storage medium than the program itself. The following description will specifically introduce the functions of each program module in this embodiment:
- the first acquisition module 200 is configured to acquire map data display instructions, the map data display instructions including displayed destination information, radius range information, target product information, and crowd attribute information.
- the map data display instruction is used to display information that the user needs to query at the destination.
- Destination information can be geographic attributes, including: POI (points of interest) distribution map, distribution of people flow in different time periods (working days), distribution of people flow in different time periods (including holidays), transportation facilities, landmark buildings
- POI points of interest
- the radius range information includes: centered on the latitude and longitude of the destination, the preset radius range for users to choose;
- the target product information includes: the interest and demand of the people around the destination in the target product, etc.;
- the crowd attribute information includes : Gender, age, educational background, wealth distribution, consumption value and product demand of the people around the destination.
- the query information input by the user can be received through the input list, and then the map data display instruction can be obtained.
- the input list you can choose to search for product information and crowd attribute information, and you can also preset the radius information of the destination information to be queried to further narrow the scope of the query.
- the list of destination information includes: landmark building name, landmark building's longitude and latitude coordinate points based on Baidu Map API, and external health fields, etc.;
- the list of crowd attribute information includes information such as gender, age, and external health fields.
- the second obtaining module 202 is configured to obtain the longitude and latitude of the destination based on the destination information.
- the map is called according to the destination information to determine the latitude and longitude of the destination. If the user gives the corresponding fuzzy destination information, the information includes "POI list” or "POI marked in the map", you can enter the POI details and click, and then query the POI ranking displayed on the map, and the POI name will be displayed when the mouse is moved in The POI list and the POI marked in the map can be clicked, and the detailed data of this POI will be expanded when clicked; if the recommended location on the map is clicked, the map point of the recommended location will be changed to the destination, and the corresponding longitude and latitude will be obtained.
- the third obtaining module 204 is configured to obtain the longitude and latitude of the radius range of the destination according to the longitude and latitude of the destination and the radius range information.
- the radius range information is set in advance, indicating that the radius of the radius extending outward from the latitude and longitude of the destination as the center can be calculated from the latitude and longitude.
- the screening module 206 is configured to screen the target product information and the crowd attribute information within the latitude and longitude range of the radius range.
- the SQL statement to obtain the longitude and latitude of the destination information from the database.
- the longitude, latitude, and radius information (such as 10km) are used as input parameters. If the user selects more input in the list The conditions should also be passed in as an input.
- Call and start the SpringBoot framework based on http request to connect to the database; then route the request through servet to the corresponding processing layer for logical processing to obtain the corresponding routing address; according to the routing address, use SQL statements to query the corresponding target product information and crowd in the database Property information.
- the cluster analysis module 208 is configured to perform a cluster analysis on the target product information and the crowd attribute information to obtain drawing data corresponding to the target product information and the crowd attribute information.
- cluster analysis is performed on the target product information and the crowd attribute information to obtain drawing data that can be used for graphic drawing.
- the cluster analysis module 208 is further used for:
- the resident address and GPS portrait of the crowd attribute information are analyzed to obtain a geographic position portrait, and the geographic position portrait includes a plurality of location tags.
- the geographic location portrait is obtained by analyzing the target user's activity range. It is generally divided into two parts: one is the resident portrait; the other is the GPS portrait. The two types of portraits are quite different. Resident portraits are easier to construct and the tags are relatively stable. GPS portraits need to be updated in real time. Permanent residence includes three levels: country, province, and city, and generally only refines to the city's granularity. Resident location mining is based on the user's IP address information, analyzes the user's IP address, and corresponds to the corresponding city, and statistics on the city where the user's IP appears can get the permanent city label.
- the user's resident city tag can not only be used to count the distribution of users in various regions, but also can identify poor crowds, tourist crowds, etc. according to the user's travel trajectory between various cities.
- GPS data is generally collected from the mobile phone.
- the user uses the OneConnect App to authorize the App to obtain the user's GPS information and can obtain the user's GPS information.
- the agglomerated hierarchical clustering algorithm is used to analyze the resident address and the GPS profile. First, each resident address and the address label that needs to be clustered and the address label in the GPS profile are regarded as an atomic cluster, and then the multiple addresses are combined. A cluster of atoms is a larger and larger cluster, until all objects are in one cluster, or a certain end condition is met.
- the embodiment of the application adopts the minimum distance agglomerated hierarchical clustering algorithm flow:
- the similarity coefficient between the location tag and the destination information is calculated according to the Manhattan distance.
- the location label and the destination information are converted into corresponding vectors, the distance between the vector of the location label and the vector of the destination information is calculated according to the Manhattan distance metric calculation formula, and the reciprocal of the smallest Manhattan distance is taken as the similarity coefficient.
- the drawing data is filtered by judging whether the similarity coefficient is greater than a preset threshold.
- the similarity coefficient is greater than the preset threshold, use the location tags with the similarity coefficient greater than the preset threshold as the drawing data of the crowd attribute information; otherwise, set the similarity coefficient to be not greater than the preset threshold.
- the location label is deleted.
- the smaller the Manhattan distance, the larger the reciprocal, that is, the larger the similarity coefficient, and the location tag with the similarity coefficient greater than the preset threshold is selected as the drawing data of the destination information.
- the cluster analysis module 208 is further used for:
- the user portrait tag is obtained through information filled in by the user: such as QQ, facebook, etc., including user information such as age, gender, and income.
- the acquired crowd attribute information is processed to make the displayed image more accurate, including the creation of user portrait tags.
- the incomplete user information and the user portrait tags in the crowd attribute information are input into a tag diffusion model to improve the incomplete user information and obtain drawing data corresponding to the crowd attribute information.
- the user data obtained by the video website is counted. Assuming that about 30% of the users fill in the user information when registering, the user information of the 30% of the users is used as the training set. However, the features of watching movies are sparse features, and the accuracy of the user information filled in by registered users is not high. The parts with higher accuracy (such as complete user information) can be extracted from the 30% sample set for training as training data.
- the model is trained to build a label diffusion model.
- the tag diffusion model can predict the gender of the user by using the watched movie list.
- the prediction model can be MLlib, LR, FM, linear SVM, GBDT, etc., and the label diffusion model is obtained after training. Furthermore, it is possible to make auxiliary predictions based on the user's viewing time, browser, and viewing duration of the movie.
- the cluster analysis module 208 is further used for:
- clustering obtains an interest label system of the crowd attribute information, and the interest label system includes a plurality of label words.
- the interest label system can extract, label, and count core information from the massive amount of behavior data of users.
- Cluster keywords treat a category of keywords as a tag, or split articles under a category. For example, like "hot pot" hashtags between keywords and categories, you can use text topic clustering to complete the construction of hashtags. That is, the content modeling of the "category-topic-keyword" three-layer tag system from rough to detailed for historically browsed articles has been completed.
- the interest label system includes the classification, themes and keywords of the target product, clustering analysis of the topics of each classification, and association with the keywords.
- the formula for calculating the interest value of the tag system is:
- score j+1 ⁇ score j +C ⁇ weight
- the interest value can be expressed as the user clicks on the target product, and all tags of the target product of the user are added to the user's interest by one.
- the interest value is attenuated to obtain the drawing data of the target product information.
- the attenuating the interest value includes:
- score i+1 ⁇ score i +C ⁇ weight(0 ⁇ 1), where score i+1 and score i represent the first interest value that attenuates interest according to the number of times, ⁇ represents the attenuation factor, and weight represents The weight value of the tag word, i represents the number of times, each time the last score is attenuated, and the final score will converge to a stable value.
