CN110930187A - Method, device, equipment and medium for mining shop visiting people - Google Patents
Method, device, equipment and medium for mining shop visiting people Download PDFInfo
- Publication number
- CN110930187A CN110930187A CN201911134828.5A CN201911134828A CN110930187A CN 110930187 A CN110930187 A CN 110930187A CN 201911134828 A CN201911134828 A CN 201911134828A CN 110930187 A CN110930187 A CN 110930187A
- Authority
- CN
- China
- Prior art keywords
- information
- visiting
- shop
- gps
- user
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000005065 mining Methods 0.000 title claims abstract description 33
- 238000012549 training Methods 0.000 claims abstract description 16
- 230000015654 memory Effects 0.000 claims description 19
- 238000009434 installation Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 6
- 230000010365 information processing Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 17
- 238000006243 chemical reaction Methods 0.000 abstract description 10
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003578 releasing effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0259—Targeted advertisements based on store location
Abstract
The application discloses a method, a device, equipment and a medium for mining shop visiting people, and relates to a user visiting prediction technology. The specific implementation scheme is as follows: determining the visiting people of the shop within a historical specific time period according to the historical position information of the user and the position information of the shop; acquiring online information and GPS (global positioning system) dotting information of each user in the visiting crowd within preset time before the historical specific time period, and determining the shop visiting convenience corresponding to each GPS dotting information; constructing model characteristics by using online information, GPS (global positioning system) dotting information and corresponding shop visiting convenience of each user in the visiting crowd, and training a visiting prediction model based on the model characteristics; the visiting prediction model is used for predicting the probability of the user visiting the shop so as to mine the shop visiting crowd. According to the embodiment of the application, possible visiting crowds when the shop launches activities can be more accurately mined, so that the conversion rate and the launching effect of advertisement launching are improved.
Description
Technical Field
The application relates to the technical field of internet, in particular to a user visiting prediction technology, and specifically relates to a method, a device, equipment and a medium for mining shop visiting people.
Background
With the development of technology, traditional advertisers no longer meet the preferential activities of advertisement delivery in a rough manner, and the like, and hope to deliver the advertisement to the people with demands more accurately, so that the ROI of advertisement delivery is improved. Some advanced advertisers can actually monitor the visiting crowd brought by the advertisements, so as to judge the advertisement putting effect.
At present, when a traditional advertiser carries out advertisement putting activities, a certain area is often selected to carry out advertisement putting offline, and some crowd attributes can be correspondingly increased on the line to carry out relatively more accurate advertisement putting. However, these methods are still relatively extensive, and the accuracy of determining the possible visiting population is not high, thereby affecting the conversion rate and the delivery effect of advertisement delivery.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment and a medium for mining shop visitors so as to improve the conversion rate and the releasing effect of releasing advertisements in shops.
In a first aspect, an embodiment of the present application provides a method for mining a store visit crowd, including:
determining the visiting people of the shop within a historical specific time period according to the historical position information of the user and the position information of the shop;
acquiring online information and GPS (global positioning system) dotting information of each user in the visiting crowd within preset time before the historical specific time period, and determining the shop visiting convenience corresponding to each GPS dotting information;
constructing model characteristics by using online information, GPS (global positioning system) dotting information and corresponding shop visiting convenience of each user in the visiting crowd, and training a visiting prediction model based on the model characteristics;
the visiting prediction model is used for predicting the probability of the user visiting the shop so as to mine the shop visiting crowd.
One embodiment in the above application has the following advantages or benefits: on the basis of online information, GPS dotting information is combined, the store visiting convenience degree corresponding to each piece of GPS dotting information is determined, model characteristics are built according to the online information, the GPS dotting information and the corresponding store visiting convenience degrees, a visiting prediction model is trained, the probability prediction of the model for visiting users is more accurate, possible visiting people in the store pushing activities are excavated by the model, and therefore advertisers are helped to achieve more accurate advertisement putting, and the conversion rate and the putting effect of the advertisement putting are improved.
