CN111190988B - Address resolution method, device, equipment and computer readable storage medium - Google Patents
Address resolution method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN111190988B CN111190988B CN201911424320.9A CN201911424320A CN111190988B CN 111190988 B CN111190988 B CN 111190988B CN 201911424320 A CN201911424320 A CN 201911424320A CN 111190988 B CN111190988 B CN 111190988B
- Authority
- CN
- China
- Prior art keywords
- point
- candidate
- resident
- determining
- information
- 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
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
- 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
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Remote Sensing (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present disclosure provides an address resolution method, apparatus, device, and computer readable storage medium, including obtaining a candidate point set corresponding to a target order, where the candidate point set includes at least one candidate location point; acquiring residence point information which is determined in advance based on user information according to information of a target order; and determining the confidence coefficient of each candidate position point according to the resident point information, and determining the target position in the candidate position points according to the confidence coefficient. The method, the device, the equipment and the computer readable storage medium provided by the disclosure can be combined with the predetermined user resident point information to determine the target position in a plurality of candidate position points which are possible to be the toed-in address, and the resident point information is obtained based on the user information and can embody the active area range of the user, so that the scheme disclosed by the disclosure can be combined with the user information to analyze the address of the target order, and thus the more accurate target address is analyzed on the premise of not depending on an address library.
Description
Technical Field
The present disclosure relates to address identification technology, and in particular, to an address resolution method, apparatus, device, and computer readable storage medium.
Background
In recent years, logistics industry has developed rapidly and coverage area is larger and larger. The whole logistics industry is also developing towards high efficiency, convenience, automation, intellectualization and refinement, wherein rapid sorting and accurate distribution are important links for reducing cost and improving user experience in a supply link.
The existing logistics sorting flow is to scan cargoes through a sorter, call an address resolution interface to further obtain the goods throwing address, sort the cargoes again, and put the cargoes into a to-be-processed area for manual processing if no accurate address exists. Wherein the address resolution interface is mainly derived from a map merchant or an internet map server.
In the address resolution scheme in the prior art, an NLP (Natural Language Processing ) algorithm is required to resolve a user candidate address set, then word segmentation and classification are carried out on the addresses, confidence assessment is carried out according to calculation rules such as classified address weights and the like and an address library model and the like, and therefore the final delivery address is determined. This approach depends on the degree of refinement of the data contained in the address library, which is costly to maintain.
Disclosure of Invention
The present disclosure provides an address resolution method, apparatus, device, and computer readable storage medium, to solve the problem in the prior art that an address resolution scheme has strong dependence on an address library.
A first aspect of the present disclosure provides an address resolution method, including:
acquiring a candidate point set corresponding to a target order, wherein the candidate point set comprises at least one candidate position point;
acquiring residence point information which is determined in advance based on user information according to the information of the target order;
and determining the confidence coefficient of each candidate position point according to the resident point information, and determining the target position in the candidate position points according to the confidence coefficient.
Another aspect of the present disclosure provides an address resolution apparatus, including:
the candidate point acquisition module is used for acquiring a candidate point set corresponding to the target order, wherein the candidate point set comprises at least one candidate position point;
the resident point acquisition module is used for acquiring resident point information which is determined in advance based on the user information according to the information of the target order;
and the target position determining module is used for determining the confidence coefficient of each candidate position point according to the resident point information and determining the target position in the candidate position points according to the confidence coefficient.
Yet another aspect of the present disclosure is to provide an address resolution apparatus, including:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the address resolution method as described in the first aspect above.
It is a further aspect of the present disclosure to provide a computer readable storage medium having stored thereon a computer program for execution by a processor to implement the address resolution method as described in the first aspect above.
The address resolution method, the address resolution device, the address resolution equipment and the computer readable storage medium provided by the disclosure have the technical effects that:
the address resolution method, the address resolution device, the address resolution equipment and the computer readable storage medium provided by the disclosure comprise the steps of obtaining a candidate point set corresponding to a target order, wherein the candidate point set comprises at least one candidate position point; acquiring residence point information which is determined in advance based on user information according to information of a target order; and determining the confidence coefficient of each candidate position point according to the resident point information, and determining the target position in the candidate position points according to the confidence coefficient. The method, the device, the equipment and the computer readable storage medium provided by the disclosure can be combined with the predetermined user residence point information to determine the target position in a plurality of candidate position points which are possible to be the address, and the residence point information is obtained based on the user information and can represent the active area range of the user.
Drawings
FIG. 1 is a flow chart of an address resolution method according to an exemplary embodiment of the invention;
FIG. 2 is a schematic diagram of candidate location points according to an exemplary embodiment of the present invention;
FIG. 3 is a flow chart of an address resolution method according to another exemplary embodiment of the present invention;
FIG. 4 is a diagram illustrating grouping results for orders according to an exemplary embodiment of the present invention;
FIG. 5 is a block diagram of an address resolution device according to an exemplary embodiment of the present invention;
FIG. 6 is a block diagram of an address resolution device according to another exemplary embodiment of the present invention;
fig. 7 is a block diagram of an address resolution apparatus according to an exemplary embodiment of the present invention.
Detailed Description
In the prior art, when cargoes are sorted by a sorter, the barking address of the cargoes needs to be identified, so that the cargoes are sorted according to the barking address, for example, the cargoes with the barking address belonging to the same area are sorted together. When the sorter identifies the consignment address of the goods, the goods can be scanned and the address resolution interface is called for identification.