- ⁇ 0.9, the score will be infinitely close to 10;
- score day+1 score day ⁇ ⁇ (0 ⁇ 1), where score day+1 and score day represent the second interest value that attenuates interest according to time, day represents period, and ⁇ represents attenuation factor;
- the interest value includes the first interest value and the second interest value.
- the interest value decay can ensure that the earlier interest will become very weak after a period of time, while the recent interest will have a greater weight. According to factors such as the speed of user interest changes, user activity, etc., interest can also be attenuated on a weekly, monthly, or hourly level.
- the drawing module 210 is configured to send the analyzed drawing data to the front end, so that the front end draws a plurality of data graphics according to the drawing data, and displays the data graphics.
- drawing data is drawn into data graphics by calling echarts through the front end; the drawn data graphics are not limited to: bar graphs, bubble graphs, doughnut graphs, and so on.
- the data graphics include: display the "geographical attributes" and "crowd attributes” information; through this chart, you can intuitively see the data after the query information has been analyzed by big data. Informing the user of the subsidiary information of the information inquired is convenient and efficient, and improves the query speed and the accuracy of the results.
- the computer device 2 is a device that can automatically perform numerical calculation and/or information processing according to pre-set or stored instructions.
- the computer device 2 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server or a server cluster composed of multiple servers).
- the computer device 2 at least includes, but is not limited to, a memory 21, a processor 22, a network interface 23, and a map display system 20 that can communicate with each other through a system bus.
- the memory 21 includes at least one type of computer-readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory ( RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disks, optical disks, etc.
- the memory 21 may be an internal storage unit of the computer device 2, for example, a hard disk or a memory of the computer device 2.
- the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a smart media card (SMC), and a secure digital (Secure Digital, SMC) equipped on the computer device 2. SD) card, flash card (Flash Card), etc.
- the memory 21 may also include both the internal storage unit of the computer device 2 and its external storage device.
- the memory 21 is generally used to store the operating system and various application software installed in the computer device 2, for example, the program code of the map display system 20 in the second embodiment.
- the map data display instruction includes displayed destination information, radius range information, target product information, and crowd attribute information; obtains the longitude and latitude of the destination based on the destination information; according to the longitude and latitude of the destination and the radius range information, Obtain the latitude and longitude of the radius of the destination; filter the target product information and the crowd attribute information within the latitude and longitude of the radius range; perform cluster analysis on the target product information and the crowd attribute information, To obtain the drawing data corresponding to the target product information and the crowd attribute information; send the drawing data to the front end, so that the front end draws a plurality of data graphics according to the drawing data, and displays the data graphics.
- the memory 21 can also be used to temporarily store various types of data that have been output or will be output.
- the processor 22 may be a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor, or other data processing chips.
- the processor 22 is generally used to control the overall operation of the computer device 2.
- the processor 22 is used to run the program code or process data stored in the memory 21, for example, to run the map display system 20, so as to implement the map display method of the first embodiment.
- the network interface 23 may include a wireless network interface or a wired network interface, and the network interface 23 is generally used to establish a communication connection between the server 2 and other electronic devices.
