CN112199455B - Geographic information point ordering method and device, electronic equipment and computer medium - Google Patents
Geographic information point ordering method and device, electronic equipment and computer medium Download PDFInfo
- Publication number
- CN112199455B CN112199455B CN202010964023.XA CN202010964023A CN112199455B CN 112199455 B CN112199455 B CN 112199455B CN 202010964023 A CN202010964023 A CN 202010964023A CN 112199455 B CN112199455 B CN 112199455B
- Authority
- CN
- China
- Prior art keywords
- geographic information
- information point
- user
- point
- geographic
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 235000019633 pungent taste Nutrition 0.000 claims abstract description 94
- 238000001514 detection method Methods 0.000 claims abstract description 25
- 238000012163 sequencing technique Methods 0.000 claims abstract description 18
- 230000006399 behavior Effects 0.000 claims description 107
- 239000013598 vector Substances 0.000 claims description 43
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000007477 logistic regression Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Remote Sensing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application discloses a geographic information point ordering method, a geographic information point ordering device, electronic equipment and a computer medium. An embodiment of the method comprises: acquiring user behavior information and attribute information of each geographic information point to be sequenced; extracting first characteristic information from user behavior information of each geographic information point, and extracting second characteristic information from attribute information of each geographic information point; respectively inputting the first characteristic information and the second characteristic information of each geographic information point into a pre-trained hotness detection model to obtain hotness scores of the geographic information points; and sequencing the geographic information points according to the hotness score to obtain a sequencing result. According to the method and the device, accuracy of the sorting result is improved, so that geographic information points recommended to the user are more effective and meet user requirements.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a method and a device for ordering geographic information points, electronic equipment and a computer medium.
Background
The map data contains a large number of geographic information points (Point of Information, POIs), which may also be referred to as points of interest. In many cases, it is necessary to sort the geographic information points in the map data, so that some geographic information points are recommended to the user according to the sorting result, so as to facilitate the travel of the user.
In the prior art, the total geographic information points are generally ordered according to the accuracy rate (such as the accuracy rate of coordinates and the accuracy rate of addresses) of the geographic information points, and partial geographic information points with the front ordering result are provided for users. Because the data used in the sorting process is single, the sorting result cannot accurately show the heat of the geographic information points, so that the geographic information points recommended to the user cannot easily meet the demands of the user.
Disclosure of Invention
The embodiment of the application provides a geographic information point ordering method, a geographic information point ordering device, electronic equipment and a computer medium, which are used for solving the technical problems that in the prior art, the ordering result of geographic information points is not accurate enough, and the geographic information points recommended to a user cannot meet the demands of the user.
In a first aspect, an embodiment of the present application provides a method for ordering geographic information points, where the method includes: acquiring user behavior information and attribute information of each geographic information point to be sequenced; extracting first characteristic information from user behavior information of each geographic information point, and extracting second characteristic information from attribute information of each geographic information point; respectively inputting the first characteristic information and the second characteristic information of each geographic information point into a pre-trained hotness detection model to obtain hotness scores of the geographic information points; and sequencing each geographic information point according to the hotness score to obtain a sequencing result.
In a second aspect, an embodiment of the present application provides a device for sorting geographic information points, where the device includes: the acquisition unit is configured to acquire user behavior information and attribute information of each geographic information point to be sequenced; an extraction unit configured to extract first feature information from user behavior information of each geographical information point and to extract second feature information from attribute information of each geographical information point; the input unit is configured to input the first characteristic information and the second characteristic information of each geographic information point to a pre-trained hotness detection model respectively to obtain hotness scores of the geographic information points; and the ordering unit is configured to order the geographic information points according to the hotness score to obtain an ordering result.
In a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a storage device having one or more programs stored thereon, which when executed by the one or more processors, cause the one or more processors to implement the method as described in the first aspect.
In a fourth aspect, embodiments of the present application provide a computer readable medium having stored thereon a computer program which, when executed by a processor, implements a method as described in the first aspect.
The method, the device, the electronic equipment and the computer medium for ordering the geographic information points are provided by the embodiment of the application, and the user behavior information and the attribute information of each geographic information point to be ordered are obtained; then extracting first characteristic information from user behavior information of each geographic information point, and extracting second characteristic information from attribute information of each geographic information point; inputting the first characteristic information and the second characteristic information of each geographic information point into a pre-trained hotness detection model to obtain hotness scores of the geographic information points; and finally, sequencing each geographic information point according to the hotness score to obtain a sequencing result. Because the user behavior information and the attribute information of each geographic information point are used simultaneously in the sorting process, and the user behavior information can show the attention degree of the geographic information points to a certain extent, the sorting result determined based on the user behavior information and the attribute information can accurately show the heat of the geographic information points, so that the geographic information points recommended to the user are more effective and are easier to match with the user demands.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:
FIG. 1 is a flow chart of one embodiment of a method of ordering geographic information points in accordance with the present application;
FIG. 2 is a flow chart of yet another embodiment of a method of ordering geographic information points in accordance with the present application;
FIG. 3 is a schematic diagram of one embodiment of a ranking apparatus for geographic information points according to the present application;
Fig. 4 is a schematic diagram of a computer system for implementing an electronic device according to an embodiment of the present application.