The core technical scheme of the address analysis interface is that a user candidate address set is analyzed through an NLP algorithm, and the NLP analyzed Chinese address consists of address elements such as a multi-level place name, a residence name, a unit name, a house number and the like. And after the address word segmentation and classification are carried out, confidence assessment is carried out according to calculation rules such as classified address weight and the like and an address library model.
In the technical scheme, the address is only analyzed based on the NLP algorithm, the analysis result is a series of point sets, and finally, the courier is required to manually confirm the specific address. The accuracy of address resolution depends largely on the degree of refinement of the data contained in the address library. Maintaining a highly accurate address library is costly. In addition, the existing algorithm is too single and is not enough to support a plurality of complex situations, and the accuracy is required to be improved.
In order to solve the technical problems, in the scheme provided by the application, the resident point information of the user is determined in advance according to the shopping information and the position information of the user, and the target position is screened out from candidate position points of the user through the resident point information. Because the user behavior has space-time characteristics, the resident point information of the user can be determined by combining the user behavior, and the active area of the user has a certain relation with the receiving address of the user, so that the target position can be determined by combining the resident point information of the user.
Fig. 1 is a flowchart illustrating an address resolution method according to an exemplary embodiment of the present invention.
As shown in fig. 1, the address resolution method provided in this embodiment includes:
step 101, a candidate point set corresponding to a target order is obtained, wherein the candidate point set comprises at least one candidate position point.
The method provided in this embodiment may be performed by an electronic device with computing capability, for example, a server. The server may be a single server, or may be a cluster server or a distributed server.
Specifically, the server may determine the set of candidate points based on information of the target order. For example, the server may obtain the receiving address information in the target order, and call a map interface to determine, through the map service, a candidate point set corresponding to the receiving address information. For example, the shipping address information may be entered into a map service interface, and a plurality of specific location points returned through the map service interface to form a candidate point set. Further, the candidate point providing device may determine a candidate point set according to the target order, and send the candidate point set to the server for executing the method provided in this embodiment. The candidate point providing device can read the information of the target order, further determine the receiving address of the target order, and obtain a plurality of specific position points corresponding to the receiving address based on the map service interface to form a candidate point set.
In practical applications, the candidate point set may include at least one candidate location point. The candidate location points may include specific location information, which may be latitude and longitude information, for example. These candidate location points are possible pick-up addresses determined based on the receiving address of the target order.
For example, the target order receiving address is XX park, and the determined candidate point set may include n candidate location points, where the locations corresponding to the candidate location points are related to XX park. For example, one candidate location point may be the XX campus east gate and another candidate location point may be the XX campus west gate.
Fig. 2 is a schematic diagram of candidate location points according to an exemplary embodiment of the present invention.
As shown in fig. 2, where 21 is the area of the XX park, the candidate location points determined may be specific location points such as XX park east gate 22, XX park west gate 23, XX park parking lot 24, and the like.
Step 102, obtaining residence point information which is determined in advance based on the user information according to the information of the target order.
In the method provided in this embodiment, the resident point information is determined in advance based on the user information, and specifically, the resident point information of the user may be determined based on the order information and the position information of the user. The residence point information may be predetermined by the device performing the method or may be determined by other devices.
Specifically, the dwell point is used to characterize the active area of the user. For example, if the user has an activity duration exceeding a preset duration in an area with a range smaller than the preset range, the area may be considered as a dwell point. For example, a location point is taken as a circle center, the activity range of the user does not exceed the area range of 50 meters of the circle center, and the activity duration in the area reaches 30 minutes, so that the location point or the area range can be determined as a residence point.
The location information of the user may be obtained by the location data reported by the user terminal, for example, after the user opens an application, the application may report specific location data to the background.
Further, each dwell point may have corresponding information, such as location information. In one embodiment, the location information of the residence point P1 may be (X 1 -X 2 、Y 1 -Y 2 )，Where X may be used to represent an abscissa or latitude on the map and Y may be used to represent an ordinate or longitude on the map, the area range of the dwell point may be indicated in this manner. In yet another embodiment, the location information of the residence point P2 may be (X 3 、Y 3 ) The radius is R, indicating that the area of the residence point P2 is represented by X 3 、Y 3 The radius is the area range of R as the center of the circle.
In actual use, the residence point may also have order information. Such as a corresponding order count. The number of orders corresponding to each resident point can be determined according to the order information of the user, specifically, the orders of the user can be grouped according to the resident points and the receiving addresses in the order information, for example, the receiving addresses of the orders 1 are located in the range of the resident point P1, and then the orders 1 are divided into order groups corresponding to the P1. Based on this, the number of orders corresponding to each resident point, that is, the number of orders to which the receiving address belongs at each resident point when the user shops, can be determined.
The residence may also have type information, for example, the type of the residence is school, home, company, etc. It can be determined from the map data that a residence is in a residential area, or in a school area, or in a company area.
Specifically, after the server obtains the candidate point set corresponding to the target order, the information in the target order can be read, so as to determine the user information. For example, the user identification, which may be a unique identification of the user, such as the user's account number.
Further, the server may obtain, according to the user identifier, residence point information corresponding to the user. Because the range of motion of people is wider, therefore, can acquire a plurality of resident point information. Such as a user moving at home and a company for a long period of time, it is possible to acquire two resident point information.
In actual application, the receiving address corresponding to the target order can be obtained, and the alternative resident point information is screened out from the resident point information of the user. For example, a dwell point whose distance from the receiving address does not exceed the distance threshold may be determined as an alternative dwell point, and information of these alternative dwell points may be acquired.