Optionally, the online information at least includes: search information of a user, portrait information, and APP installation information of a user terminal.
Optionally, the determining the shop visit convenience corresponding to each piece of GPS dotting information includes:
according to the road network information and the position information of the shops, the arrival time from different positions on the road network around the shops to the shops is calculated, and the equal-time circle information of the shops is described according to the arrival time of the different positions, wherein the arrival time from the positions on the different equal-time circles to the shops is different;
and determining the shop visit convenience corresponding to each piece of GPS dotting information according to the equal time circle to which each piece of GPS dotting information belongs.
One embodiment in the above application has the following advantages or benefits: whether the user visits is related to the convenience degree of the store, therefore, the road network information is used for depicting the equal-time circle of the store, the equal-time circle, namely the store arriving time, is used for measuring the convenience degree of the store visiting, and the model is used for learning, so that the trained model is used for accurately mining the store visiting people.
Optionally, the determining the store visit convenience corresponding to each GPS dotting information according to the equal time circle to which each GPS dotting information belongs includes:
and determining the shop visit convenience corresponding to each GPS dotting information according to the equal time circle to which each GPS dotting information belongs, and the holiday and weather information corresponding to each GPS dotting information.
One embodiment in the above application has the following advantages or benefits: besides the time of arrival at the store affects whether the user visits, the information of holidays and weather also affects, and therefore the information of holidays and weather can also be used as a basis for determining the convenience of visit to the store, and the accuracy of model prediction is further improved.
Optionally, the constructing model features by using the online information of each user in the visiting crowd, the GPS dotting information and the corresponding shop visiting convenience includes:
constructing the time sequence characteristics of each GPS dotting information by using the time dimension information of each GPS dotting information;
and constructing model characteristics by using the online information of each user in the visiting crowd, the GPS dotting information, the corresponding time sequence characteristics and the shop visiting convenience.
One embodiment in the above application has the following advantages or benefits: and constructing time sequence characteristics according to the time dimension information of each GPS dotting information to distinguish the GPS dotting information in time, and further refining the construction of the characteristics to realize accurate learning and prediction.
In a second aspect, an embodiment of the present application further provides a store visiting crowd digging device, including:
the visiting crowd determining module is used for determining the visiting crowd of the shop within a historical specific time period according to the historical position information of the user and the position information of the shop;
the information processing module is used for acquiring online information and GPS (global positioning system) dotting information of each user in the visiting crowd within preset time before the historical specific time period and determining the shop visiting convenience corresponding to each piece of GPS dotting information;
the characteristic construction and model training module is used for constructing model characteristics by utilizing online information, GPS (global positioning system) dotting information and corresponding shop visiting convenience of each user in the visiting crowd and training a visiting prediction model based on the model characteristics;
the visiting prediction model is used for predicting the probability of the user visiting the shop so as to mine the shop visiting crowd.
In a third aspect, an embodiment of the present application further provides an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the store visited population mining method of any embodiment of the present application.
In a fourth aspect, the present application further provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the store visit crowd mining method according to any embodiment of the present application.
One embodiment in the above application has the following advantages or benefits: on the basis of online information such as search information, portrait information and APP installation information of a user terminal of a user, GPS (global positioning system) dotting information, road network information, shop positions, holidays, weather and the like are combined, convenience degree of the user to the shop is measured by using the offline information, and model features are refined, so that a more accurate visiting prediction model is trained, possible visiting people in the shop pushing-out activities are mined by using the model, an advertiser is helped to realize more accurate advertisement putting, and conversion rate and putting effect of the advertisement putting are improved.