Detailed Description
The application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be noted that, for convenience of description, only the portions related to the present application are shown in the drawings.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
Referring to FIG. 1, a flow 100 of one embodiment of a method of ordering geographic information points according to the present application is shown. The method for ordering the geographic information points comprises the following steps:
step 101, obtaining user behavior information and attribute information of each geographic information point to be sequenced.
In this embodiment, an execution body (e.g., an electronic device such as a server) of the geographic information point ordering method may obtain user behavior information and attribute information of each geographic information point to be ordered. The geographic information points to be ranked may be the full geographic information points in the map data, or may be partial geographic information points in the map data, such as geographic information points in a local geographic area, geographic information points in which user behaviors (such as a menu, a visit, etc.) are generated, and the like, which are not particularly limited herein.
In this embodiment, for each geographic information point, the user behavior information of that geographic information point may be information characterizing the user behavior generated by the user for that geographic information point. As an example, the user behavior information for each geographic information point may include, but is not limited to, at least one of: the number of times the wireless network (e.g., wifi) of each geographic information point is connected by the user device, the number of times the user sends a request associated with each geographic information point, the number of times the user has been placed in each geographic information point, information indicating whether there is a target user behavior in each geographic information point, and so on.
Wherein the request associated with each geographic information point may include at least one of: ride requests, search requests, take-away reservation requests, etc. The number of times the user makes an order in each geographic information point may include at least one of: the number of take-out orders for each geographic information point and the number of riding orders for each geographic information point. Here, the number of riding orders per geographical information point may refer to the number of riding orders destined for the geographical information point. The target behavior may include, but is not limited to, at least one of: the use behavior of the voucher, the use behavior of the group buying voucher, the behavior of the code scanning buying bill, the renting behavior of the charging bank and the like.
It should be noted that, the user behavior information of each geographic information point may include other information besides the above list, for example, the number of times of contact with the staff of the geographic information point, the number of times of evaluation on the geographic information point, and the like, which is not limited in the embodiment of the present application.
In the present embodiment, for each geographic information point, the attribute information of the geographic information point may include, but is not limited to, at least one of the following: information indicating whether a sub-geographic information point is included (which may be characterized by 1 or 0), information indicating whether an AOI (Area of Interest) contour is included (which may be characterized by 1 or 0), comment information, information indicating whether a telephone number is included (which may be characterized by 1 or 0), and the like. For example, if the geographic information point is a casino, since the casino is generally included as a geographic information point of a store, the casino includes sub-geographic information points. At the same time, casinos typically occupy a large area and thus contain AOI profiles. In practice, geographic information points with a footprint greater than a certain threshold may be considered to be geographic information points that include an AOI profile.
Step 102, extracting first characteristic information from user behavior information of each geographic information point, and extracting second characteristic information from attribute information of each geographic information point.
In this embodiment, the execution body may extract feature information from the user behavior information of each geographical information point and the attribute information of each geographical information point, respectively, and refer to the feature information extracted from the user behavior information as first feature information and the feature information extracted from the attribute information as second feature information.
Wherein the characteristic information may be used to characterize the characteristics of the geographic information points. The first characteristic information and the second characteristic information may each be represented in the form of vectors. The value of each dimension in the vector is a characteristic value. The feature value in the first feature information may be derived based on user behavior information and may be a numerical representation of one or more items of user behavior information. The feature value in the second feature information may be derived based on the attribute information and may be a numerical representation of one or more items of information in the attribute information. In practice, the feature information may be normalized such that the value of each dimension in the vector is within the numerical interval of [0,1] to facilitate subsequent data processing.
In some optional implementations of this embodiment, the executing entity may extract the first feature information from the user behavior information of each geographic information point through the following sub-steps:
Substep S11, determining a one-hot encoding (one-hot) vector for each geographical information point based on information indicating whether or not there is a target user behavior in each geographical information point.
Here, a one-hot vector may be a multidimensional vector, and each target behavior may correspond to a dimension. For example, if there are 12 target behaviors in total, the one-hot encoded vector is a 12-dimensional vector.
For each geographic information point, if a certain target behavior exists in the geographic information point, the value corresponding to the target behavior in the one-hot coding vector of the geographic information point is 1; and vice versa is 0. For example, the one-time heat encoding vector is a 4-dimensional vector, the first dimension indicates whether a coupon use behavior exists, the second dimension indicates whether a group purchase use behavior exists, the third dimension indicates whether a code scanning purchase behavior exists, and the fourth dimension indicates whether a charge bank lease behavior exists. If the user has a group purchase ticket use behavior, a group purchase ticket use behavior and a code scanning ticket purchase behavior at a certain geographic information point and does not have a charging treasured leasing behavior, the unique thermal coding vector of the geographic information point can be [ 111 0].
In the substep S12, the first feature information of each geographic information point is determined based on at least one of the unique heat encoding vector of each geographic information point and the number of times the wireless network of each geographic information point is connected by the user equipment, the number of times the user sends the request related to each geographic information point, and the number of times the user places an order in each geographic information point.