- the network interface 23 is used to connect the server 2 to an external terminal through a network, and to establish a data transmission channel and a communication connection between the server 2 and the external terminal.
- the network may be Intranet, Internet, Global System of Mobile Communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G Network, Bluetooth (Bluetooth), Wi-Fi and other wireless or wired networks.
- FIG. 6 only shows the computer device 2 with components 20-23, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.
- the map display system 20 stored in the memory 21 may also be divided into one or more program modules.
- the one or more program modules are stored in the memory 21 and are composed of one or more program modules. It is executed by two processors (the processor 22 in this embodiment) to complete the application.
- FIG. 5 shows a schematic diagram of program modules for implementing the second embodiment of the map display system 20.
- the map display system 20 can be divided into a first acquisition module 200, a second acquisition module 202, and a second acquisition module.
- the program module referred to in this application refers to a series of computer program instruction segments that can complete specific functions, and is more suitable than a program to describe the execution process of the map display system 20 in the computer device 2.
- the specific functions of the program modules 200-210 have been described in detail in the second embodiment, and will not be repeated here.
- the computer-readable storage medium may be non-volatile or volatile, such as flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX). Memory, etc.), random access memory (RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory , Magnetic disks, optical disks, servers, App application malls, etc., on which computer programs are stored, and the corresponding functions are realized when the programs are executed by the processor.
- RAM random access memory
- SRAM static random access memory
- ROM read only memory
- EEPROM electrically erasable programmable read only memory
- PROM programmable read only memory
- magnetic memory Magnetic disks, optical disks, servers, App application malls, etc.
- the computer-readable storage medium of this embodiment is used to store the map display system 20, and when executed by the processor, the map display method of the first embodiment is implemented, wherein the map display method includes: obtaining a map data display instruction, the map data
- the display instructions include displayed destination information, radius range information, target product information, and crowd attribute information; obtain the longitude and latitude of the destination based on the destination information; obtain the longitude and latitude of the destination and the radius range information according to the destination information.
- the latitude and longitude of the radius of the destination screening the target product information and the crowd attribute information within the latitude and longitude of the radius; performing cluster analysis on the target product information and the crowd attribute information to obtain all
- the target product information and the drawing data corresponding to the crowd attribute information is sent to the front end, so that the front end draws a plurality of data graphics according to the drawing data, and displays the data graphics.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
一种地图展示方法,包括:获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息(S100);基于所述目的地信息获取目的地的经纬度(S102);根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的经纬度(S104);筛选所述半径范围的经纬度范围内的所述目标产品信息和所述人群属性信息(S106);对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据(S108)。可以直观的在地图上展示所需信息,以供用户进行查看。
Description
本申请要求于2020年2月20日提交中国专利局、申请号为202010103441.X,发明名称为“地图展示方法与***”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。
本申请实施例涉及智慧城市中的地图数据处理领域,尤其涉及一种地图展示方法与***。
地图是个很方便的软件,能够在陌生的地方迅速找到去目的地的路线,但是现有的地图只是输入要查询的地方,显示出当前位置到查询位置的交通路线,且提供可供选择的路线,只有交通路线。
发明人意识到,若要通过地图查询目的地附近美食等,不可以直观的看到,要到目的地附近才可进行查询,耗时耗力。
发明内容
有鉴于此,本申请实施例的目的是提供一种地图展示方法与***,可以直观的在地图上展示所需信息,以供用户进行查看。
为实现上述目的,本申请实施例提供了一种地图展示方法,包括:
获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息;
基于所述目的地信息获取目的地的经纬度;
根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的经纬度;
筛选所述半径范围的经纬度范围内的所述目标产品信息和所述人群属性信息;
对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据;
将所述绘图数据发送给前端,以使所述前端根据所述绘图数据绘制多个数据图形,并展示所述数据图形。
为实现上述目的,本申请实施例还提供了一种地图展示***,包括:
第一获取模块,用于获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息;
第二获取模块,用于基于所述目的地信息获取目的地的经纬度;
第三获取模块,用于根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的经纬度;