And step 103, determining the confidence coefficient of each candidate position point according to the resident point information, and determining the target position in the candidate position points according to the confidence coefficient.
In practical application, the residence point refers to an area where a user frequently moves, and is determined based on information of the user. The user information has certain relevance with the receiving address when shopping, so that the confidence level of the candidate position point can be determined according to the information of each resident point, and the target position can be determined in the candidate position point according to the confidence level.
If the resident point information includes location information, the distance confidence of each candidate location point may be determined according to the location information of the resident point. I.e. the likelihood that the candidate location point is the toboggan address is determined by the location relationship with the resident point. For example, the resident point closest to each candidate location point may be determined, and the distance between the corresponding points may be calculated, where the candidate location point with the smallest distance is considered to be the most likely toboggan address.
Specifically, if the resident point information includes order information, the shopping confidence of each candidate location point may be determined according to the order information of the resident point. The resident points closest to each candidate location point can be determined, and then the shopping confidence of the candidate location point is determined according to the order information of the closest resident points. For example, if the nearest resident point of the candidate location point a is P1, the shopping confidence of a may be determined according to the order information of P1. For example, the more orders there are for the nearest resident points, the more likely the corresponding candidate location point is the toboggan address.
Further, if the resident point information includes type information, the shopping confidence of each candidate location point may be determined according to the type information. The resident points closest to each candidate location point can be determined, and the shopping confidence of the corresponding candidate location point is determined by combining the type of the closest resident point. For example, if the nearest resident point of a candidate location point is P2, the type of which is a residential area, and the type of goods in the target order is used in the home, the probability that the candidate location point is a home address can be considered to be high.
The method provided by the embodiment can determine one or more confidence degrees according to the resident point information, determine the target position in the candidate position points by combining the confidence degrees, and determine the determined target position as the toboggan address.
In practical application, if a confidence coefficient is determined, the candidate position point with the largest confidence coefficient can be directly determined as the target position. If multiple confidence levels are determined, a sum or weighted sum of these confidence levels may be determined, resulting in a final confidence level, and the target location may be determined in the candidate location points based on the final confidence level.
The method provided by the present embodiment is used for address resolution, and the method is performed by an apparatus provided with the method provided by the present embodiment, and the apparatus is typically implemented in hardware and/or software.
The address resolution method provided by the embodiment comprises the steps of obtaining a candidate point set corresponding to a target order, wherein the candidate point set comprises at least one candidate position point; acquiring residence point information which is determined in advance based on user information according to information of a target order; and determining the confidence coefficient of each candidate position point according to the resident point information, and determining the target position in the candidate position points according to the confidence coefficient. The method provided by the embodiment can be combined with the predetermined user resident point information to determine the target position in the plurality of candidate position points which are possible to be the address, and the resident point information is obtained based on the user information and can represent the active area range of the user, so that the method provided by the embodiment can be combined with the user information to analyze the address of the target order, and the more accurate target address can be analyzed on the premise of not depending on the address library.
Fig. 3 is a flowchart illustrating an address resolution method according to another exemplary embodiment of the present invention.
As shown in fig. 3, the address resolution method provided in this embodiment includes:
step 301, determining at least one residence point of a user according to the position information of the user.
The method provided in this embodiment may determine the residence point information in advance.
Specifically, the server may receive location information reported by the user. For example, the user terminal opens an application program, and the application program can read the positioning device data installed by the terminal, further obtain the position of the terminal, and report the position information to the server. The specific reported content may include a user identification and a specific location.
Further, the range of the active area of the user can be determined according to the position information of the user, so as to determine the residence point. For example, if the user stays near the position P1 for 30 minutes, the area near P1 can be regarded as a stay point. Specifically, according to the location information, an area where the user does not exceed the preset range in the preset duration range and the active area is determined to be the residence point
In practical application, an area may be defined about the reported position, for example, an area range with a radius R may be defined about the reported position, and the time t1 when the user enters the area and the time t2 when the user leaves the area are determined, and if the time difference between t1 and t2 is greater than or equal to a time threshold, the area may be considered as a residence point, or the reported position may be determined as a residence point.
Step 302, grouping shopping orders of users according to the resident points, and determining order information corresponding to the resident points according to grouping results.
In the method provided in this embodiment, the resident point information may include order information.
Shopping orders for the user may be acquired for grouping. Specifically, the receiving address of the shopping order can be obtained, and the residence point corresponding to the order is determined according to the receiving address. For example, if the receiving address 1 belongs to the area range of the point 1, the order corresponding to the receiving address may be divided into order groups corresponding to the point 1, and if the receiving address 2 does not belong to the area range of any point, for example, the point 1 closest to the receiving address 2 may be determined, and the order corresponding to the receiving address 2 may be divided into order groups corresponding to the point 1.
FIG. 4 is a diagram illustrating grouping results for orders according to an exemplary embodiment of the present invention.
As shown in fig. 4, 3 residence points A, B, C may be included in the figure, where squares in the figure indicate the receiving addresses of the respective orders, where orders 1, 2 may be divided into order groups corresponding to residence point a, orders 3, 4, 5 may be divided into order groups corresponding to residence point B, and order 6 may be divided into order groups corresponding to residence point C.
Specifically, order information corresponding to the residents may be determined according to the grouping result, and the order information may be, for example, the order quantity, that is, the order quantity corresponding to each residents. For example, the number of orders corresponding to dwell point A is 2, the number of orders corresponding to dwell point B is 3, and the number of orders corresponding to dwell point C is 1.