Here, for each geographic information point, at least one of the number of times the wireless network of the geographic information point is connected by the user equipment, the number of times the user sends a request related to the geographic information point, and the number of times the user places a order in the geographic information point may be quantized into a numerical value, and each numerical value may be normalized, thereby obtaining a vector including at least one normalized numerical value. And combining (such as splicing) the vector with a one-hot encoding (one-hot) vector of the geographic information point to obtain first characteristic information of each geographic information point.
At least one of the number of times the wireless network of the geographical information point is connected by the user equipment, the number of times the user sends a request related to the geographical information point, and the number of times the user makes a purchase in the geographical information point is quantized into a numerical value, which may be a value obtained by directly using the respective times or by performing further numerical operations on the respective times, and is not particularly limited herein.
Because the user behavior information can show the attention degree of the geographic information points to a certain extent, the first characteristic information is extracted from the user behavior information, and the geographic information points are ranked based on the first characteristic information, so that the ranking result can accurately show the heat of the geographic information points, and the geographic information points provided for the user are more effective and are easier to match with the user demands. In addition, since the user behavior information includes multiple dimensions (such as the number of times the wireless network of the geographic information point is connected by the user equipment, the number of times the user sends a request related to the geographic information point, the number of times the user places a order in the geographic information point, information indicating whether the geographic information point has user-to-store behavior, etc.), the data utilization rate of the ordering process can be greatly increased, and thus the accuracy of the ordering result can be improved.
And step 103, respectively inputting the first characteristic information and the second characteristic information of each geographic information point into a pre-trained hotness detection model to obtain hotness scores of the geographic information points.
In this embodiment, the execution subject may have a pre-trained heat detection model stored therein. The hotness detection model may be used to predict hotness scores for geographic information points. Wherein the heat may indicate a degree of user interest in predicting the geographic information point. The higher the user's attention to the geographic information point, the higher its hotness score.
In this embodiment, the executing body may input the first feature information and the second feature information of each geographic information point to a pre-trained hotness detection model, so as to obtain a hotness score of the geographic information point. Here, when the first characteristic information and the second characteristic information of each geographical information point are input to the heat detection model trained in advance, the first characteristic information and the second characteristic information of the geographical information point may be first spliced, and the spliced characteristic information may be input to the heat detection model.
The heat detection model can be obtained by training a basic model in advance by adopting a machine learning method (such as a supervised learning method). The base model may use a logistic regression (Logistic Regression, LR) model, a neural network, or the like, among others. In practice, the sample set used to train the heat detection model may include a large number of sample geographic information points, each of which may contain a label indicating whether it is a hotspot geographic information point. For example, if a certain sample geographic information point is a hot geographic information point, its label may be set to 1; otherwise, the label may be set to 0.
In the training process, feature information of the sample geographic information points (including the first feature information and the second feature information of the sample geographic information points) can be input into the basic model one by one, and the feature information extraction mode can be referred to as step 102), so as to obtain a detection result output by the basic model. The detection result is a hotness score predicted value of a sample geographic information point. Then, the loss value can be determined based on the labeling information corresponding to the detection result and the sample geographic information point. The loss value is a non-negative real value function and can be used for representing the difference between the detection result and the real result. In general, the smaller the value of the loss function (loss value), the better the robustness of the model. The above-described loss values may be determined in various existing loss functions (e.g., cross entropy loss functions), and the like. The loss function can be set according to actual requirements. The loss value may then be used to update parameters of the base model. Therefore, once the sample geographic information point is input, the parameters of the basic model can be updated once based on the loss value corresponding to the sample geographic information point until model training is completed.
And step 104, sequencing each geographic information point according to the hotness score to obtain a sequencing result.
In this embodiment, the geographic information points may be specifically ranked according to the order of the hotness score from high to low, to obtain a ranking result.
After the sorting result is obtained, a preset number of geographic information points can be selected according to the sorting order indicated by the sorting result, and the selected geographic information points are pushed to the user so that the pushed geographic information points can be displayed on the electronic map used by the user. Because the geographic information points pushed to the user are geographic information points with higher heat, namely most of the geographic information points which are more interesting to the user, the geographic information points are selected to be recommended to the user, so that the geographic information points provided for the user are more effective and are more easily matched with the user demands, and the effectiveness and the practicability of the pushed information are improved.
According to the method provided by the embodiment of the application, the user behavior information and the attribute information of each geographic information point to be sequenced are obtained; then extracting first characteristic information from user behavior information of each geographic information point, and extracting second characteristic information from attribute information of each geographic information point; inputting the first characteristic information and the second characteristic information of each geographic information point into a pre-trained hotness detection model to obtain hotness scores of the geographic information points; and finally, sequencing each geographic information point according to the hotness score to obtain a sequencing result. Because the user behavior information and the attribute information of each geographic information point are used simultaneously in the sorting process, and the user behavior information can show the attention degree of the geographic information points to a certain extent, the sorting result determined based on the user behavior information and the attribute information can accurately show the heat of the geographic information points, so that the geographic information points provided for the user are more effective and are easier to match with the user demands.
With further reference to fig. 2, a flow 200 of yet another embodiment of a method of ordering geographic information points is shown. The flow 200 of the geographic information point ordering method includes the following steps:
step 201, obtaining user behavior information and attribute information of each geographic information point to be sequenced.