筛选模块,用于筛选所述半径范围的经纬度范围内的所述目标产品信息和所述人群属性信息;
聚类分析模块,用于对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据;
绘制模块,用于将所述绘图数据发送给前端,以使所述前端根据所述绘图数据绘制多个数据图形,并展示所述数据图形。
进一步地,所述聚类分析模块还用于:
根据所述人群属性信息,聚类得到所述人群属性信息的兴趣标签体系,所述兴趣标签体系包括多个标签词;
计算每个所述标签词与所述目标产品信息的兴趣值;
对所述兴趣值进行衰减,以得到所述目标产品信息的绘图数据。
为实现上述目的,本申请实施例还提供了一种计算机设备,所述计算机设备包括存储器、处理器,所述存储器上存储有可在所述处理器上运行的计算机程序,所述计算机程序被所述处理器执行时实现如上所述的地图展示方法的步骤,其中,地图展示方法至少包括:
获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息;
基于所述目的地信息获取目的地的经纬度;
根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的经纬度;
筛选所述半径范围的经纬度范围内的所述目标产品信息和所述人群属性信息;
对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据;
将所述绘图数据发送给前端,以使所述前端根据所述绘图数据绘制多个数据图形,并展示所述数据图形。
为实现上述目的,本申请实施例还提供了一种计算机可读存储介质,所述计算机可读存储介质内存储有计算机程序,所述计算机程序可被至少一个处理器所执行,以使所述至少一个处理器执行如上所述的地图展示方法的步骤,其中,地图展示方法至少包括:
获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息;
基于所述目的地信息获取目的地的经纬度;
根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的经纬度;
筛选所述半径范围的经纬度范围内的所述目标产品信息和所述人群属性信息;
对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据;
将所述绘图数据发送给前端,以使所述前端根据所述绘图数据绘制多个数据图形,并展示所述数据图形。
本申请实施例提供的地图展示方法、***计算机设备和存储介质,通过地图数据显示指令获取目的地信息、半径范围信息、目标产品信息和人群属性信息对应的绘图数据,并对该绘图数据进行分析,再将经分析后的绘图数据发送给前端,以使前端根据所述绘图数据绘制多个数据图形,并展示数据图形,以供用户进行查看。
图1为本申请地图展示方法实施例一的流程图。
图2为本申请实施例一图1中步骤S108的实施例一的流程图。
图3为本申请实施例一图1中步骤S108的实施例二的流程图。
图4为本申请实施例一图1中步骤S108的实施例三的流程图。
图5为本申请地图展示***实施例二的程序模块示意图。
图6为本申请计算机设备实施例三的硬件结构示意图。
实施例一
参阅图1,示出了本申请实施例一之地图展示方法的步骤流程图。可以理解,本方法实施例中的流程图不用于对执行步骤的顺序进行限定。下面以服务器为执行主体进行示例性描述。具体如下。
步骤S100,获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息。
具体地,地图数据显示指令用于显示用户根据需求,在目的地进行查询的信息。目的地信息可以为地理属性,包括:POI(城市中的兴趣点,points of interest)分布图、不同时间段人流分布(工作日)、不同时间段人流分布(含节假日)、交通设施、标志建筑等;半径范围信息包括:以目的地的经纬度为中心,预设的半径范围,以供用户进行选择;目标产品信息包括:目的地周边人群对目标产品的兴趣度、需求等;人群属性信息包括:目的地周边人群的性别、年龄、学历、财富值分布、消费值与产品需求等。
示例性地,可通过输入列表接收用户输入的查询信息,进而得到地图数据显示指令。在输入列表中,可选择搜索的产品信息及人群属性信息,还可预先设置所要查询的目的地信息的半径范围信息,以进一步缩小查询范围。
例如:目的地信息的的列表包括:标志建筑名称、标志建筑基于百度地图API的经纬度坐标点与外健字段等信息;
人群属性信息的的列表包括:性别、年龄与外健字段等信息。
步骤S102,基于所述目的地信息获取目的地的经纬度。
具体地,根据目的地信息调用地图,确定目的地的经纬度。若用户给出的是相应的模糊目的地信息,信息包括“POI列表”或“地图中标注的POI”,可进入POI详情进行点击, 再查询地图中展示的POI排名,鼠标移入会显示POI名称;POI列表和地图中标注的POI均可点击,点击时展开这个POI的详细数据;若点中地图的推荐地点,则推荐地点的地图点改为目的地,获取相应的经纬度。
步骤S104,根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的经纬度。
具体地,半径范围信息预先进行设置,表示以目的地的经纬度为中心,向外延伸半径的半径长度,从经纬度上可计算得到。
步骤S106,筛选所述半径范围的经纬度范围内的所述目标产品信息和所述人群属性信息。
具体地,调用SQL语句从数据库获取目的地信息的目的地的经纬度,得到目的地信息的经纬度后将经纬度、半径范围信息(如:10km)当作入参,如果用户选择了更多输入列表里的条件,也要一并当作入参传入。通过http请求调用并启动基于SpringBoot框架以连接数据库;再通过servet路由请求到对应的处理层进行逻辑处理,得到对应的路由地址;根据路由地址,利用SQL语句查询数据库里的对应目标产品信息和人群属性信息。
步骤S108,对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据。
具体地,将目标产品信息和人群属性信息进行聚类分析,以得到可以进行图形绘制的绘图数据。
示例性地,参阅图2,步骤S108的实施例一包括:
步骤S108A1,分析所述人群属性信息中的常驻地址与GPS画像,得到地理位置画像,所述地理位置画像包括多个位置标签。
具体地,地理位置画像根据目标用户的活动范围进行分析得到。一般分为两部分:一部分是常驻地画像;一部分是GPS画像。两类画像的差别很大,常驻地画像比较容易构造,且标签比较稳定,GPS画像需要实时更新。常驻地包括国家、省份、城市三级,一般只细化到城市粒度。常驻地的挖掘基于用户的IP地址信息,对用户的IP地址进行解析,对应到相应的城市,对用户IP出现的城市进行统计就可以得到常驻城市标签。用户的常驻城市标签,不仅可以用来统计各个地域的用户分布,还可以根据用户在各个城市之间的出行轨迹识别出差人群、旅游人群等。GPS数据一般从手机端收集,用户使用壹账通App授权App获取用户GPS信息的权限,能够获取用户GPS信息。
具体地,采用凝聚的层次聚类算法对常驻地址与GPS画像进行分析,先将每个常驻地址与中需要聚类的地址标签与GPS画像中的地址标签作为一个原子簇,然后合并多个原子簇为越来越大的簇,直到所有对象都在一个簇中,或者某个终结条件被满足。本申请实施例采用最小距离的凝聚层次聚类算法流程:
(1)、将每个地址标签看作一类,计算两两地址标签之间的最小距离;
(2)、将距离最小的两个类合并成一个新类;
(3)、重新计算新类与所有类之间的距离;
(4)、重复上述步骤(2)与(3),直到所有类最后合并成一类。
步骤S108A2,根据曼哈顿距离计算所述位置标签与所述目的地信息的相似度系数。
具体地,将位置标签与目的地信息转换为对应的向量,根据曼哈顿距离度量计算公式计算位置标签的向量与目的地信息的向量的距离,取最小的曼哈顿距离的倒数作为相似度系数。
步骤S108A3,判断所述相似度系数是否大于预设阈值。
具体地,曼哈顿距离越小,倒数越大,即相似度系数越大,通过判断相似度系数是否大于预设阈值,筛选绘图数据。
步骤S108A4,若所述相似度系数大于预设阈值,则将所述相似度系数大于预设阈值的位置标签,作为所述人群属性信息的绘图数据;反之,将所述相似度系数不大于预设阈值的位置标签删除。
具体地,曼哈顿距离越小,倒数越大,即相似度系数越大,选取相似度系数大于预设阈值的位置标签作为目的地信息的绘图数据。
示例性地,参阅图3,步骤S108的实施例二包括:
步骤S108B1,获取所述人群属性信息中完整用户信息。
具体地,用户画像标签通过用户填写的信息获取:如QQ、facebook等,包括有年龄、性别、收入等用户信息。
步骤S108B2,对所述完整用户信息进行聚类,得到所述完整用户信息的用户画像标签。
具体地,对获取的人群属性信息进行处理,以使显示的图像更加精确,包括建立用户画像标签。
步骤S108B3,将所述人群属性信息中非完整用户信息与所述用户画像标签输入至标签扩散模型,以完善所述非完整用户信息,得到所述人群属性信息对应的绘图数据。
具体地,但若有些用户填写的用户信息不完善,且有些社交软件不需要填写用户信息(如输入法、团购APP、视频网站等),则无法获取完整的用户信息,基于上述用户信息建立的用户画像标签不够准确。因此需要将用户信息补充完善:将完整用户信息的用户作为样本数据,将样本数据输入至标签扩散模型进行训练,以得到对非完整用户信息的预测。
以在视频网站中的用户画像标签的性别训练标签扩散模型为例:
对视频网站获取的用户数据进行统计,假设有大约30%的用户在注册时填写了用户信息,将该30%的用户的用户信息作为训练集。但观看影片特征是稀疏特征,且注册用户填写的用户信息本身的准确率不高,可以从30%的样本集中提取准确率较高的部分(如完整用户信息)用于训练,作为训练数据。获取训练数据中男性和女性分别观看的影片列表;计算男性与女性对每个影片的兴趣度;将影片作为预测模型的输入,对应的性别作为预测模型的输出,兴趣度作为判断标准,对预测模型进行训练,以构建标签扩散模型。标签扩散模型可以达到利用观看的影片列表来预测用户性别。预测模型可以为MLlib,LR、FM、线性SVM、GBDT等模 型,训练后得到标签扩散模型。进一步还可以通过用户的观看影片的时间、浏览器、观看时长等进行辅助预测。
示例性地,参阅图4,步骤S108的实施例三包括:
步骤S108C1,根据所述人群属性信息,聚类得到所述人群属性信息的兴趣标签体系,所述兴趣标签体系包括多个标签词。