Step 303, determining the position type information of each resident point according to the preset map data.
The execution timing of step 302 and step 303 is not limited.
Further, in the method provided in this embodiment, the residence point information may further include location type information.
In practical application, map data can be preset, and position type information of the residence point can be determined.
The location type information may be, for example, a point of interest type (POI, point of Interest) of the resident point, and may also be a road network type.
The POI may be a house, a shop, a mailbox, a bus station, etc., and in combination with the preset map data, the corresponding interest point type can be determined based on the location of the resident point. The road network type may be used to characterize road information around a dwell point, for example between road line1 and line2, and for example on road line 3.
The confidence of the candidate location point may be determined in combination with the location where the dwell point is located, such as a higher dwell point confidence on the dwell point avoidance road of the residential area.
The resident point information of the user can be determined in advance according to the user information, and the resident point information of the user can be directly obtained and analyzed when the order receiving address of the user is analyzed.
Step 304, a candidate point set corresponding to the target order is obtained, wherein the candidate point set comprises at least one candidate position point.
Step 305, obtaining residence point information determined in advance based on the user information according to the information of the target order.
Steps 304-305 are similar to the specific principles and implementations of steps 101-102 and are not repeated here.
And step 306, determining the distance value confidence coefficient, the shopping behavior confidence coefficient and the type confidence coefficient corresponding to each candidate position point according to the resident point information.
Specifically, according to the method provided by the embodiment, the confidence of the distance value corresponding to each candidate position point can be determined according to the position of the resident point in the resident point information.
Further, the method for determining the distance confidence may further include:
determining the nearest resident point which is nearest to each candidate position point in the resident points;
determining the distance between the points according to the candidate position points and the corresponding nearest resident points;
determining a maximum distance and a minimum distance among the inter-point distances;
and determining the distance confidence coefficient of the candidate position point according to the distance between the candidate position point and the corresponding nearest resident point, the maximum distance and the minimum distance.
The nearest dwell point closest to each candidate location point may be determined among the dwell points. The received candidate point set may include a plurality of candidate location points, e.g., Q, which is a candidate location point set { Q1, Q2, Q3 … qn }.
In practical application, the obtained residence point information may be a set, including each residence point and its corresponding information. For example, the dwell point may be an SP, including { SP1, SP2, SP3 … spm }.
Wherein a closest dwell point (q) closest to each candidate location point may be determined among dwell points. For example, the nearest dwell point corresponding to q1 may be sp2 and the nearest dwell point corresponding to q2 may be sp3.
Specifically, the inter-point distance dist (q, sp) may be determined according to the candidate location point and its corresponding nearest resident point. Specifically, the euclidean distance between the candidate position point q and the nearest resident point sp corresponding to the candidate position point q can be calculated as the inter-point distance.
Further, for each set of corresponding q and sp, an inter-point distance can be determined. A maximum distance and a minimum distance may be determined among the inter-point distances.
In practical application, the distance confidence coefficient of the candidate position point can be determined according to the distance, the maximum distance and the minimum distance between the candidate position point and the corresponding nearest resident point. For a candidate location point q, the distance confidence of the candidate location point q can be determined by combining the distance between the point q and the corresponding nearest resident point, and the determined maximum distance and minimum distance.
The distance between the candidate position point and the corresponding nearest resident point can be normalized to be a distance confidence between 0 and 1 according to the maximum distance and the minimum distance. For example, for a candidate location point q, the distance between the candidate location point q and the corresponding nearest resident point is L, the distance between the points L may be normalized to a distance confidence level between 0 and 1 according to the determined maximum distance and minimum distance, and the distance confidence level may be used to represent the angle of the distance between the candidate location point q and the resident point, where each candidate location point is a probability value of the target address.
Specifically, according to the method provided by the embodiment, the shopping behavior confidence coefficient corresponding to each candidate location point can be determined according to the order information in the resident point information.
Further, the method for determining the confidence level of the shopping behavior may further include:
determining the number of orders corresponding to each resident point according to the order information corresponding to each resident point;
the maximum amount of orders and the minimum amount of orders are determined in the order quantity;
and determining the shopping behavior confidence coefficient of the candidate position point according to the order quantity, the maximum order quantity and the minimum order quantity of the nearest resident point corresponding to the candidate position point.
The nearest dwell point closest to each candidate location point may be determined among the dwell points. The specific determination is similar to the above, and the previously determined nearest residence point can also be directly read.
In one embodiment, order information corresponding to each of the points may be obtained, for example, order data that determines that the receiving address belongs to the point may be determined, and the number of orders corresponding to each of the points may be determined based on the order data.
In another embodiment, the predetermined order information corresponding to each resident point may include the number of orders, and at this time, the number of orders corresponding to the resident points may be determined directly according to the read order information. For example, the order number corresponding to the dwell point sp1 is 5, and the order number corresponding to the dwell point sp2 is 10.
Further, for the number of orders corresponding to each point, the maximum number of orders and the minimum number of orders can be determined. For example, for a user of a target order, 20 pieces of corresponding resident point information are acquired, and for each resident point, one order quantity can be determined, so that 20 order quantities can be obtained. In which a maximum order quantity and a minimum order quantity may be determined.
In practical application, the shopping behavior confidence coefficient of the candidate position point can be determined according to the order quantity, the maximum order quantity and the minimum order quantity of the nearest resident point corresponding to the candidate position point. For a candidate location point q, the shopping behavior confidence of the candidate location point q can be determined according to the order quantity of the nearest resident point corresponding to the location point q and the determined maximum order quantity and minimum order quantity.