In this embodiment, an execution body (e.g., an electronic device such as a server) of the geographic information point ordering method may obtain user behavior information and attribute information of each geographic information point to be ordered.
In this embodiment, for each geographic information point, the user behavior information of that geographic information point may be information characterizing the user behavior generated by the user for that geographic information point. As an example, the user behavior information for each geographic information point may include, but is not limited to, at least one of: the number of times the wireless network of each geographical information point is connected by the user device, the number of times the user sends a request associated with each geographical information point, the number of times the user has been ordered in each geographical information point, information indicating whether or not there is a target user behavior in each geographical information point, etc.
Wherein the request associated with each geographic information point may include at least one of: ride requests, search requests, take-away reservation requests, etc. The number of times the user makes an order in each geographic information point may include at least one of: the number of take-out orders for each geographic information point and the number of riding orders for each geographic information point. Wherein the number of orders for each geographic information point may refer to the number of orders for a vehicle destined for that geographic information point. The target behavior may include, but is not limited to, at least one of: the use behavior of the voucher, the use behavior of the group buying voucher, the behavior of the code scanning buying bill, the renting behavior of the charging bank and the like.
In the present embodiment, for each geographic information point, the attribute information of the geographic information point may include, but is not limited to, at least one of the following: information indicating whether a sub-geographic information point is included, information indicating whether an AOI profile is included, comment information, information indicating whether a telephone number is included, and the like.
It should be noted that, the user behavior information of each geographic information point may include other information besides the above list, for example, the number of times of contact with the staff of the geographic information point, the number of times of evaluation on the geographic information point, and the like, which is not limited in the embodiment of the present application.
Step 202, determining a single-hot encoding vector for each geographic information point based on information indicating whether or not there is a target user behavior in each geographic information point.
In this embodiment, the execution body may determine the one-hot encoding vector of each geographical information point based on information indicating whether or not there is a target user behavior in each geographical information point. Here, a one-hot vector may be a multidimensional vector, and each target behavior may correspond to a dimension. For example, if there are 12 target behaviors in total, the one-hot encoded vector is a 12-dimensional vector.
For each geographic information point, if a certain target behavior exists in the geographic information point, the value corresponding to the target behavior in the one-hot coding vector of the geographic information point is 1; and vice versa is 0. For example, the one-time heat encoding vector is a 4-dimensional vector, the first dimension indicates whether a coupon use behavior exists, the second dimension indicates whether a group purchase use behavior exists, the third dimension indicates whether a code scanning purchase behavior exists, and the fourth dimension indicates whether a charge bank lease behavior exists. If the user has a group purchase ticket use behavior, a group purchase ticket use behavior and a code scanning ticket purchase behavior at a certain geographic information point and does not have a charging treasured leasing behavior, the unique thermal coding vector of the geographic information point can be [ 111 0].
Step 203, determining first feature information of each geographic information point based on at least one item of the number of times the wireless network of each geographic information point is connected by the user equipment, the number of times the user sends a request related to each geographic information point, the number of times the user orders in each geographic information point and the unique heat coding vector of each geographic information point.
In this embodiment, for each geographic information point, the executing body may quantize at least one of the number of times the wireless network of the geographic information point is connected by the user equipment, the number of times the user sends the request related to the geographic information point, and the number of times the user places a order in the geographic information point into a numerical value, and normalize each numerical value, thereby obtaining a vector including at least one normalized numerical value. And combining (such as splicing) the vector with a one-hot encoding (one-hot) vector of the geographic information point to obtain first characteristic information of each geographic information point.
In some optional implementations of this embodiment, the foregoing execution body may execute according to the following substeps:
in a substep S21, a network connection hotness score of each geographic information point is determined based on the number of times the wireless network of each geographic information point is connected by the user equipment.
For example, the number of times the wireless network of each geographic information point is connected by the user device may be directly taken as the network connection hotness score for that geographic information point.
For another example, the geographical information points may be first ordered based on the number of times the wireless network of the geographical information points is connected by the user device, resulting in a first order for the geographical information points. And then, determining the network connection hotness score of each geographic information point based on preset first corresponding relation information and a first order of each geographic information point, wherein the first corresponding relation information comprises a corresponding relation between each first order and the network connection hotness score.
For another example, a first sum of the number of times the wireless network of each geographic information point is connected by the user device may be first determined. Then, for each geographic information point, the ratio of the number of times the wireless network of the geographic information point is connected by the user equipment to the first sum is used as the network connection hotness score of the geographic information point.
In a substep S22, a user request hotness score for each geographic information point is determined based on the number of times the user has sent a request associated with each geographic information point.
For example, the number of times a user sends a request associated with each geographic information point may be directly taken as the user request hotness score for that geographic information point.
For another example, the geographic information points may be first ordered based on the number of times the user sent a request associated with each geographic information point, resulting in a second order for each geographic information point. And then, determining a user request hotness score of each geographic information point based on preset second corresponding relation information and a second order of each geographic information point, wherein the second corresponding relation information comprises a corresponding relation between each second order and the user request hotness score.
For another example, a second sum of the number of times the user sent the request associated with each geographic information point may be first determined. Then, for each geographic information point, the ratio of the number of times the user sends the request related to the geographic information point to the second sum is used as the user request hotness score of the geographic information point.