Other effects of the above-described alternative will be described below with reference to specific embodiments.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is a schematic flow diagram of a store visit crowd mining method according to a first embodiment of the present application;
FIG. 2 is a schematic flow diagram of a store visited population mining method according to a second embodiment of the present application;
FIG. 3 is a schematic structural view of a store visited population excavating device according to a third embodiment of the present application;
fig. 4 is a block diagram of an electronic device for implementing the store visited population mining method according to the embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic flow chart of a mining method for store visiting people according to a first embodiment of the present application, which is applicable to mining possible visiting people when a store launches a campaign to improve conversion rate of advertisement delivery. The method can be executed by a shop visiting people digging device which is realized by software and/or hardware, and is preferably configured in electronic equipment, such as a server or computer equipment. As shown in fig. 1, the method specifically includes the following steps:
s101, according to the historical position information of the user and the position information of the shop, the visiting people of the shop in a historical specific time period are determined.
In order to mine the shop visit crowd, a visit prediction model capable of predicting whether a user visits needs to be trained, and sample data needs to be acquired in the model training. In the embodiment of the application, the visiting crowd who visits the shop once is used as a sample, and model features are constructed from the relevant data of the visiting crowd for training.
The specific time period of the history may be any time period, or any time period with any length, and may be configured according to the number of sample data and actual needs. As to which belong to the visiting users, it can be determined from the historical location information of the users and the location information of the stores. For example, if the users whose historical location information matches the location information of the store in the historical specific time period belong to visiting users, all the visiting users constitute the visiting crowd.
S102, obtaining online information and GPS dotting information of each user in the visiting crowd in preset time before the historical specific time period, and determining the shop visiting convenience corresponding to each GPS dotting information.
After determining the visiting population, it is also necessary to determine which information of the visiting population is utilized to construct model features. As is well known, in the prior art, a certain area is usually defined on the line according to the position of the store, and advertisement placement is performed on people in the area. However, the determination of advertisement placement crowd based on location around a store is very comprehensive, and even the comprehensive crowd attribute information can only improve the accuracy within a small range, and the current mining requirement for the store visiting crowd cannot be met. In the embodiment of the application, various factors of online and offline information are combined, so that the efficiency and the accuracy of mining of visiting people can be improved to a great extent.
Specifically, the online information at least includes: search information of a user, portrait information, and APP installation information of a user terminal. The search information of the user refers to query information searched by the user on the internet, the portrait information is information obtained according to big data statistics and used for describing different user characteristics, and the APP installation information of the user terminal refers to which APPs are installed on the terminal by the user. The query information, the portrait information and the APP installation information are relevant information for prediction of the shop visited by the user, so that the content interested by the user, the characteristics and the attributes of the user and the like can be obtained and used as the basis for prediction of the visited shop.
In addition, the GPS dotting information, which is one of offline information, also contributes to the visit prediction of the user. The GPS dotting information refers to real-time location information of the user, which is obtained through the internet, that is, location information such as where the user has passed, or where the user has passed, and may be, for example, latitude and longitude information. However, when predicting whether the user visits, the convenience degree of the user visiting may also be taken into consideration, for example, if the visiting convenience degree is low, the probability of the user visiting is lower, and vice versa. Therefore, in the embodiment of the application, in addition to online information, offline GPS dotting information is combined, and the store visit convenience corresponding to each piece of GPS dotting information is determined to serve as a data base for constructing model features.
In one embodiment, the determining the convenience of store visit corresponding to each piece of GPS dotting information includes:
according to the road network information and the position information of the shops, the arrival time from different positions on the road network around the shops to the shops is calculated, and the equal-time circle information of the shops is described according to the arrival time of the different positions, wherein the arrival time from the positions on the different equal-time circles to the shops is different;
and determining the shop visit convenience corresponding to each piece of GPS dotting information according to the equal time circle to which each piece of GPS dotting information belongs.