The order quantity of the nearest resident point corresponding to the candidate position point can be normalized to be the shopping behavior confidence coefficient between 0 and 1 according to the maximum order quantity and the minimum order quantity. For example, for a candidate location point q, the number of orders of the corresponding nearest stay point is n, the distance n between points can be normalized to be a shopping behavior confidence between 0 and 1 according to the determined maximum number of orders and the minimum number of orders, and the shopping behavior confidence can be used for showing the shopping behavior angle of the user, so that each candidate location point is a probability value of the target address.
According to the method provided by the embodiment, the type confidence corresponding to each candidate position point can be determined according to the position type information in the resident point information.
Further, the method for determining the type confidence may further include:
determining a position type score corresponding to each resident point according to the position type information corresponding to each resident point;
determining a maximum type score and a minimum type score in the position type scores;
and determining the type confidence of the candidate position point according to the position type score, the maximum type score and the minimum type score of the nearest resident point corresponding to the candidate position point.
The nearest dwell point closest to each candidate location point may be determined among the dwell points. The specific determination is similar to the above, and the previously determined nearest residence point can also be directly read.
The method comprises the steps of acquiring position type information of each resident point, and determining a position type score corresponding to each resident point. For example, a score for a resident point that belongs to the location type may be determined based on location type information for the resident point. The score corresponding to each location type may be preset, so that the corresponding score may be obtained directly based on the location type to which the resident point belongs.
For example, if the location type includes POI types, the score corresponding to each POI type may be preset, such as a score corresponding to a house, a score corresponding to an office area, and the like.
For another example, if the location type information includes a road network type, road information around the residence point may be determined by combining preset map data, so as to determine that the road network information corresponding to the residence point is information of national roads, provincial roads, county roads, or the like. The corresponding road type score may be determined from the road type of the stagnation point.
Specifically, a corresponding location type score may be determined for each dwell point. The location type information may include POI type, road network type; correspondingly, the location type score comprises a POI type score and a road network type score of the resident point.
The score may be used to characterize the score that the resident point belongs to the corresponding location type, e.g., the higher the score, the more pronounced the score
Further, the sum of the POI type score and the road network type score can be used as the final location type score of the resident point.
In practical application, the maximum type score and the minimum type score can be determined in the determined position type scores.
For a candidate location point q, the type confidence of the candidate location point q may be determined according to the location type score of the nearest resident point corresponding to the location point q, and the determined maximum type score and minimum type score.
The position type score of the nearest resident point corresponding to the candidate position point can be normalized to be of the type confidence between 0 and 1 according to the maximum type score and the minimum type score. For example, for a candidate location point q, the location type score of the corresponding nearest resident point is s, and then the location type score s may be normalized to a type confidence between 0 and 1 according to the determined maximum type score and minimum type score, where the type confidence may represent an angle of the location type, and each candidate location point is a probability value of the target address.
Step 307, determining the confidence of each candidate position point according to the confidence of the distance value, the confidence of the shopping behavior and the confidence of the type.
Specifically, after the distance value confidence coefficient, the shopping behavior confidence coefficient and the type confidence coefficient of a candidate position point are obtained, the confidence coefficient of the candidate position point can be determined by combining the distance value confidence coefficient, the shopping behavior confidence coefficient and the type confidence coefficient, and the average value of the distance value confidence coefficient, the shopping behavior confidence coefficient and the type confidence coefficient can be calculated and used as the confidence coefficient of the candidate position point.
Based on the above manner, the confidence level corresponding to each candidate position point can be obtained.
Step 308, determining the target position in the candidate position points according to the confidence level.
Step 308 is similar to the manner of determining the target position in step 103, and will not be described again.
Fig. 5 is a block diagram of an address resolution apparatus according to an exemplary embodiment of the present invention.
As shown in fig. 5, the address resolution apparatus provided in this embodiment includes:
a candidate point obtaining module 51, configured to obtain a candidate point set corresponding to a target order, where the candidate point set includes at least one candidate location point;
a resident point obtaining module 52, configured to obtain, according to the information of the target order, resident point information determined in advance based on the user information;
the target position determining module 53 is configured to determine a confidence level of each candidate position point according to the resident point information, and determine a target position in the candidate position points according to the confidence level.
The address resolution device provided by the embodiment of the application comprises: the candidate point acquisition module is used for acquiring a candidate point set corresponding to the target order, wherein the candidate point set comprises at least one candidate position point; the resident point acquisition module is used for acquiring resident point information which is determined in advance based on the user information according to the information of the target order; and the target position determining module is used for determining the confidence coefficient of each candidate position point according to the resident point information and determining the target position in the candidate position points according to the confidence coefficient. The device provided in this embodiment may determine the target location in a plurality of candidate location points that may be the target address by combining predetermined user residence point information, where the residence point information is obtained based on the user information and may represent the active area range of the user, so that the device provided in this embodiment may resolve the address of the target order by combining the user information, and thus resolve a more accurate target address without depending on an address library.
The specific principle and implementation manner of the address resolution device provided in this embodiment are similar to those of the embodiment shown in fig. 2, and are not repeated here.
Fig. 6 is a block diagram of an address resolution apparatus according to another exemplary embodiment of the present invention.