In a substep S23, an order hotness score for each geographic information point is determined based on the number of times the user places an order in each geographic information point.
For example, the number of times a user places a order in each geographic information point may be directly taken as the order hotness score for that geographic information point.
For another example, the geographic information points may be first ordered based on the number of times the user has placed in each geographic information point, resulting in a third order for each geographic information point. And then, determining the order hotness score of each geographic information point based on preset third corresponding relation information and a third order of each geographic information point, wherein the third corresponding relation information comprises a corresponding relation between each third order and the order hotness score.
For another example, a third sum of the number of orders made by the user in each geographic information point may be first determined. Then, for each geographic information point, the ratio of the number of times the user places orders in the geographic information point to the third sum is used as the order hotness score of the geographic information point.
In the substep S24, at least one of the user request popularity score, the user request popularity score and the order popularity score of each geographic information point is combined with the unique heat encoding vector of the geographic information point to obtain the first feature information of the geographic information point.
Here, for each geographic information point, at least one of a user request hotness score, and an order hotness score of the geographic information point may be normalized, thereby obtaining a vector including at least one normalized numerical value. And combining (such as splicing) the vector with a one-hot encoding (one-hot) vector of the geographic information point to obtain first characteristic information of each geographic information point.
Because the user behavior information can show the attention degree of the geographic information points to a certain extent, the first characteristic information is extracted from the user behavior information, and the geographic information points are ranked based on the first characteristic information, so that the ranking result can accurately show the heat of the geographic information points, and the geographic information points provided for the user are more effective and are easier to match with the user demands. In addition, since the user behavior information includes multiple dimensions (such as the number of times the wireless network of the geographic information point is connected by the user equipment, the number of times the user sends a request related to the geographic information point, the number of times the user places a order in the geographic information point, information indicating whether the geographic information point has user-to-store behavior, etc.), the data utilization rate of the ordering process can be greatly increased, and thus the accuracy of the ordering result can be improved.
And 204, respectively inputting the first characteristic information and the second characteristic information of each geographic information point into a pre-trained hotness detection model to obtain hotness scores of the geographic information points.
Step 204 in this embodiment can be referred to step 103 in the above embodiment, and will not be described herein.
And step 205, sequencing each geographic information point according to the hotness score to obtain a sequencing result.
Step 205 in this embodiment can be referred to step 104 in the above embodiment, and will not be described here again.
As can be seen from fig. 2, compared with the embodiment corresponding to fig. 1, the flow 200 of the method for ordering geographic information points in this embodiment involves a step of extracting first feature information based on the number of times the wireless network of each geographic information point is connected by the user device, the number of times the user sends a request related to each geographic information point, the number of times the user places a order in each geographic information point, and information indicating whether or not there is a target user behavior in each geographic information point. Therefore, the scheme described in the embodiment can use multidimensional user behavior information, so that more dimensional characteristic information is introduced, and the data utilization rate of the sorting process can be greatly increased. In addition, the user behavior information of each dimension can represent the attention degree of the geographic information points, so that the ordering result can more accurately show the heat of the geographic information points, and the accuracy of the ordering result is further improved.
With further reference to fig. 3, as an implementation of the method shown in the foregoing drawings, the present application provides an embodiment of a geographic information point sorting device, where an embodiment of the device corresponds to the embodiment of the method shown in fig. 1, and the device may be specifically applied to various electronic devices.
As shown in fig. 3, the sorting apparatus 300 for geographic information points according to the present embodiment includes: an acquiring unit 301 configured to acquire user behavior information and attribute information of each geographical information point to be ranked; an extraction unit 302 configured to extract first feature information from user behavior information of each geographical information point, and extract second feature information from attribute information of each geographical information point; an input unit 303 configured to input the first feature information and the second feature information of each geographic information point to a pre-trained hotness detection model, respectively, to obtain hotness scores of the geographic information points; the ranking unit 304 is configured to rank the geographic information points according to the hotness score, so as to obtain a ranking result.
In some optional implementations of this embodiment, the user behavior information for each geographic information point includes at least one of: the number of times the wireless network of each geographical information point is connected by the user device, the number of times the user sends a request associated with each geographical information point, the number of times the user has been ordered in each geographical information point, information indicating whether or not there is a target user behavior in each geographical information point.
In some optional implementations of this embodiment, the request related to each geographic information point includes at least one of: riding request, searching request and takeout reservation request; the number of orders includes at least one of: number of riding orders, number of take-out orders.
In some optional implementations of this embodiment, the extracting unit 302 is further configured to: determining a single-hot encoding vector of each geographic information point based on the information indicating whether the target user behavior exists in each geographic information point; the first characteristic information of each geographic information point is determined based on at least one of the number of times the wireless network of each geographic information point is connected by the user equipment, the number of times the user sends a request related to each geographic information point, the number of times the user places an order in each geographic information point, and the unique heat encoding vector of each geographic information point.
In some optional implementations of this embodiment, the extracting unit 302 is further configured to: determining a network connection hotness score of each geographic information point based on the number of times the wireless network of each geographic information point is connected by the user equipment; determining a user request heat score for each geographic information point based on the number of times the user sends a request associated with each geographic information point; determining order hotness scores of the geographic information points based on the order number of the users in the geographic information points; and combining at least one of the user request hotness score, the user request hotness score and the order hotness score of each geographic information point with the independent hotness coding vector of the geographic information point to obtain first characteristic information of the geographic information point.