具体地,兴趣标签体系可以从用户的海量行为数据中进行核心信息的抽取、标签化和统计。获取用户的历史浏览文章,并且提取历史浏览文章中的关键词,尤其是专有名词(人名、机构名),这些词也表示了用户的兴趣。将关键词进行聚类,把一类关键词当成一个标签,或者把一个分类下的文章进行拆分。比如有如“火锅”介于关键词和分类之间的主题标签,可以使用文本主题聚类完成主题标签的构建。即完成了对历史浏览文章从粗到细的“分类-主题-关键词”三层标签体系内容建模。当用户的关键词中有美食时,能够直接给用户进行推荐;而对于比较小众的主题(如火锅类的羊肉火锅),若当天没有进行推送,可以根据分类标签进行推荐。兴趣标签体系包括目标产品的分类、主题与关键词,对每个分类的主题进行聚类分析,并且与关键词进行关联。
步骤S104C2,计算每个所述标签词与所述目标产品信息的兴趣值。
示例性地,所述计算所述标签体系的兴趣值的公式为:
score
j+1=α×score
j+C×weight;
其中,若所述标签词在所述目标产品信息中出现,则C=1,反之,则C=0;weight表示标签词的权重值,score
j+1与score
j表示标签词的兴趣值;j为整数。
具体地,兴趣值可以表示为用户点击了目标产品,就把用户对该目标产品的所有标签在用户兴趣上加一。
步骤S108C3,对所述兴趣值进行衰减,以得到所述目标产品信息的绘图数据。
示例性地,所述对所述兴趣值进行衰减包括:
对所述兴趣值进行次数衰减和时间衰减;
所述次数衰减的计算公式为:
score
i+1=α×score
i+C×weight(0<α<1),其中,score
i+1与score
i表示根据次数对兴趣进行衰减的第一兴趣值,α表示衰减因子,weight表示标签词的权重值,i表示次数,每次都对上一次的分数做衰减,最终得分会收敛到一个稳定值,α取0.9时,得分会无限接近10;
所述时间衰减的计算公式为:
score
day+1=score
day×β(0<β<1),其中,score
day+1与score
day表示根据时间对兴趣进行衰减的第二兴趣值,day表示周期,β表示衰减因子;
所述兴趣值包括所述第一兴趣值与所述第二兴趣值。
具体地,兴趣值衰减可以保证时间较早的兴趣会在一段时间以后变的非常弱,同时近期的兴趣会有更大的权重。根据用户兴趣变化的速度、用户活跃度等因素,也可以对兴趣进 行周级别、月级别或小时级别的衰减。
步骤S110,将经分析后的绘图数据发送给前端,以使所述前端根据所述绘图数据绘制多个数据图形,并展示所述数据图形。
具体地,通过前端调用echarts将绘图数据绘制成数据图形;绘制的数据图形不限于:柱状图、气泡图、圆环图等。使用echarts进行数据图形的绘制后传输至前端,数据图形包括有:展示该“地理属性”和“人群属性”信息;通过此图表可以很直观的看到查询信息经过大数据统计分析之后的数据,告知用户所查询的信息的附属信息,方便高效,而且提高查询速度和结果的准确性。
示例性地,将所述绘图数据发送给前端时,并将绘图数据在地图上绘制标记,以使所述绘图数据的格式符合所述前端接收的格式。对数据进行特殊处理,即如果传入的是百度地图数据,数据库里存的是高德地图数据,将数据库里的元数据转为百度地图的数据,转换步骤有公式转换,底层存多份数据等方式。但高德地图直接转百度地图数据,可能会出现数据遗漏情况,需要做特殊处理,例如进行经纬度偏移计算,进而得到更准确的数据。
示例性地,可以实现左右联动显示数据图形,当获取到目的地的经纬度时,调地图API在地图上高亮显示并绘制热力范围圈。当点击地图的坐标点时,根据Index索引与输入列表进行高亮显示,从而实现视觉上的联动。
示例性地,所述用户根据所述多个数据图形进行分析,以判断所述目的地是否为目的地址,若是,则生成相应的交通路线,若否,则进一步输入查询信息进行重新规划。
实施例二
请继续参阅图5,示出了本申请地图展示***实施例二的程序模块示意图。在本实施例中,地图展示***20可以包括或被分割成一个或多个程序模块,一个或者多个程序模块被存储于存储介质中,并由一个或多个处理器所执行,以完成本申请,并可实现上述地图展示方法。本申请实施例所称的程序模块是指能够完成特定功能的一系列计算机程序指令段,比程序本身更适合于描述地图展示***20在存储介质中的执行过程。以下描述将具体介绍本实施例各程序模块的功能:
第一获取模块200,用于获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息。
具体地,地图数据显示指令用于显示用户根据需求,在目的地进行查询的信息。目的地信息可以为地理属性,包括:POI(城市中的兴趣点,points of interest)分布图、不同时间段人流分布(工作日)、不同时间段人流分布(含节假日)、交通设施、标志建筑等;半径范围信息包括:以目的地的经纬度为中心,预设的半径范围,以供用户进行选择;目标产品信息包括:目的地周边人群对目标产品的兴趣度、需求等;人群属性信息包括:目的地周边人群的性别、年龄、学历、财富值分布、消费值与产品需求等。
示例性地,可通过输入列表接收用户输入的查询信息,进而得到地图数据显示指令。 在输入列表中,可选择搜索的产品信息及人群属性信息,还可预先设置所要查询的目的地信息的半径范围信息,以进一步缩小查询范围。
例如:目的地信息的的列表包括:标志建筑名称、标志建筑基于百度地图API的经纬度坐标点与外健字段等信息;
人群属性信息的的列表包括:性别、年龄与外健字段等信息。
第二获取模块202,用于基于所述目的地信息获取目的地的经纬度。
具体地,根据目的地信息调用地图,确定目的地的经纬度。若用户给出的是相应的模糊目的地信息,信息包括“POI列表”或“地图中标注的POI”,可进入POI详情进行点击,再查询地图中展示的POI排名,鼠标移入会显示POI名称;POI列表和地图中标注的POI均可点击,点击时展开这个POI的详细数据;若点中地图的推荐地点,则推荐地点的地图点改为目的地,获取相应的经纬度。
第三获取模块204,用于根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的经纬度。
具体地,半径范围信息预先进行设置,表示以目的地的经纬度为中心,向外延伸半径的半径长度,从经纬度上可计算得到。
筛选模块206,用于筛选所述半径范围的经纬度范围内的所述目标产品信息和所述人群属性信息。
具体地,调用SQL语句从数据库获取目的地信息的目的地的经纬度,得到目的地信息的经纬度后将经纬度、半径范围信息(如:10km)当作入参,如果用户选择了更多输入列表里的条件,也要一并当作入参传入。通过http请求调用并启动基于SpringBoot框架以连接数据库;再通过servet路由请求到对应的处理层进行逻辑处理,得到对应的路由地址;根据路由地址,利用SQL语句查询数据库里的对应目标产品信息和人群属性信息。
聚类分析模块208,用于对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据。
具体地,将目标产品信息和人群属性信息进行聚类分析,以得到可以进行图形绘制的绘图数据。
示例性地,所述聚类分析模块208还用于:
分析所述人群属性信息的常驻地址与GPS画像,得到地理位置画像,所述地理位置画像包括多个位置标签。
具体地,地理位置画像根据目标用户的活动范围进行分析得到。一般分为两部分:一部分是常驻地画像;一部分是GPS画像。两类画像的差别很大,常驻地画像比较容易构造,且标签比较稳定,GPS画像需要实时更新。常驻地包括国家、省份、城市三级,一般只细化到城市粒度。常驻地的挖掘基于用户的IP地址信息,对用户的IP地址进行解析,对应到相应的城市,对用户IP出现的城市进行统计就可以得到常驻城市标签。用户的常驻城市标签,不仅可以用来统计各个地域的用户分布,还可以根据用户在各个城市之间的出行轨迹识别出 差人群、旅游人群等。GPS数据一般从手机端收集,用户使用壹账通App授权App获取用户GPS信息的权限,能够获取用户GPS信息。
具体地,采用凝聚的层次聚类算法对常驻地址与GPS画像进行分析,先将每个常驻地址与中需要聚类的地址标签与GPS画像中的地址标签作为一个原子簇,然后合并多个原子簇为越来越大的簇,直到所有对象都在一个簇中,或者某个终结条件被满足。本申请实施例采用最小距离的凝聚层次聚类算法流程:
(1)、将每个地址标签看作一类,计算两两地址标签之间的最小距离;
(2)、将距离最小的两个类合并成一个新类;
(3)、重新计算新类与所有类之间的距离;
(4)、重复上述步骤(2)与(3),直到所有类最后合并成一类。
根据曼哈顿距离计算所述位置标签与所述目的地信息的相似度系数。
具体地,将位置标签与目的地信息转换为对应的向量,根据曼哈顿距离度量计算公式计算位置标签的向量与目的地信息的向量的距离,取最小的曼哈顿距离的倒数作为相似度系数。
判断所述相似度系数是否大于预设阈值。
具体地,曼哈顿距离越小,倒数越大,即相似度系数越大,通过判断相似度系数是否大于预设阈值,筛选绘图数据。
若所述相似度系数大于预设阈值,则将所述相似度系数大于预设阈值的位置标签,作为所述人群属性信息的绘图数据;反之,将所述相似度系数不大于预设阈值的位置标签删除。
具体地,曼哈顿距离越小,倒数越大,即相似度系数越大,选取相似度系数大于预设阈值的位置标签作为目的地信息的绘图数据。
示例性地,所述聚类分析模块208还用于:
获取所述人群属性信息中完整用户信息。
具体地,用户画像标签通过用户填写的信息获取:如QQ、facebook等,包括有年龄、性别、收入等用户信息。
对所述完整用户信息进行聚类,得到所述完整用户信息的用户画像标签。
具体地,对获取的人群属性信息进行处理,以使显示的图像更加精确,包括建立用户画像标签。
将所述人群属性信息中非完整用户信息与所述用户画像标签输入至标签扩散模型,以完善所述非完整用户信息,得到所述人群属性信息对应的绘图数据。
具体地,但若有些用户填写的用户信息不完善,且有些社交软件不需要填写用户信息(如输入法、团购APP、视频网站等),则无法获取完整的用户信息,基于上述用户信息建立的用户画像标签不够准确。因此需要将用户信息补充完善:将完整用户信息的用户作为样本数据,将样本数据输入至标签扩散模型进行训练,以得到对非完整用户信息的预测。
以在视频网站中的用户画像标签的性别训练标签扩散模型为例:
对视频网站获取的用户数据进行统计,假设有大约30%的用户在注册时填写了用户信息,将该30%的用户的用户信息作为训练集。但观看影片特征是稀疏特征,且注册用户填写的用户信息本身的准确率不高,可以从30%的样本集中提取准确率较高的部分(如完整用户信息)用于训练,作为训练数据。获取训练数据中男性和女性分别观看的影片列表;计算男性与女性对每个影片的兴趣度;将影片作为预测模型的输入,对应的性别作为预测模型的输出,兴趣度作为判断标准,对预测模型进行训练,以构建标签扩散模型。标签扩散模型可以达到利用观看的影片列表来预测用户性别。预测模型可以为MLlib,LR、FM、线性SVM、GBDT等模型,训练后得到标签扩散模型。进一步还可以通过用户的观看影片的时间、浏览器、观看时长等进行辅助预测。