The method comprises the steps of obtaining passing roads around shops according to road network information, radiating the passing roads to all the passing roads by taking the shops as centers, determining random position points on each passing road and arrival time from the position points to the shops, and drawing equal-time circles according to the arrival time, wherein the arrival time from the position points on the same equal-time circles to the shops is the same or similar, and the arrival time from the position points on different equal-time circles to the shops is different or has a long difference. The GPS dotting information is positioned on different equal time circles, and the arrival time to the shop is different, so the corresponding shop visit convenience degrees are different, and the shop visit convenience degree corresponding to each piece of GPS dotting information can be determined according to the equal time circles.
S103, establishing model characteristics by using online information, GPS (global positioning system) dotting information and corresponding shop visiting convenience of each user in the visiting crowd, and training a visiting prediction model based on the model characteristics, wherein the visiting prediction model is used for predicting the probability of the user visiting the shop so as to mine the shop visiting crowd.
By combining online and offline information to construct model features, the problem of low accuracy of single features in the prior art is avoided, and the accuracy of the trained visiting prediction model is higher.
According to the technical scheme, on the basis of online information, offline GPS dotting information is combined, the shop visit convenience corresponding to each piece of GPS dotting information is determined, model features are established according to the online information, the GPS dotting information and the corresponding shop visit convenience, a visit prediction model is trained, the probability prediction of the visit of a user by the model is more accurate, possible visit people in the shop push-out activities are mined by the model, and therefore advertisers are helped to achieve more accurate advertisement putting, and the conversion rate and the putting effect of the advertisement putting are improved.
Fig. 2 is a schematic flow chart of a mining method for store visited people according to a second embodiment of the present application, which is further optimized based on the above embodiments. As shown in fig. 2, the method specifically includes the following steps:
s201, according to the historical position information of the user and the position information of the shop, the visiting people of the shop in a historical specific time period are determined.
S202, acquiring online information and GPS dotting information of each user in the visiting crowd within preset time before the historical specific time period.
Wherein the online information at least comprises: search information of a user, portrait information, and APP installation information of a user terminal.
In the model training, the portrait information and the APP installation information of the user terminal may be embedded first and then trained as an input of the model. The search information of the user can be screened firstly, namely the similarity between the original search information and the shop advertisement or the activity content is obtained through a specific interface, the original search information with the similarity reaching a certain threshold is divided by combining the time dimension information to obtain the search information with time sequence characteristics, namely the search information in different time periods, the model is used for distinguishing the search information according to the time sequence characteristics and learning according to different weights, so that the further refinement of the model characteristics is realized, and the accuracy of model prediction is improved.
S203, according to the road network information and the position information of the shops, the arrival time from different positions on the road network around the shops to the shops is calculated, and the equal-time circle information of the shops is drawn according to the arrival time of the different positions, wherein the arrival time from the positions on the different equal-time circles to the shops is different.
S204, determining the shop visit convenience corresponding to each GPS dotting information according to the equal time circle to which each GPS dotting information belongs and the holiday and weather information corresponding to each GPS dotting information.
On the basis of the above embodiment, in the process of determining the convenience of store visit, the embodiment combines holiday and weather information in addition to the isochronal information. Specifically, whether the user is in a holiday period or not and the current weather conditions have an influence on the convenience level of the user from a store. For example, if during holidays, people not only have time but are more willing to come to a store or store to purchase the desired merchandise, and thus, the convenience of going to the store during holidays is higher; when the user encounters severe weather such as wind or rain, the convenience degree is naturally lower when the user arrives at a store, and the convenience degree is higher when the user arrives at the store. Therefore, the convenience degree of the store to the store is determined by combining the holiday and weather information in addition to the isochronal information, the model features are constructed for learning, the model can comprehensively predict the probability of the user to the store according to the real-time GPS dotting information of the user, the current holiday and weather information and other on-line information, and therefore accurate mining of the visiting user is achieved.
S205, constructing the time sequence characteristics of each GPS dotting information by using the time dimension information of each GPS dotting information.