As shown in fig. 6, on the basis of the above embodiment, the address resolution apparatus provided in this embodiment,
optionally, the resident point information includes order information corresponding to a resident point and position type information corresponding to the resident point;
the apparatus further comprises a preprocessing module 54 for:
determining at least one residence point of a user according to the position information of the user;
grouping shopping orders of the users according to the resident points, and determining order information corresponding to the resident points according to grouping results;
and determining the position type information of each resident point according to preset map data.
Optionally, the target location determining module 53 includes:
the first confidence determining unit 531 is configured to determine a distance confidence level, a shopping behavior confidence level, and a type confidence level corresponding to each candidate location point according to the resident point information;
a second confidence determining unit 532, configured to determine a confidence level of each candidate location point according to the distance value confidence level, the shopping behavior confidence level, and the type confidence level.
Optionally, the first confidence determining unit 531 is specifically configured to:
determining nearest resident points which are nearest to each candidate position point in the resident points;
determining the distance between the points according to the candidate position points and the corresponding nearest resident points;
determining a maximum distance and a minimum distance among the inter-point distances;
and determining the distance confidence coefficient of the candidate position point according to the distance between the candidate position point and the corresponding nearest resident point, the maximum distance and the minimum distance.
Optionally, the first confidence determining unit 531 is specifically configured to:
determining the number of orders corresponding to each resident point according to the order information corresponding to each resident point;
the maximum quantity of orders and the minimum quantity of orders are determined in the order quantity;
and determining the shopping behavior confidence coefficient of the candidate position point according to the order quantity of the nearest stay point corresponding to the candidate position point, the maximum order quantity and the minimum order quantity.
Optionally, the first confidence determining unit 531 is specifically configured to:
determining a position type score corresponding to each resident point according to the position type information corresponding to each resident point;
determining a maximum type score and a minimum type score in the position type scores;
and determining the type confidence of the candidate position point according to the position type score, the maximum type score and the minimum type score of the nearest resident point corresponding to the candidate position point.
Optionally, the preprocessing module 54 is specifically configured to:
and determining an area of which the active area does not exceed a preset range in a preset duration range according to the position information, and determining the area as the residence point.
The first confidence determining unit 531 specifically is configured to:
and normalizing the distance between the candidate position points and the corresponding nearest resident points to be a distance confidence degree between 0 and 1 according to the maximum distance and the minimum distance.
The first confidence determining unit 531 specifically is configured to: and normalizing the number of orders of the nearest resident points corresponding to the candidate position points to be the shopping behavior confidence coefficient between 0 and 1 according to the maximum number of orders and the minimum number of orders.
The first confidence determining unit 531 specifically is configured to: and normalizing the position type score of the nearest resident point corresponding to the candidate position point to be a type confidence coefficient between 0 and 1 according to the maximum type score and the minimum type score.
The second confidence determining unit 532 is specifically configured to: and determining the confidence coefficient of the candidate position point as the average value of the distance value confidence coefficient, the shopping behavior confidence coefficient and the type confidence coefficient of the candidate position point.
The specific principle and implementation manner of the address resolution device provided in this embodiment are similar to those of the embodiment shown in fig. 3, and are not repeated here.
Fig. 7 is a block diagram of an address resolution apparatus according to an exemplary embodiment of the present invention.
As shown in fig. 7, the address resolution apparatus provided in this embodiment includes:
a memory 71;
a processor 72; and
a computer program;
wherein the computer program is stored in the memory 71 and configured to be executed by the processor 72 to implement any one of the address resolution methods described above.
The present embodiment also provides a computer-readable storage medium, having stored thereon a computer program,
the computer program is executed by a processor to implement any of the address resolution methods described above.
The present embodiment also provides a computer program comprising program code which, when run by a computer, performs any of the address resolution methods described above.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the method embodiments described above may be performed by hardware associated with program instructions. The foregoing program may be stored in a computer readable storage medium. The program, when executed, performs steps including the method embodiments described above; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (13)
1. An address resolution method, comprising:
acquiring a candidate point set corresponding to a target order, wherein the candidate point set comprises at least one candidate position point;
acquiring residence point information which is determined in advance based on user information according to the information of the target order;
determining the confidence coefficient of each candidate position point according to the resident point information, and determining a target position in the candidate position points according to the confidence coefficient;
the resident point information comprises order information corresponding to a resident point and position type information corresponding to the resident point;
the method further comprises the steps of:
determining at least one residence point of a user according to the position information of the user;
grouping shopping orders of the users according to the resident points, and determining order information corresponding to the resident points according to grouping results;
and determining the position type information of each resident point according to preset map data.
2. The method of claim 1, wherein said determining a confidence level for each of said candidate location points based on said dwell point information comprises:
determining the distance confidence coefficient, the shopping behavior confidence coefficient and the type confidence coefficient corresponding to each candidate position point according to the resident point information;
and determining the confidence coefficient of each candidate position point according to the distance confidence coefficient, the shopping behavior confidence coefficient and the type confidence coefficient.
3. The method of claim 2, wherein determining a distance confidence level for each candidate location point based on the dwell point information comprises:
determining nearest resident points which are nearest to each candidate position point in the resident points;
determining the distance between the points according to the candidate position points and the corresponding nearest resident points;
determining a maximum distance and a minimum distance among the inter-point distances;
and determining the distance confidence coefficient of the candidate position point according to the distance between the candidate position point and the corresponding nearest resident point, the maximum distance and the minimum distance.
4. The method of claim 2, wherein determining a confidence level of shopping behavior for each candidate location point based on the stay point information comprises:
determining the number of orders corresponding to each resident point according to the order information corresponding to each resident point;
the maximum quantity of orders and the minimum quantity of orders are determined in the order quantity;
and determining the shopping behavior confidence coefficient of the candidate position point according to the order quantity of the nearest stay point corresponding to the candidate position point, the maximum order quantity and the minimum order quantity.