示例性地,所述聚类分析模块208还用于:
根据所述人群属性信息,聚类得到所述人群属性信息的兴趣标签体系,所述兴趣标签体系包括多个标签词。
具体地,兴趣标签体系可以从用户的海量行为数据中进行核心信息的抽取、标签化和统计。获取用户的历史浏览文章,并且提取历史浏览文章中的关键词,尤其是专有名词(人名、机构名),这些词也表示了用户的兴趣。将关键词进行聚类,把一类关键词当成一个标签,或者把一个分类下的文章进行拆分。比如有如“火锅”介于关键词和分类之间的主题标签,可以使用文本主题聚类完成主题标签的构建。即完成了对历史浏览文章从粗到细的“分类-主题-关键词”三层标签体系内容建模。当用户的关键词中有美食时,能够直接给用户进行推荐;而对于比较小众的主题(如火锅类的羊肉火锅),若当天没有进行推送,可以根据分类标签进行推荐。兴趣标签体系包括目标产品的分类、主题与关键词,对每个分类的主题进行聚类分析,并且与关键词进行关联。
计算每个所述标签词与所述目标产品信息的兴趣值。
示例性地,所述计算所述标签体系的兴趣值的公式为:
score
j+1=α×score
j+C×weight;
其中,若所述标签词在所述目标产品信息中出现,则C=1,反之,则C=0;weight表示标签词的权重值,score
j+1与score
j表示标签词的兴趣值;j为整数。
具体地,兴趣值可以表示为用户点击了目标产品,就把用户对该目标产品的所有标签在用户兴趣上加一。
对所述兴趣值进行衰减,以得到所述目标产品信息的绘图数据。
示例性地,所述对所述兴趣值进行衰减包括:
对所述兴趣值进行次数衰减和时间衰减;
所述次数衰减的计算公式为:
score
i+1=α×score
i+C×weight(0<α<1),其中,score
i+1与score
i表示根据次数对兴趣进行衰减的第一兴趣值,α表示衰减因子,weight表示标签词的权重值,i表示次数,每次都对上一次的分数做衰减,最终得分会收敛到一个稳定值,α取0.9时,得分会 无限接近10;
所述时间衰减的计算公式为:
score
day+1=score
day×β(0<β<1),其中,score
day+1与score
day表示根据时间对兴趣进行衰减的第二兴趣值,day表示周期,β表示衰减因子;
所述兴趣值包括所述第一兴趣值与所述第二兴趣值。
具体地,兴趣值衰减可以保证时间较早的兴趣会在一段时间以后变的非常弱,同时近期的兴趣会有更大的权重。根据用户兴趣变化的速度、用户活跃度等因素,也可以对兴趣进行周级别、月级别或小时级别的衰减。
绘制模块210,用于将经分析后的绘图数据发送给前端,以使所述前端根据所述绘图数据绘制多个数据图形,并展示所述数据图形。
具体地,通过前端调用echarts将绘图数据绘制成数据图形;绘制的数据图形不限于:柱状图、气泡图、圆环图等。使用echarts进行数据图形的绘制后传输至前端,数据图形包括有:展示该“地理属性”和“人群属性”信息;通过此图表可以很直观的看到查询信息经过大数据统计分析之后的数据,告知用户所查询的信息的附属信息,方便高效,而且提高查询速度和结果的准确性。
实施例三
参阅图6,是本申请实施例三之计算机设备的硬件架构示意图。本实施例中,所述计算机设备2是一种能够按照事先设定或者存储的指令,自动进行数值计算和/或信息处理的设备。该计算机设备2可以是机架式服务器、刀片式服务器、塔式服务器或机柜式服务器(包括独立的服务器,或者多个服务器所组成的服务器集群)等。如图6所示,所述计算机设备2至少包括,但不限于,可通过***总线相互通信连接存储器21、处理器22、网络接口23、以及地图展示***20。
本实施例中,存储器21至少包括一种类型的计算机可读存储介质,所述可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如,SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中,存储器21可以是计算机设备2的内部存储单元,例如该计算机设备2的硬盘或内存。在另一些实施例中,存储器21也可以是计算机设备2的外部存储设备,例如该计算机设备2上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。当然,存储器21还可以既包括计算机设备2的内部存储单元也包括其外部存储设备。本实施例中,存储器21通常用于存储安装于计算机设备2的操作***和各类应用软件,例如实施例二的地图展示***20的程序代码,至少实现以下步骤:获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息;基于所述目的地信息获取目的地的经纬度;根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的经纬度;筛选所述半径范围的经纬度范围 内的所述目标产品信息和所述人群属性信息;对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据;将所述绘图数据发送给前端,以使所述前端根据所述绘图数据绘制多个数据图形,并展示所述数据图形。此外,存储器21还可以用于暂时地存储已经输出或者将要输出的各类数据。
处理器22在一些实施例中可以是中央处理器(Central Processing Unit,CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。该处理器22通常用于控制计算机设备2的总体操作。本实施例中,处理器22用于运行存储器21中存储的程序代码或者处理数据,例如运行地图展示***20,以实现实施例一的地图展示方法。
所述网络接口23可包括无线网络接口或有线网络接口,该网络接口23通常用于在所述服务器2与其他电子装置之间建立通信连接。例如,所述网络接口23用于通过网络将所述服务器2与外部终端相连,在所述服务器2与外部终端之间的建立数据传输通道和通信连接等。所述网络可以是企业内部网(Intranet)、互联网(Internet)、全球移动通讯***(Global System of Mobile communication,GSM)、宽带码分多址(Wideband Code Division Multiple Access,WCDMA)、4G网络、5G网络、蓝牙(Bluetooth)、Wi-Fi等无线或有线网络。
需要指出的是,图6仅示出了具有部件20-23的计算机设备2,但是应理解的是,并不要求实施所有示出的部件,可以替代的实施更多或者更少的部件。
在本实施例中,存储于存储器21中的所述地图展示***20还可以被分割为一个或者多个程序模块,所述一个或者多个程序模块被存储于存储器21中,并由一个或多个处理器(本实施例为处理器22)所执行,以完成本申请。
例如,图5示出了所述实现地图展示***20实施例二的程序模块示意图,该实施例中,所述地图展示***20可以被划分为第一获取模块200、第二获取模块202、第三获取模块204、筛选模块206、聚类分析208与绘制模块210。其中,本申请所称的程序模块是指能够完成特定功能的一系列计算机程序指令段,比程序更适合于描述所述地图展示***20在所述计算机设备2中的执行过程。所述程序模块200-210的具体功能在实施例二中已有详细描述,在此不再赘述。
实施例四
本实施例还提供一种计算机可读存储介质,所述计算机可读存储介质可以是非易失性,也可以是易失性,如闪存、硬盘、多媒体卡、卡型存储器(例如,SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘、服务器、App应用商城等等,其上存储有计算机程序,程序被处理器执行时实现相应功能。本实施例的计算机可读存储介质用于存储地图展示***20,被处理器执行时实现实施例一的地图展示方法,其中,所述地图展示方法包括:获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息;基于所述目的地信息获取目的地的经纬度;根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的 经纬度;筛选所述半径范围的经纬度范围内的所述目标产品信息和所述人群属性信息;对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据;将所述绘图数据发送给前端,以使所述前端根据所述绘图数据绘制多个数据图形,并展示所述数据图形。
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。
以上仅为本申请的优选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。
Claims (20)
- 一种地图展示方法,其中,包括:获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息;基于所述目的地信息获取目的地的经纬度;根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的经纬度;筛选所述半径范围的经纬度范围内的所述目标产品信息和所述人群属性信息;对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据;将所述绘图数据发送给前端,以使所述前端根据所述绘图数据绘制多个数据图形,并展示所述数据图形。
- 根据权利要求1所述的地图展示方法,其中,所述对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据包括:分析所述人群属性信息中的常驻地址与GPS画像,得到地理位置画像,所述地理位置画像包括多个位置标签;根据曼哈顿距离计算所述位置标签与所述目的地信息的相似度系数;判断所述相似度系数是否大于预设阈值;若所述相似度系数大于预设阈值,则将所述相似度系数大于预设阈值的位置标签,作为所述人群属性信息的绘图数据;反之,将所述相似度系数不大于预设阈值的位置标签删除。
- 根据权利要求1所述的地图展示方法,其中,所述对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据包括:获取所述人群属性信息中完整用户信息;对所述完整用户信息进行聚类,得到所述完整用户信息的用户画像标签;将所述人群属性信息中非完整用户信息与所述用户画像标签输入至标签扩散模型,以完善所述非完整用户信息,得到所述人群属性信息对应的绘图数据。
- 根据权利要求1所述的地图展示方法,其中,所述对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据包括:根据所述人群属性信息,聚类得到所述人群属性信息的兴趣标签体系,所述兴趣标签体系包括多个标签词;计算每个所述标签词与所述目标产品信息的兴趣值;对所述兴趣值进行衰减,以得到所述目标产品信息的绘图数据。