The time dimension information may refer to the time when each piece of GPS dotting information is acquired, or the time when the GPS dotting information occurs. The time dimension information of each GPS dotting information is different, and the influence of the GPS dotting information at different times on the user visit prediction is different. For example, if a user has GPS dotting information around a store one month ago, or has high convenience of arriving at the store, but the probability that the user arrives at the store after the month is not represented is still high, which only indicates that the probability that the user arrives at the store one month ago is high.
Therefore, the time sequence characteristics of each piece of GPS dotting information need to be constructed according to the time dimension information, that is, from the dimension of time, different pieces of GPS dotting information are divided according to the distance of time, and are expressed and distinguished by the way of time sequence characteristics. Moreover, the weights of the GPS dotting information with different time sequence characteristics can be different, and the weight of the dotting information with the time occurring in the near future can be higher, otherwise, the weight is lower, so that the model has the capability of distinguishing the GPS dotting information with different occurrence times, and learns the characteristics and the rules in the GPS dotting information so as to predict more accurately.
S206, establishing model characteristics by using online information, GPS dotting information and corresponding time sequence characteristics of each user in the visiting crowd and the shop visiting convenience, and training a visiting prediction model based on the model characteristics.
The model may be, for example, a DCN (Deep & Cross Network) model.
According to the technical scheme, on the basis of online information such as search information, portrait information and APP installation information of a user terminal of a user, GPS dotting information, road network information, shop positions, off-line information such as holidays and weather are combined, convenience degree from the user to the shop is measured by using the off-line information, model features are refined, a more accurate visiting prediction model is trained, possible visiting people when the shop pushes out activities are excavated by using the model, an advertiser is helped to achieve more accurate advertisement putting, and conversion rate and putting effect of the advertisement putting are improved.
Fig. 3 is a schematic structural diagram of a device for excavating a visiting crowd according to a third embodiment of the present application, which is applicable to a situation where a possible visiting crowd is excavated to improve conversion rate of advertisement delivery when a store launches a campaign. The device can realize the store visiting crowd mining method in any embodiment of the application. As shown in fig. 3, the apparatus 300 specifically includes:
the visited people determining module 301 is used for determining visited people of the shop within a historical specific time period according to historical position information of the user and position information of the shop;
the information processing module 302 is configured to acquire online information and GPS dotting information of each user in the visited people within a preset time before the historical specific time period, and determine a store visiting convenience corresponding to each GPS dotting information;
a feature construction and model training module 303, configured to construct model features using online information of each user in the visited population, GPS dotting information, and store visiting convenience corresponding thereto, and train a visiting prediction model based on the model features;
the visiting prediction model is used for predicting the probability of the user visiting the shop so as to mine the shop visiting crowd.
Optionally, the online information at least includes: search information of a user, portrait information, and APP installation information of a user terminal.
Optionally, the information processing module 302 includes:
the information acquisition unit is used for acquiring online information and GPS (global positioning system) dotting information of each user in the visiting crowd within preset time before the historical specific time period;
the system comprises an equal-time circle depicting unit, a storage unit and a processing unit, wherein the equal-time circle depicting unit is used for calculating the arrival time from different positions on a road network around a store to the store according to road network information and position information of the store, and depicting the equal-time circle information of the arrival store according to the arrival time of the different positions, wherein the arrival time from the positions on different equal-time circles to the store is different;
and the shop visiting convenience determining unit is used for determining the shop visiting convenience corresponding to each piece of GPS dotting information according to the equal time circle to which each piece of GPS dotting information belongs.
Optionally, the shop visit convenience determination unit is specifically configured to:
and determining the shop visit convenience corresponding to each GPS dotting information according to the equal time circle to which each GPS dotting information belongs, and the holiday and weather information corresponding to each GPS dotting information.
Optionally, the feature building and model training module 303 is specifically configured to:
time sequence characteristics of each GPS dotting information are constructed by utilizing the time dimension information of each GPS dotting information;
and constructing model characteristics by using the online information of each user in the visiting crowd, the GPS dotting information, the corresponding time sequence characteristics and the shop visiting convenience.