5. The method of claim 2, wherein determining a type confidence level for each candidate location point based on the dwell point information comprises:
determining a position type score corresponding to each resident point according to the position type information corresponding to each resident point;
determining a maximum type score and a minimum type score in the position type scores;
and determining the type confidence of the candidate position point according to the position type score, the maximum type score and the minimum type score of the nearest resident point corresponding to the candidate position point.
6. The method of claim 1, wherein said determining at least one point of residence for a user based on user location information comprises:
and determining an area of which the active area does not exceed a preset range in a preset duration range according to the position information, and determining the area as the residence point.
7. A method according to claim 3, wherein said determining a distance value confidence of said candidate location point from an inter-point distance of said candidate location point to a corresponding nearest resident point, said maximum distance, said minimum distance comprises:
and normalizing the distance between the candidate position points and the corresponding nearest resident points to be a distance confidence degree between 0 and 1 according to the maximum distance and the minimum distance.
8. The method of claim 4, wherein determining the confidence of the shopping behavior of the candidate location point according to the number of orders of the nearest resident point corresponding to the candidate location point, the maximum amount of orders, and the minimum amount of orders comprises:
and normalizing the number of orders of the nearest resident points corresponding to the candidate position points to be the shopping behavior confidence coefficient between 0 and 1 according to the maximum number of orders and the minimum number of orders.
9. The method of claim 5, wherein the determining the type confidence of the candidate location point based on the location type score, the maximum type score, and the minimum type score of the nearest resident point corresponding to the candidate location point comprises:
and normalizing the position type score of the nearest resident point corresponding to the candidate position point to be a type confidence coefficient between 0 and 1 according to the maximum type score and the minimum type score.
10. The method of claim 2, wherein said determining a confidence level for each of said candidate location points based on said distance value confidence level, said shopping behavior confidence level, said type confidence level comprises:
and determining the distance confidence coefficient of the candidate position point, the shopping behavior confidence coefficient and the average value of the type confidence coefficient as the confidence coefficient of the candidate position point.
11. An address resolution apparatus, comprising:
the candidate point acquisition module is used for acquiring a candidate point set corresponding to the target order, wherein the candidate point set comprises at least one candidate position point;
the resident point acquisition module is used for acquiring resident point information which is determined in advance based on the user information according to the information of the target order;
the target position determining module is used for determining the confidence coefficient of each candidate position point according to the resident point information and determining a target position in the candidate position points according to the confidence coefficient;
the resident point information comprises order information corresponding to a resident point and position type information corresponding to the resident point;
the device also comprises a preprocessing module for:
determining at least one residence point of a user according to the position information of the user;
grouping shopping orders of the users according to the resident points, and determining order information corresponding to the resident points according to grouping results;
and determining the position type information of each resident point according to preset map data.
12. An address resolution device, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-10.
13. A computer-readable storage medium, having a computer program stored thereon,
the computer program being executed by a processor to implement the method of any of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911424320.9A CN111190988B (en) | 2019-12-31 | 2019-12-31 | Address resolution method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911424320.9A CN111190988B (en) | 2019-12-31 | 2019-12-31 | Address resolution method, device, equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111190988A CN111190988A (en) | 2020-05-22 |
| CN111190988B true CN111190988B (en) | 2023-08-08 |
Family
ID=70708080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911424320.9A Active CN111190988B (en) | 2019-12-31 | 2019-12-31 | Address resolution method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111190988B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111915072A (en) * | 2020-07-20 | 2020-11-10 | 上海燕汐软件信息科技有限公司 | Courier attendance amount prediction method, device and equipment |
| CN112767740B (en) * | 2021-02-04 | 2022-08-16 | 广州小鹏自动驾驶科技有限公司 | Parking lot selection method and device |
| CN113720340A (en) * | 2021-04-16 | 2021-11-30 | 京东城市(北京)数字科技有限公司 | Method and device for determining geographic position, electronic equipment and storage medium |
| CN113535880B (en) * | 2021-09-16 | 2022-02-25 | 阿里巴巴达摩院(杭州)科技有限公司 | Geographic information determination method and device, electronic equipment and computer storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2755175A1 (en) * | 2013-01-15 | 2014-07-16 | Pilar B.V. | Method and system for delivering an item |
| WO2015172583A1 (en) * | 2014-05-15 | 2015-11-19 | 华为技术有限公司 | Data processing system and method |
| CN105488645A (en) * | 2014-09-15 | 2016-04-13 | 深圳前海百递网络有限公司 | Position range obtaining method and device |