- 根据权利要求4所述的地图展示方法,其中,所述计算每个所述标签词与所述目标产品信息的兴趣值的公式为:score j+1=α×score j+C×weight;其中,若所述标签词在所述目标产品信息中出现,则C=1,反之,则C=0;weight表示 标签词的权重值,score j+1与score j表示标签词的兴趣值;j为整数。
- 根据权利要求4所述的地图展示方法,其中,所述对所述兴趣值进行衰减包括:对所述兴趣值进行次数衰减和时间衰减;所述次数衰减的计算公式为:score i+1=α×score i+C×weight(0<α<1),其中,score i+1与score i表示根据次数对兴趣进行衰减的第一兴趣值,α表示衰减因子,weight表示标签词的权重值,i表示次数;所述时间衰减的计算公式为:score day+1=score day×β(0<β<1),其中,score day+1与score day表示根据时间对兴趣进行衰减的第二兴趣值,day表示周期,β表示衰减因子;所述兴趣值包括所述第一兴趣值与所述第二兴趣值。
- 一种地图展示***,其中,包括:第一获取模块,用于获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息;第二获取模块,用于基于所述目的地信息获取目的地的经纬度;第三获取模块,用于根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的经纬度;筛选模块,用于筛选所述半径范围的经纬度范围内的所述目标产品信息和所述人群属性信息;聚类分析模块,用于对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据;绘制模块,用于将所述绘图数据发送给前端,以使所述前端根据所述绘图数据绘制多个数据图形,并展示所述数据图形。
- 根据权利要求7所述的地图展示***,其中,所述聚类分析模块还用于:根据所述人群属性信息,聚类得到所述人群属性信息的兴趣标签体系,所述兴趣标签体系包括多个标签词;计算每个所述标签词与所述目标产品信息的兴趣值;对所述兴趣值进行衰减,以得到所述目标产品信息的绘图数据。
- 一种计算机设备,其中,所述计算机设备包括存储器、处理器,所述存储器上存储有可在所述处理器上运行的地图展示***,所述地图展示***被所述处理器执行时实现一种地图展示方法的步骤,其中,地图展示方法包括:获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息;基于所述目的地信息获取目的地的经纬度;根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的经纬度;筛选所述半径范围的经纬度范围内的所述目标产品信息和所述人群属性信息;对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据;将所述绘图数据发送给前端,以使所述前端根据所述绘图数据绘制多个数据图形,并展示所述数据图形。
- 根据权利要求9所述的计算机设备,其中,所述对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据包括:分析所述人群属性信息中的常驻地址与GPS画像,得到地理位置画像,所述地理位置画像包括多个位置标签;根据曼哈顿距离计算所述位置标签与所述目的地信息的相似度系数;判断所述相似度系数是否大于预设阈值;若所述相似度系数大于预设阈值,则将所述相似度系数大于预设阈值的位置标签,作为所述人群属性信息的绘图数据;反之,将所述相似度系数不大于预设阈值的位置标签删除。
- 根据权利要求9所述的计算机设备,其中,所述对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据包括:获取所述人群属性信息中完整用户信息;对所述完整用户信息进行聚类,得到所述完整用户信息的用户画像标签;将所述人群属性信息中非完整用户信息与所述用户画像标签输入至标签扩散模型,以完善所述非完整用户信息,得到所述人群属性信息对应的绘图数据。
- 根据权利要求9所述的计算机设备,其中,所述对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据包括:根据所述人群属性信息,聚类得到所述人群属性信息的兴趣标签体系,所述兴趣标签体系包括多个标签词;计算每个所述标签词与所述目标产品信息的兴趣值;对所述兴趣值进行衰减,以得到所述目标产品信息的绘图数据。
- 根据权利要求12所述的计算机设备,其中,所述计算每个所述标签词与所述目标产品信息的兴趣值的公式为:score_(j+1)=α×score_j+C×weight;其中,若所述标签词在所述目标产品信息中出现,则C=1,反之,则C=0;weight表示标签词的权重值,score_(j+1)与score_j表示标签词的兴趣值;j为整数。
- 根据权利要求13所述的计算机设备,其中,所述对所述兴趣值进行衰减包括:对所述兴趣值进行次数衰减和时间衰减;所述次数衰减的计算公式为:score_(i+1)=α×score_i+C×weight(0<α<1),其中,score_(i+1)与score_i表示根据次数对兴趣进行衰减的第一兴趣值,α表示衰减因子,weight表示标签词的权重值,i表示次数;所述时间衰减的计算公式为:score_(day+1)=score_day×β(0<β<1),其中,score_(day+1)与score_day表示根据时间对兴趣进行衰减的第二兴趣值,day表示周期,β表示衰减因子;所述兴趣值包括所述第一兴趣值与所述第二兴趣值。
- 一种计算机可读存储介质,其中,所述计算机可读存储介质内存储有计算机程序,所述计算机程序可被至少一个处理器所执行,以使所述至少一个处理器执行如一种地图展示方法的步骤,其中,所述地图展示方法包括:获取地图数据显示指令,所述地图数据显示指令包括显示的目的地信息、半径范围信息、目标产品信息和人群属性信息;基于所述目的地信息获取目的地的经纬度;根据所述目的地的经纬度与所述半径范围信息,得到所述目的地的半径范围的经纬度;筛选所述半径范围的经纬度范围内的所述目标产品信息和所述人群属性信息;对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据;将所述绘图数据发送给前端,以使所述前端根据所述绘图数据绘制多个数据图形,并展示所述数据图形。
- 根据权利要求15所述的计算机可读存储介质,其中,所述对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据包括:分析所述人群属性信息中的常驻地址与GPS画像,得到地理位置画像,所述地理位置画像包括多个位置标签;根据曼哈顿距离计算所述位置标签与所述目的地信息的相似度系数;判断所述相似度系数是否大于预设阈值;若所述相似度系数大于预设阈值,则将所述相似度系数大于预设阈值的位置标签,作为所述人群属性信息的绘图数据;反之,将所述相似度系数不大于预设阈值的位置标签删除。
- 根据权利要求15所述的计算机可读存储介质,其中,所述对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据包括:获取所述人群属性信息中完整用户信息;对所述完整用户信息进行聚类,得到所述完整用户信息的用户画像标签;将所述人群属性信息中非完整用户信息与所述用户画像标签输入至标签扩散模型,以完善所述非完整用户信息,得到所述人群属性信息对应的绘图数据。
- 根据权利要求15所述的计算机可读存储介质,其中,所述对所述目标产品信息和所述人群属性信息进行聚类分析,以得到所述目标产品信息和所述人群属性信息对应的绘图数据包括:根据所述人群属性信息,聚类得到所述人群属性信息的兴趣标签体系,所述兴趣标签体系包括多个标签词;计算每个所述标签词与所述目标产品信息的兴趣值;对所述兴趣值进行衰减,以得到所述目标产品信息的绘图数据。
- 根据权利要求18所述的计算机可读存储介质,其中,所述计算每个所述标签词与所述目标产品信息的兴趣值的公式为:score_(j+1)=α×score_j+C×weight;其中,若所述标签词在所述目标产品信息中出现,则C=1,反之,则C=0;weight表示标签词的权重值,score_(j+1)与score_j表示标签词的兴趣值;j为整数。
- 根据权利要求19所述的计算机可读存储介质,其中,所述对所述兴趣值进行衰减包括:对所述兴趣值进行次数衰减和时间衰减;所述次数衰减的计算公式为:score_(i+1)=α×score_i+C×weight(0<α<1),其中,score_(i+1)与score_i表示根据次数对兴趣进行衰减的第一兴趣值,α表示衰减因子,weight表示标签词的权重值,i表示次数;所述时间衰减的计算公式为:score_(day+1)=score_day×β(0<β<1),其中,score_(day+1)与score_day表示根据时间对兴趣进行衰减的第二兴趣值,day表示周期,β表示衰减因子;所述兴趣值包括所述第一兴趣值与所述第二兴趣值。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010103441.XA CN111339409A (zh) | 2020-02-20 | 2020-02-20 | 地图展示方法与*** |
CN202010103441.X | 2020-02-20 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021164131A1 true WO2021164131A1 (zh) | 2021-08-26 |
Family
ID=71185370
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/087959 WO2021164131A1 (zh) | 2020-02-20 | 2020-04-30 | 地图展示方法、***、计算机设备和存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111339409A (zh) |
WO (1) | WO2021164131A1 (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114238762A (zh) * | 2021-12-16 | 2022-03-25 | 郑州捷安高科股份有限公司 | 一种动态页面内容展示方法、装置、设备及可读存储介质 |
CN116800618A (zh) * | 2023-08-24 | 2023-09-22 | 明阳时创(北京)科技有限公司 | 一种网络ip画像构建方法、***、介质及设备 |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112131475B (zh) * | 2020-09-25 | 2023-10-10 | 重庆邮电大学 | 一种可解释、可交互的用户画像方法及装置 |
CN112861484B (zh) * | 2021-02-20 | 2023-03-14 | 山东旗帜信息有限公司 | 一种通过无头浏览器进行报表编辑的方法、设备及存储介质 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104657416A (zh) * | 2014-12-11 | 2015-05-27 | 百度在线网络技术(北京)有限公司 | 地图显示方法和装置 |
CN105404629A (zh) * | 2014-09-12 | 2016-03-16 | 华为技术有限公司 | 确定地图界面的方法和装置 |
US20170300511A1 (en) * | 2016-04-15 | 2017-10-19 | Google Inc. | Providing geographic locations related to user interests |
CN110442662A (zh) * | 2019-07-08 | 2019-11-12 | 清华大学 | 一种确定用户属性信息的方法以及信息推送方法 |
CN110457420A (zh) * | 2019-08-13 | 2019-11-15 | 腾讯云计算(北京)有限责任公司 | 兴趣点位置识别方法、装置、设备及存储介质 |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170169341A1 (en) * | 2015-12-14 | 2017-06-15 | Le Holdings (Beijing) Co., Ltd. | Method for intelligent recommendation |
CN110309405B (zh) * | 2018-03-08 | 2022-09-30 | 腾讯科技(深圳)有限公司 | 一种项目推荐方法、装置及存储介质 |
CN109829020B (zh) * | 2018-12-20 | 2023-04-07 | 平安科技(深圳)有限公司 | 地点资源数据推送方法、装置、计算机设备和存储介质 |
CN109886719B (zh) * | 2018-12-20 | 2023-06-20 | 平安科技(深圳)有限公司 | 基于网格的数据挖掘处理方法、装置和计算机设备 |
CN110059147A (zh) * | 2019-04-21 | 2019-07-26 | 黎慧斌 | 基于空间大数据进行知识挖掘的地图可视化***及方法 |
-
2020
- 2020-02-20 CN CN202010103441.XA patent/CN111339409A/zh active Pending
- 2020-04-30 WO PCT/CN2020/087959 patent/WO2021164131A1/zh active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105404629A (zh) * | 2014-09-12 | 2016-03-16 | 华为技术有限公司 | 确定地图界面的方法和装置 |
CN104657416A (zh) * | 2014-12-11 | 2015-05-27 | 百度在线网络技术(北京)有限公司 | 地图显示方法和装置 |
US20170300511A1 (en) * | 2016-04-15 | 2017-10-19 | Google Inc. | Providing geographic locations related to user interests |
CN110442662A (zh) * | 2019-07-08 | 2019-11-12 | 清华大学 | 一种确定用户属性信息的方法以及信息推送方法 |
CN110457420A (zh) * | 2019-08-13 | 2019-11-15 | 腾讯云计算(北京)有限责任公司 | 兴趣点位置识别方法、装置、设备及存储介质 |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114238762A (zh) * | 2021-12-16 | 2022-03-25 | 郑州捷安高科股份有限公司 | 一种动态页面内容展示方法、装置、设备及可读存储介质 |
CN114238762B (zh) * | 2021-12-16 | 2024-07-23 | 郑州捷安高科股份有限公司 | 一种动态页面内容展示方法、装置、设备及可读存储介质 |
CN116800618A (zh) * | 2023-08-24 | 2023-09-22 | 明阳时创(北京)科技有限公司 | 一种网络ip画像构建方法、***、介质及设备 |
CN116800618B (zh) * | 2023-08-24 | 2023-10-20 | 明阳时创(北京)科技有限公司 | 一种网络ip画像构建方法、***、介质及设备 |
Also Published As
Publication number | Publication date |
---|---|
CN111339409A (zh) | 2020-06-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108062375B (zh) | 一种用户画像的处理方法、装置、终端和存储介质 | |
WO2021164131A1 (zh) | 地图展示方法、***、计算机设备和存储介质 | |
CN111010882B (zh) | 在基于地图的社交媒体平台上的位置隐私关联 | |
US9805060B2 (en) | System and method for predicting a geographic origin of content and accuracy of geotags related to content obtained from social media and other content providers | |
US20200082481A1 (en) | Selecting photographs for a destination or point of interest | |
US8484224B1 (en) | System and method for ranking geofeeds and content within geofeeds | |
US11861516B2 (en) | Methods and system for associating locations with annotations | |
US9563850B2 (en) | Method and interface for displaying locations associated with annotations | |
CN107315824B (zh) | 用于生成热力图的方法和装置 | |
US11122009B2 (en) | Systems and methods for identifying geographic locations of social media content collected over social networks | |
US9363634B1 (en) | Providing context-relevant information to users | |
US9442905B1 (en) | Detecting neighborhoods from geocoded web documents | |
US20140095303A1 (en) | Apparatus and Method for Personalizing Maps | |
CN110019616B (zh) | 一种poi现势状态获取方法及其设备、存储介质、服务器 | |
US20180039691A1 (en) | Client-Side Caching of Search Keywords for Online Social Networks | |
CN102163214B (zh) | 一种数字地图生成装置及方法 | |
CN107085600B (zh) | Poi推荐方法、装置、设备及计算机可读存储介质 | |
Zhang et al. | How are tourists different?-Reading geo-tagged photos through a deep learning model | |
US20130110985A1 (en) | Systems and Methods for Geographical Location Based Cloud Storage | |
CN105874452B (zh) | 从社交摘要中标记兴趣点 | |
CN107220308B (zh) | Poi的合理性的检测方法及装置、设备及可读介质 | |
CN104516980B (zh) | 搜索结果的输出方法以及服务器*** | |
Zhang et al. | Terrafly geocloud: an online spatial data analysis and visualization system | |
JP2017501501A (ja) | ニュースタイムラインおよび薦められるニュースエディションの生成 | |
CN115408618A (zh) | 一种基于社交关系融合位置动态流行度和地理特征的兴趣点推荐方法 |
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: 20919532 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 09/12/2022) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20919532 Country of ref document: EP Kind code of ref document: A1 |