The store visited people mining device 300 provided by the embodiment of the application can execute the store visited people mining method provided by any embodiment of the application, and has corresponding functional modules and beneficial effects of the execution method. Reference may be made to the description of any method embodiment of the present application for details not explicitly described in this embodiment.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
As shown in fig. 4, the present invention is a block diagram of an electronic device of a shop visiting crowd mining method according to an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 4, the electronic apparatus includes: one or more processors 401, memory 402, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 4, one processor 401 is taken as an example.
The memory 402, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the store visited population mining method in the embodiments of the present application (e.g., the visited population determining module 301, the information processing module 302, and the feature building and model training module 303 shown in fig. 3). The processor 401 executes various functional applications of the server and data processing by running non-transitory software programs, instructions and modules stored in the memory 402, so as to implement the store visited population mining method in the above-described method embodiment.
The memory 402 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of an electronic device that implements the store visited population mining method of the embodiment of the present application, and the like. Further, the memory 402 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 402 may optionally include memory located remotely from the processor 401, which may be connected via a network to an electronic device implementing the store-visited crowd mining method of embodiments of the present application. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device for implementing the method for mining the store visiting people in the embodiment of the application can further comprise: an input device 403 and an output device 404. The processor 401, the memory 402, the input device 403 and the output device 404 may be connected by a bus or other means, and fig. 4 illustrates an example of a connection by a bus.
The input device 403 may receive input numeric or character information and generate key signal inputs related to user settings and function control of an electronic device implementing the store visited population mining method of the embodiments of the present application, such as an input device of a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, or the like. The output devices 404 may include a display device, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
According to the technical scheme of the embodiment of the application, on the basis of online information such as search information, portrait information and APP installation information of a user terminal of a user, GPS (global positioning system) dotting information, road network information, shop positions, off-line information such as holidays and weather are combined, convenience of the user to a shop is measured by using the off-line information, model features are refined, a more accurate visiting prediction model is trained, possible visiting people when the shop pushes out activities are mined by using the model, an advertiser is helped to achieve more accurate advertisement putting, and conversion rate and putting effect of the advertisement putting are improved.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (12)
1. A method for mining store visit people, which is characterized by comprising the following steps:
determining the visiting people of the shop within a historical specific time period according to the historical position information of the user and the position information of the shop;
acquiring online information and GPS (global positioning system) dotting information of each user in the visiting crowd within preset time before the historical specific time period, and determining the shop visiting convenience corresponding to each GPS dotting information;
constructing model characteristics by using online information, GPS (global positioning system) dotting information and corresponding shop visiting convenience of each user in the visiting crowd, and training a visiting prediction model based on the model characteristics;
the visiting prediction model is used for predicting the probability of the user visiting the shop so as to mine the shop visiting crowd.
2. The method of claim 1, wherein the online information comprises at least: search information of a user, portrait information, and APP installation information of a user terminal.
3. The method of claim 1, wherein the determining the store visit convenience corresponding to each piece of GPS dotting information comprises:
according to the road network information and the position information of the shops, the arrival time from different positions on the road network around the shops to the shops is calculated, and the equal-time circle information of the shops is described according to the arrival time of the different positions, wherein the arrival time from the positions on the different equal-time circles to the shops is different;
and determining the shop visit convenience corresponding to each piece of GPS dotting information according to the equal time circle to which each piece of GPS dotting information belongs.
4. The method according to claim 3, wherein the determining the store visit convenience corresponding to each piece of GPS dotting information according to the isochronous cycle to which each piece of GPS dotting information belongs comprises:
and determining the shop visit convenience corresponding to each GPS dotting information according to the equal time circle to which each GPS dotting information belongs, and the holiday and weather information corresponding to each GPS dotting information.