| CN106204186A (en) * | 2016-06-22 | 2016-12-07 | 北京小米移动软件有限公司 | Sequence information determines method and device |
| CN106296059A (en) * | 2015-06-02 | 2017-01-04 | 阿里巴巴集团控股有限公司 | Send site with charge free and determine method and apparatus |
| CN107305577A (en) * | 2016-04-25 | 2017-10-31 | 北京京东尚科信息技术有限公司 | Correct-distribute address date processing method and system based on K-means |
| CN107451767A (en) * | 2016-05-31 | 2017-12-08 | 阿里巴巴集团控股有限公司 | The recommendation method and device of logistics information, the methods of exhibiting and device of logistics information |
| CN107844933A (en) * | 2017-09-21 | 2018-03-27 | 北京小度信息科技有限公司 | order processing method and device |
| CN108364143A (en) * | 2017-01-26 | 2018-08-03 | 北京京东尚科信息技术有限公司 | Allocator and delivery system |
| CN108805492A (en) * | 2018-05-28 | 2018-11-13 | 北京小米移动软件有限公司 | Order allocator, device and storage medium |
| CN109299901A (en) * | 2018-09-29 | 2019-02-01 | 北京掌上先机网络科技有限公司 | A kind of method, apparatus, equipment and the storage medium of determining commodity distribution shops |
| CN109359759A (en) * | 2018-08-07 | 2019-02-19 | 深圳市易达云科技有限公司 | Intelligence divides storehouse method, equipment and computer readable storage medium |
| CN110084557A (en) * | 2019-04-28 | 2019-08-02 | 北京云迹科技有限公司 | A kind of automatic delivery system, method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070150375A1 (en) * | 2000-12-08 | 2007-06-28 | Ping Yang | Method and apparatus for efficient meal delivery |
| US9852391B2 (en) * | 2014-02-22 | 2017-12-26 | Mena360 Dwc-Llc | System and method for logistics network utilizing mobile device location information |
-
2019
- 2019-12-31 CN CN201911424320.9A patent/CN111190988B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2755175A1 (en) * | 2013-01-15 | 2014-07-16 | Pilar B.V. | Method and system for delivering an item |
| WO2015172583A1 (en) * | 2014-05-15 | 2015-11-19 | 华为技术有限公司 | Data processing system and method |
| CN105488645A (en) * | 2014-09-15 | 2016-04-13 | 深圳前海百递网络有限公司 | Position range obtaining method and device |
| CN106296059A (en) * | 2015-06-02 | 2017-01-04 | 阿里巴巴集团控股有限公司 | Send site with charge free and determine method and apparatus |
| CN107305577A (en) * | 2016-04-25 | 2017-10-31 | 北京京东尚科信息技术有限公司 | Correct-distribute address date processing method and system based on K-means |
| CN107451767A (en) * | 2016-05-31 | 2017-12-08 | 阿里巴巴集团控股有限公司 | The recommendation method and device of logistics information, the methods of exhibiting and device of logistics information |
| CN106204186A (en) * | 2016-06-22 | 2016-12-07 | 北京小米移动软件有限公司 | Sequence information determines method and device |
| CN108364143A (en) * | 2017-01-26 | 2018-08-03 | 北京京东尚科信息技术有限公司 | Allocator and delivery system |
| CN107844933A (en) * | 2017-09-21 | 2018-03-27 | 北京小度信息科技有限公司 | order processing method and device |
| CN108805492A (en) * | 2018-05-28 | 2018-11-13 | 北京小米移动软件有限公司 | Order allocator, device and storage medium |
| CN109359759A (en) * | 2018-08-07 | 2019-02-19 | 深圳市易达云科技有限公司 | Intelligence divides storehouse method, equipment and computer readable storage medium |
| CN109299901A (en) * | 2018-09-29 | 2019-02-01 | 北京掌上先机网络科技有限公司 | A kind of method, apparatus, equipment and the storage medium of determining commodity distribution shops |
| CN110084557A (en) * | 2019-04-28 | 2019-08-02 | 北京云迹科技有限公司 | A kind of automatic delivery system, method and device |
Non-Patent Citations (1)
| Title |
|---|
| 基于地理位置信息的安卓购物系统设计;李峰等;《计算机技术与发展》(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111190988A (en) | 2020-05-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111190988B (en) | Address resolution method, device, equipment and computer readable storage medium | |
| WO2021017679A1 (en) | Address information parsing method and apparatus, system and data acquisition method | |
| CN109325116B (en) | Urban event automatic classification dispatching method and device based on deep learning | |
| CN113255815B (en) | User behavior abnormity analysis method, device, equipment and storage medium | |
| CN108628811B (en) | Address text matching method and device | |
| CN111028016A (en) | Sales data prediction method and device and related equipment | |
| CN111931077B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN113177101B (en) | User track identification method, device, equipment and storage medium | |
| CN111782741A (en) | Interest point mining method and device, electronic equipment and storage medium | |
| CN113722617A (en) | Method and device for identifying actual office address of enterprise and electronic equipment | |
| CN116029637A (en) | Cross-border electronic commerce logistics channel intelligent recommendation method and device, equipment and storage medium | |
| CN114330550A (en) | Model fusion strategy selection method and device and electronic equipment | |
| CN112200644B (en) | Method and device for identifying fraudulent user, computer equipment and storage medium | |
| CN116522565B (en) | BIM-based power engineering design power distribution network planning method and computer equipment | |
| CN111582313B (en) | Sample data generation method and device and electronic equipment | |
| CN112435078A (en) | Method for classifying loyalty of users | |
| CN111882421B (en) | Information processing method, wind control method, device, equipment and storage medium | |
| CN109919811B (en) | Insurance agent culture scheme generation method based on big data and related equipment | |
| CN111369284B (en) | Target object type determining method and device | |
| CN113032514A (en) | Method and device for processing point of interest data | |
| CN112015937A (en) | Picture geographical positioning method and system | |
| CN110689170A (en) | Object parameter determination method and device, electronic equipment and storage medium | |
| CN112464970A (en) | Regional value evaluation model processing method and device and computing equipment | |
| CN115438138B (en) | Employment center identification method and device, electronic equipment and storage medium | |
| CN115481961A (en) | Method and device for predicting time of delivery resources reaching merchants |
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 |