In some optional implementations of this embodiment, the extracting unit 302 is further configured to: ordering the geographic information points based on the connection times of the wireless network of the geographic information points by the user equipment to obtain a first order of the geographic information points; and determining the network connection hotness score of each geographic information point based on preset first corresponding relation information and a first order of each geographic information point, wherein the first corresponding relation information comprises a corresponding relation between each first order and the network connection hotness score.
In some optional implementations of this embodiment, the extracting unit 302 is further configured to: determining a first sum of the times that the wireless network of each geographic information point is connected by the user equipment; for each geographic information point, the ratio of the number of times the wireless network of the geographic information point is connected by the user equipment to the first sum is used as the network connection hotness score of the geographic information point.
In some optional implementations of this embodiment, the extracting unit 302 is further configured to: ordering the geographic information points based on the times of sending the requests related to the geographic information points by the user to obtain a second order of the geographic information points; and determining the user request hotness score of each geographic information point based on preset second corresponding relation information and a second order of each geographic information point, wherein the second corresponding relation information comprises a corresponding relation between each second order and the user request hotness score.
In some optional implementations of this embodiment, the extracting unit 302 is further configured to: determining a second sum of the number of times the user sends the request associated with each geographic information point; for each geographic information point, the ratio of the number of times the user sends the request related to the geographic information point to the second sum is used as the user request hotness score of the geographic information point.
In some optional implementations of this embodiment, the extracting unit 302 is further configured to: ordering the geographic information points based on the order of the users in the geographic information points to obtain a third order of the geographic information points; and determining the order hotness score of each geographic information point based on preset third corresponding relation information and a third order of each geographic information point, wherein the third corresponding relation information comprises a corresponding relation between each third order and the order hotness score.
In some optional implementations of this embodiment, the extracting unit 302 is further configured to: determining a third sum of the number of times of the user ordering in each geographic information point; for each geographic information point, the ratio of the number of times the user places orders in the geographic information point to the third sum is used as the order hotness score of the geographic information point.
In some optional implementations of this embodiment, the heat detection model is obtained by training a logistic regression model using a machine learning method.
The device provided by the embodiment of the application obtains the user behavior information and the attribute information of each geographic information point to be sequenced; then extracting first characteristic information from user behavior information of each geographic information point, and extracting second characteristic information from attribute information of each geographic information point; inputting the first characteristic information and the second characteristic information of each geographic information point into a pre-trained hotness detection model to obtain hotness scores of the geographic information points; and finally, sequencing each geographic information point according to the hotness score to obtain a sequencing result. Because the user behavior information and the attribute information of each geographic information point are used simultaneously in the sorting process, and the user behavior information can show the attention degree of the geographic information points to a certain extent, the sorting result determined based on the user behavior information and the attribute information can accurately show the heat of the geographic information points, so that the geographic information points provided for the user are more effective and are easier to match with the user demands.
Referring now to FIG. 4, there is illustrated a schematic diagram of a computer system 400 suitable for use in implementing an electronic device of an embodiment of the present application. The electronic device shown in fig. 4 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the application.
As shown in fig. 4, the computer system 400 includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In RAM 403, various programs and data required for the operation of system 400 are also stored. The CPU401, ROM 402, and RAM 403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output portion 407 including a Liquid Crystal Display (LCD) or the like, a speaker or the like; a storage section 408 including a hard disk or the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. The drive 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 409 and/or installed from the removable medium 411. The above-described functions defined in the method of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 401. The computer readable medium according to the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present application may be implemented in software or in hardware. The described units may also be provided in a processor, wherein the names of the units do not in some cases constitute a limitation of the unit itself.
As another aspect, the present application also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: acquiring user behavior information and attribute information of each geographic information point to be sequenced; extracting first characteristic information from user behavior information of each geographic information point, and extracting second characteristic information from attribute information of each geographic information point; respectively inputting the first characteristic information and the second characteristic information of each geographic information point into a pre-trained hotness detection model to obtain hotness scores of the geographic information points; and sequencing the geographic information points according to the hotness score to obtain a sequencing result.
The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the application referred to in the present application is not limited to the specific combinations of the technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the inventive concept described above. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.
Claims (13)
1. A method for ordering geographic information points, comprising:
Acquiring user behavior information and attribute information of each geographic information point to be sequenced;
Extracting first characteristic information from user behavior information of each geographic information point, and extracting second characteristic information from attribute information of each geographic information point;
Respectively inputting the first characteristic information and the second characteristic information of each geographic information point into a pre-trained hotness detection model to obtain hotness scores of the geographic information points;
sequencing each geographic information point according to the hotness score to obtain a sequencing result;
Wherein the user behavior information of each geographic information point comprises at least one of the following: the number of times the wireless network of each geographic information point is connected by the user equipment, the number of times the user sends a request related to each geographic information point, the number of times the user orders in each geographic information point, and information indicating whether a target user behavior exists in each geographic information point;
wherein the attribute information of the geographic information point includes, but is not limited to, at least one of the following: information for indicating whether a sub-geographic information point is included, information for indicating whether an AOI interest surface contour is included, comment information, information for indicating whether a telephone number is included;
The extracting the first characteristic information from the user behavior information of each geographic information point comprises the following steps:
Determining a single-hot encoding vector of each geographic information point based on the information indicating whether the target user behavior exists in each geographic information point;
the first characteristic information of each geographic information point is determined based on at least one of the number of times the wireless network of each geographic information point is connected by the user equipment, the number of times the user sends a request related to each geographic information point, the number of times the user places an order in each geographic information point, and the unique heat encoding vector of each geographic information point.