5. The method of any of claims 1-4, wherein the constructing model features using online information, GPS dotting information, and their corresponding store visit conveniences for each user in the visiting population comprises:
constructing the time sequence characteristics of each GPS dotting information by using the time dimension information of each GPS dotting information;
and constructing model characteristics by using the online information of each user in the visiting crowd, the GPS dotting information, the corresponding time sequence characteristics and the shop visiting convenience.
6. A store visit crowd digging implement, comprising:
the visiting crowd determining module is used for determining the visiting crowd of the shop within a historical specific time period according to the historical position information of the user and the position information of the shop;
the information processing module is used for acquiring online information and GPS (global positioning system) dotting information of each user in the visiting crowd within preset time before the historical specific time period and determining the shop visiting convenience corresponding to each piece of GPS dotting information;
the characteristic construction and model training module is used for constructing model characteristics by utilizing online information, GPS (global positioning system) dotting information and corresponding shop visiting convenience of each user in the visiting crowd and training a visiting prediction model based on the model characteristics;
the visiting prediction model is used for predicting the probability of the user visiting the shop so as to mine the shop visiting crowd.
7. The apparatus of claim 6, wherein the online information comprises at least: search information of a user, portrait information, and APP installation information of a user terminal.
8. The apparatus of claim 6, wherein the information processing module comprises:
the information acquisition unit is used for acquiring online information and GPS (global positioning system) dotting information of each user in the visiting crowd within preset time before the historical specific time period;
the system comprises an equal-time circle depicting unit, a storage unit and a processing unit, wherein the equal-time circle depicting unit is used for calculating the arrival time from different positions on a road network around a store to the store according to road network information and position information of the store, and depicting the equal-time circle information of the arrival store according to the arrival time of the different positions, wherein the arrival time from the positions on different equal-time circles to the store is different;
and the shop visiting convenience determining unit is used for determining the shop visiting convenience corresponding to each piece of GPS dotting information according to the equal time circle to which each piece of GPS dotting information belongs.
9. The apparatus according to claim 8, wherein the store visit convenience determination unit is specifically configured to:
and determining the shop visit convenience corresponding to each GPS dotting information according to the equal time circle to which each GPS dotting information belongs, and the holiday and weather information corresponding to each GPS dotting information.
10. The apparatus according to any one of claims 6-9, wherein the feature construction and model training module is specifically configured to:
time sequence characteristics of each GPS dotting information are constructed by utilizing the time dimension information of each GPS dotting information;
and constructing model characteristics by using the online information of each user in the visiting crowd, the GPS dotting information, the corresponding time sequence characteristics and the shop visiting convenience.
11. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the store visited population mining method of any one of claims 1-5.
12. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the store visited population mining method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911134828.5A CN110930187A (en) | 2019-11-19 | 2019-11-19 | Method, device, equipment and medium for mining shop visiting people |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911134828.5A CN110930187A (en) | 2019-11-19 | 2019-11-19 | Method, device, equipment and medium for mining shop visiting people |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110930187A true CN110930187A (en) | 2020-03-27 |
Family
ID=69850286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911134828.5A Pending CN110930187A (en) | 2019-11-19 | 2019-11-19 | Method, device, equipment and medium for mining shop visiting people |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110930187A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111353828A (en) * | 2020-03-30 | 2020-06-30 | 中国工商银行股份有限公司 | Method and device for predicting number of people arriving at store from network |
| CN112561569A (en) * | 2020-12-07 | 2021-03-26 | 上海明略人工智能(集团)有限公司 | Dual-model-based arrival prediction method and system, electronic device and storage medium |
| CN113869963A (en) * | 2021-11-01 | 2021-12-31 | 北京深演智能科技股份有限公司 | Method and device for intelligently predicting user presence situation and data processing equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106767835A (en) * | 2017-02-08 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Localization method and device |
| CN108460622A (en) * | 2018-01-30 | 2018-08-28 | 深圳冠思大数据服务有限公司 | Interactive advertising system under a kind of line |
| KR20190102501A (en) * | 2018-02-26 | 2019-09-04 | 주식회사 지니웍스 | Apparatus and method for recommending online event advertisement |
-
2019
- 2019-11-19 CN CN201911134828.5A patent/CN110930187A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106767835A (en) * | 2017-02-08 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Localization method and device |
| CN108460622A (en) * | 2018-01-30 | 2018-08-28 | 深圳冠思大数据服务有限公司 | Interactive advertising system under a kind of line |
| KR20190102501A (en) * | 2018-02-26 | 2019-09-04 | 주식회사 지니웍스 | Apparatus and method for recommending online event advertisement |
Non-Patent Citations (1)
| Title |
|---|
| 位和: "如何批量制作交通等时圈", 《HTTPS://ZHUANLAN.ZHIHU.COM/P/36708679》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111353828A (en) * | 2020-03-30 | 2020-06-30 | 中国工商银行股份有限公司 | Method and device for predicting number of people arriving at store from network |
| CN111353828B (en) * | 2020-03-30 | 2023-09-12 | 中国工商银行股份有限公司 | Method and device for predicting number of people coming to store at website |
| CN112561569A (en) * | 2020-12-07 | 2021-03-26 | 上海明略人工智能(集团)有限公司 | Dual-model-based arrival prediction method and system, electronic device and storage medium |
| CN112561569B (en) * | 2020-12-07 | 2024-02-27 | 上海明略人工智能(集团)有限公司 | Dual-model-based store arrival prediction method, system, electronic equipment and storage medium |
| CN113869963A (en) * | 2021-11-01 | 2021-12-31 | 北京深演智能科技股份有限公司 | Method and device for intelligently predicting user presence situation and data processing equipment |
| CN113869963B (en) * | 2021-11-01 | 2023-11-07 | 北京深演智能科技股份有限公司 | Method and device for intelligently predicting user presence condition and data processing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111538904B (en) | Method and device for recommending interest points | |
| JP7159405B2 (en) | MAP INFORMATION DISPLAY METHOD, APPARATUS, ELECTRONIC DEVICE AND STORAGE MEDIUM | |
| CN110930187A (en) | Method, device, equipment and medium for mining shop visiting people | |
| CN111708858A (en) | Map data processing method, device, equipment and storage medium | |
| CN110705800B (en) | Mixed travel route determination method, device, equipment and storage medium | |
| CN112036668A (en) | Water consumption prediction method, device, electronic equipment and computer readable medium | |
| CN107222526B (en) | Method, device and equipment for pushing promotion information and computer storage medium | |
| CN110851738A (en) | Method, device and equipment for acquiring POI state information and computer storage medium | |
| CN110660219A (en) | Parking lot parking prediction method and device | |
| CN112163676A (en) | Multitask service prediction model training method, device, equipment and storage medium | |
| CN112129315B (en) | Method and device for recommending parking lot, electronic equipment and storage medium | |
| CN111506803A (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN111667095A (en) | Method for predicting economic state and establishing economic state prediction model and corresponding device | |
| CN113360792A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN111915608A (en) | Building extraction method, device, equipment and storage medium | |
| CN110514211B (en) | Positioning method, apparatus, device and medium | |
| CN111523007A (en) | User interest information determination method, device, equipment and storage medium | |
| CN113139118A (en) | Parking lot recommendation method and device, electronic equipment and medium | |
| CN111694914B (en) | Method and device for determining resident area of user | |
| CN110751853B (en) | Parking space data validity identification method and device | |
| CN111625710B (en) | Processing method and device of recommended content, electronic equipment and readable storage medium | |
| CN112381305A (en) | Taxi taking time estimation method and device, electronic equipment and storage medium | |
| CN112382090A (en) | Method, apparatus, device and storage medium for outputting information | |
| CN111625724A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN112507249A (en) | Method and device for generating interest points, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200327 |
|
| RJ01 | Rejection of invention patent application after publication |