2. The method of claim 1, wherein the request associated with each geographic information point comprises at least one of: riding request, searching request and takeout reservation request;
The number of orders includes at least one of: number of riding orders, number of take-out orders.
3. The method of claim 1, wherein determining the first characteristic information for each geographic information point based on at least one of a number of times the wireless network of each geographic information point is connected by the user device, a number of times the user sends a request associated with each geographic information point, a number of times the user places a order in each geographic information point, and a unique heat encoding vector for each geographic information point, comprises:
determining a network connection hotness score of each geographic information point based on the number of times the wireless network of each geographic information point is connected by the user equipment;
determining a user request heat score for each geographic information point based on the number of times the user sends a request associated with each geographic information point;
Determining order hotness scores of the geographic information points based on the order number of the users in the geographic information points;
and combining at least one of the user request hotness score, the user request hotness score and the order hotness score of each geographic information point with the independent hotness coding vector of the geographic information point to obtain first characteristic information of the geographic information point.
4. The method of claim 3, wherein determining the network connection hotness score for each geographic information point based on the number of times the wireless network for each geographic information point is connected by the user device comprises:
ordering the geographic information points based on the connection times of the wireless network of the geographic information points by the user equipment to obtain a first order of the geographic information points;
And determining the network connection hotness score of each geographic information point based on preset first corresponding relation information and first sequences of each geographic information point, wherein the first corresponding relation information comprises corresponding relations between each first sequence and the network connection hotness score.
5. The method of claim 3, wherein determining the network connection hotness score for each geographic information point based on the number of times the wireless network for each geographic information point is connected by the user device comprises:
determining a first sum of the times that the wireless network of each geographic information point is connected by the user equipment;
for each geographic information point, the ratio of the number of times the wireless network of the geographic information point is connected by the user equipment to the first sum is used as the network connection hotness score of the geographic information point.
6. The method of claim 3, wherein determining a user request heat score for each geographic information point based on the number of times the user sent a request associated with each geographic information point comprises:
ordering the geographic information points based on the times of sending the requests related to the geographic information points by the user to obtain a second order of the geographic information points;
And determining the user request hotness score of each geographic information point based on preset second corresponding relation information and a second order of each geographic information point, wherein the second corresponding relation information comprises a corresponding relation between each second order and the user request hotness score.
7. The method of claim 3, wherein determining a user request heat score for each geographic information point based on the number of times the user sent a request associated with each geographic information point comprises:
Determining a second sum of the number of times the user sends the request associated with each geographic information point;
For each geographic information point, the ratio of the number of times the user sends the request related to the geographic information point to the second sum is used as the user request hotness score of the geographic information point.
8. The method of claim 3, wherein determining the order hotness score for each geographic information point based on the number of times the user has placed an order in each geographic information point comprises:
Ordering the geographic information points based on the order of the users in the geographic information points to obtain a third order of the geographic information points;
And determining the order hotness score of each geographic information point based on preset third corresponding relation information and a third order of each geographic information point, wherein the third corresponding relation information comprises a corresponding relation between each third order and the order hotness score.
9. The method of claim 3, wherein determining the order hotness score for each geographic information point based on the number of times the user has placed an order in each geographic information point comprises:
determining a third sum of the number of times of the user ordering in each geographic information point;
For each geographic information point, the ratio of the number of times the user places orders in the geographic information point to the third sum is used as the order hotness score of the geographic information point.
10. The method of claim 1, wherein the heat detection model is obtained by training a logistic regression model using a machine learning method.
11. A geographical information point ordering apparatus, comprising:
the acquisition unit is configured to acquire user behavior information and attribute information of each geographic information point to be sequenced;
an extraction unit configured to extract first feature information from user behavior information of each geographical information point and to extract second feature information from attribute information of each geographical information point;
The input unit is configured to input the first characteristic information and the second characteristic information of each geographic information point to a pre-trained hotness detection model respectively to obtain hotness scores of the geographic information points;
the ordering unit is configured to order the geographic information points according to the hotness score to obtain an ordering result;
Wherein the user behavior information of each geographic information point comprises at least one of the following: the number of times the wireless network of each geographic information point is connected by the user equipment, the number of times the user sends a request related to each geographic information point, the number of times the user orders in each geographic information point, and information indicating whether a target user behavior exists in each geographic information point;
wherein the attribute information of the geographic information point includes, but is not limited to, at least one of the following: information for indicating whether a sub-geographic information point is included, information for indicating whether an AOI interest surface contour is included, comment information, information for indicating whether a telephone number is included;
The extracting the first characteristic information from the user behavior information of each geographic information point comprises the following steps:
Determining a single-hot encoding vector of each geographic information point based on the information indicating whether the target user behavior exists in each geographic information point;
the first characteristic information of each geographic information point is determined based on at least one of the number of times the wireless network of each geographic information point is connected by the user equipment, the number of times the user sends a request related to each geographic information point, the number of times the user places an order in each geographic information point, and the unique heat encoding vector of each geographic information point.
12. An electronic device, comprising:
one or more processors;
A storage device having one or more programs stored thereon,
When executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-10.
13. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010964023.XA CN112199455B (en) | 2020-09-14 | 2020-09-14 | Geographic information point ordering method and device, electronic equipment and computer medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010964023.XA CN112199455B (en) | 2020-09-14 | 2020-09-14 | Geographic information point ordering method and device, electronic equipment and computer medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112199455A CN112199455A (en) | 2021-01-08 |
| CN112199455B true CN112199455B (en) | 2024-08-30 |
Family
ID=74016344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010964023.XA Active CN112199455B (en) | 2020-09-14 | 2020-09-14 | Geographic information point ordering method and device, electronic equipment and computer medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112199455B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112784185B (en) * | 2021-01-18 | 2022-07-08 | 腾讯科技（深圳）有限公司 | Information management method based on information points and related device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104123398A (en) * | 2014-08-15 | 2014-10-29 | 百度在线网络技术（北京）有限公司 | Information pushing method and device |
| CN104135718A (en) * | 2014-08-15 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Position information obtaining method and device |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201506356D0 (en) * | 2015-04-15 | 2015-05-27 | Tomtom Int Bv | Methods of obtaining point of interest data |
| CN106339502A (en) * | 2016-09-18 | 2017-01-18 | 电子科技大学 | Modeling recommendation method based on user behavior data fragmentation cluster |
| CN107944618B (en) * | 2017-11-20 | 2020-03-20 | 阿里巴巴集团控股有限公司 | Point arrangement planning method and device for shared vehicle and electronic equipment |
| CN109900281A (en) * | 2017-12-08 | 2019-06-18 | 北京搜狗科技发展有限公司 | Air navigation aid, device based on point of interest and the device for navigation |
| KR102681756B1 (en) * | 2018-12-27 | 2024-07-04 | 현대오토에버 주식회사 | Apparatus and method for recommending a searching result |
| CN110929162B (en) * | 2019-12-04 | 2021-08-03 | 腾讯科技（深圳）有限公司 | Recommendation method and device based on interest points, computer equipment and storage medium |
| CN111651688A (en) * | 2020-04-03 | 2020-09-11 | 北京嘀嘀无限科技发展有限公司 | Interest point retrieval method and device, electronic equipment and storage medium |
| CN111639269B (en) * | 2020-05-26 | 2023-10-27 | 汉海信息技术(上海)有限公司 | Site recommendation method and device |
-
2020
- 2020-09-14 CN CN202010964023.XA patent/CN112199455B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104123398A (en) * | 2014-08-15 | 2014-10-29 | 百度在线网络技术（北京）有限公司 | Information pushing method and device |
| CN104135718A (en) * | 2014-08-15 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Position information obtaining method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112199455A (en) | 2021-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115917535A (en) | Recommendation model training method, recommendation device and computer readable medium | |
| CN107862339B (en) | Method and apparatus for outputting information | |
| CN109242044A (en) | Training method, device, storage medium and the electronic equipment of vehicle and goods matching model | |
| CN110008973B (en) | Model training method, method and device for determining target user based on model | |
| CN110363220B (en) | Behavior class detection method and device, electronic equipment and computer readable medium | |
| CN111078940B (en) | Image processing method, device, computer storage medium and electronic equipment | |
| CN111061979B (en) | User tag pushing method and device, electronic equipment and medium | |
| CN112184290A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN111695041B (en) | Method and device for recommending information | |
| CN110489521A (en) | Text categories detection method, device, electronic equipment and computer-readable medium | |
| CN111639970A (en) | Method for determining price of article based on image recognition and related equipment | |
| CN111209351B (en) | Object relation prediction method, object recommendation method, object relation prediction device, object recommendation device, electronic equipment and medium | |
| CN111681085A (en) | Commodity pushing method and device, server and readable storage medium | |
| CN111858873A (en) | Method and device for determining recommended content, electronic equipment and storage medium | |
| CN111754278A (en) | Article recommendation method and device, computer storage medium and electronic equipment | |
| CN114579858A (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN112199455B (en) | Geographic information point ordering method and device, electronic equipment and computer medium | |
| CN110827101A (en) | Shop recommendation method and device | |
| EP3800561A1 (en) | Electronic device and control method for electronic device | |
| CN116628349B (en) | Information recommendation method, device, equipment, storage medium and program product | |
| CN113327132A (en) | Multimedia recommendation method, device, equipment and storage medium | |
| CN116611891A (en) | Content information recommendation method, device, server and storage medium | |
| CN115496420A (en) | New user quality evaluation method and device, computer equipment and storage medium | |
| CN112035740B (en) | Project use time length prediction method, device, equipment and storage medium | |
| KR102453673B1 (en) | System for sharing or selling machine learning model and operating method thereof |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |