Address query method and device based on user habits

Abstract

The invention discloses an address query method and device based on user habits. The method comprises the steps of obtaining input address data input by a target user; based on a matching algorithm, determining a plurality of candidate matching addresses according to the input address data; determining an address priority parameter corresponding to each candidate matching address according to the number of access times of the target user to each candidate matching address in a historical time period; and determining a target matching address corresponding to the input address data from the plurality of candidate matching addresses according to the address priority parameter. Visibly, the target matching address can be provided according to the query habit of the user, the effect of personalized address recommendation is achieved, and the use experience of the user is effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of address data, and in particular relates to an address query method and device based on user habits. Background Art

[0002] Address query technology is the key to effectively connect geographic space information resources with digital space. As a natural language string describing spatial coordinates, addresses not only identify the spatial coordinates of human residence, work, and life, but also have a wide range of applications in logistics, telecommunications registration, household registration, taxation, real estate, industry and commerce, and many other fields.

[0003] Traditional address recognition methods require structured input, that is, they need to specify various attributes of the address information and convert the address information entered by the user into geographic coordinates. As time goes by and data accumulates, users expect the address query system to learn their query habits and provide more personalized query results. However, existing technologies generally lack this adaptive and learning ability. Summary of the invention

[0004] The present invention provides an address query method based on user habits, which can determine the address priority parameter corresponding to each candidate matching address according to the number of visits of the target user to each candidate matching address in a historical time period, that is, provide the target matching address according to the user's query habits, thereby effectively improving the user's usage experience.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses an address query method based on user habits, the method comprising: Get the input address data entered by the target user; Based on the matching algorithm, a plurality of candidate matching addresses are determined according to the input address data; Determine an address priority parameter corresponding to each candidate matching address according to the number of visits of the target user to each candidate matching address in a historical time period; According to the address priority parameter, a target matching address corresponding to the input address data is determined from the multiple candidate matching addresses.

[0006] As a preferred implementation, determining the address priority parameter corresponding to each candidate matching address according to the number of visits of the target user to each candidate matching address in a historical time period includes: Selecting a target time period within the historical time period, and determining the number of visits to each of the candidate matching addresses; Assigning a score to each of the candidate matching addresses based on a pre-established scoring model that is positively correlated with the number of visits; The candidate matching addresses are arranged in descending order of scores.

[0007] As a preferred implementation, the matching algorithm is used to determine multiple candidate matching addresses according to the input address data, including: Based on a pre-established hierarchical splitting model, splitting the input address data into multiple hierarchical address data; Matching each of the hierarchical address data with reference address data in a pre-established address database to obtain a plurality of recommended address data; Based on a pre-established character completion model, the hierarchical address data is compared with the recommended address data and completed in order from low to high levels. If the hierarchical address data at the lowest level successfully matches the recommended address data, the recommended address data is output as a candidate matching address.

[0008] As a preferred implementation, the matching algorithm is used to determine multiple candidate matching addresses according to the input address data, including: Based on a pre-established hierarchical splitting model, splitting the input address data into multiple hierarchical address data; Matching each of the hierarchical address data with reference address data in a pre-established address database to obtain a plurality of recommended address data; Based on a pre-established statistical completion model, the hierarchical address data is compared with the recommended address data to determine whether the frequency of occurrence of the character string in the hierarchical address data in the recommended address data is greater than a threshold preset by the statistical completion model. If the judgment is yes, the input address data is completed; if the judgment is no, the statistical completion model cannot complete the input address data.

[0009] As a preferred implementation, based on a pre-established statistical completion model, the hierarchical address data is compared with the reference address data in the database to complete the address data, including: Based on a pre-established statistical completion model, determining whether the character string in the hierarchical address data completely matches the character string in the reference address data, and if so, outputting the obtained recommended address data; If the judgment is no, then based on the pre-established Softf-Find algorithm model, the hierarchical address data is subjected to fault-tolerant matching.

[0010] As a preferred implementation, the scoring model is established by the following steps: Establish a scale coefficient ranging from 0 to 1 to control the upper limit of the score value; Establish a function to characterize the change of score value with the number of visits; Establishing a sharpness coefficient to control the sensitivity of the score value; A scoring model is established based on the scale coefficient, the function and the sharpness coefficient.

[0011] As a preferred implementation, the step of performing fault-tolerant matching on the hierarchical address data based on a pre-established Softf-Find algorithm model includes: Setting a ratio threshold of the character string of the hierarchical address data to the character string of the reference address data, or a number threshold of identical character strings; The numerical value actually calculated between the character string of the hierarchical address data and the character string of the reference address data is compared with the ratio threshold or the number threshold. If it is greater than or equal to the ratio threshold or the number threshold, the statistical completion model completes the hierarchical address data; if it is less than the ratio threshold or the number threshold, the statistical completion model cannot complete it.

[0012] A second aspect of the present invention discloses an address query device based on user habits, the device comprising: An acquisition module, used to acquire input address data input by a target user; An output module, configured to determine a plurality of candidate matching addresses according to the input address data based on a matching algorithm; A calculation module, used to calculate and determine the address priority parameter corresponding to each candidate matching address according to the number of visits of the target user to each candidate matching address in a historical time period; The selection module is used to determine the target matching address corresponding to the input address data from the multiple candidate matching addresses according to the address priority parameter.

[0013] The third aspect of the present invention discloses another address query device based on user habits, the device comprising: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the address query method based on user habits disclosed in the first aspect of the present invention.

[0014] The fourth aspect of the present invention discloses a computer storage medium, wherein the computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the address query method based on user habits disclosed in the first aspect of the present invention.

[0015] Compared with the prior art, the present invention has the following beneficial effects: In the embodiment of the present invention, the input address data input by the target user is obtained; based on the matching algorithm, multiple candidate matching addresses are determined according to the input address data; the address priority parameter corresponding to each candidate matching address is determined according to the number of visits of the target user to each candidate matching address in the historical time period; and the target matching address corresponding to the input address data is determined from the multiple candidate matching addresses according to the address priority parameter. It can be seen that the implementation of the present invention can provide the target matching address according to the user's query habits, play the role of personalized recommendation address, and effectively improve the user's experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of an address query method based on user habits disclosed in an embodiment of the present invention; Figure 2 An example diagram of a character completion model in an address query method based on user habits disclosed in an embodiment of the present invention; Figure 3 A schematic diagram of the structure of an address query device based on user habits disclosed in an embodiment of the present invention; Figure 4 A schematic diagram of the structure of another address query device based on user habits disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0019] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments.

[0020] It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] The present invention discloses an address query method and device based on user habits, which can determine the address priority parameter corresponding to each candidate matching address according to the number of visits of the target user to each candidate matching address in a historical time period, that is, provide the target matching address according to the user's query habits, play the effect of personalized recommendation address, and effectively improve the user's usage experience.

[0022] Embodiment 1 See also Figure 1 , Figure 1 : is a flowchart of an address query method based on user habits disclosed in an embodiment of the present invention. Figure 1 The described method for address query based on user habits can be applied to an address query device based on user habits, wherein the address query based on user habits can be integrated in a local server or a cloud server, which is not limited in the embodiments of the present invention. Figure 1 As shown, the address query method based on user habits may include the following operations: 101. Obtain input address data input by a target user.

[0023] In the embodiment of the present invention, the input address data may be Chinese text, English text, Japanese text, etc., and the language type is not limited here.

[0024] 102. Based on a matching algorithm, a plurality of candidate matching addresses are determined according to the input address data.

[0025] Specifically, it includes: splitting the input address data into multiple levels of address data based on a pre-established hierarchical splitting model; for example, if the input address data is "Province A, City B, District C, Street D", the hierarchical splitting model will split the input address data into four levels of address data, namely "Province A", "City B", "District C" and "Street D".

[0026] Furthermore, each level of address data is matched with the reference address data in a pre-established address database to obtain multiple recommended address data; that is, "Province A", "City B", "District C" and "Street D" are searched in the address database respectively to obtain multiple matching recommended address data.

[0027] Furthermore, based on the pre-established character completion model, the hierarchical address data is compared with the recommended address data, and the missing data of each hierarchical data is completed in order from low to high levels, and the candidate matching address is output, such as Figure 2 As shown in the figure, taking the input address data of "No. 22, Health College, Zhongshan Avenue, Chaozhou, Guangdong Province" as an example, the hierarchical splitting model splits the address into "Guangdong Province", "Chaozhou", "Zhongshan Avenue", "Health College" and "No. 22", and searches for "Guangdong Province", "Chaozhou", "Zhongshan Avenue", "Health College" and "No. 22" in the address database respectively, and obtains multiple matching recommended address data. Since the hierarchical address data of "No. 22" is commonly found in various places and does not have the nature of address identification, the hierarchical address data does not participate in the completion action of the character completion model. At this time, the hierarchical address data of the lowest level is "Health College", then start from "Health College" and complete from back to front, as shown in the figure. Figure 2 As shown, the output candidate matching address is "No. 22, Health College, Zhongshan Avenue, Xiangqiao District, Chaozhou City, Guangdong Province"; it can be understood that in the step of comparing the hierarchical address data with the recommended address data, if the hierarchical address data of the lowest level successfully matches the recommended address data, there is no need to complete the data for each level, and the recommended address data will be directly output as the candidate matching address; because the candidate address is complete, it is equivalent to completing the missing content of the middle level of the input address data.

[0028] As an optional implementation, after matching each hierarchical address data with the reference address data in a pre-established address database to obtain multiple recommended address data, the hierarchical address data can also be compared with the recommended address data based on a pre-established statistical completion model for statistical completion. The statistical completion model can take into account the robustness and fault tolerance of the algorithm and be used in scenarios where "the user's input may have typos" and "the matching results of the matching algorithm may not match the user input." In the action of statistical completion, the statistical completion model determines whether the frequency of occurrence of the string in the hierarchical address data in the recommended address data is greater than the threshold preset by the statistical completion model. If the judgment is yes, the input address data is completed; if the judgment is no, the statistical completion model cannot complete the input address data. Specifically, each recommended address data of the Top10 results in multiple recommended address data is split by level, split into N levels, and N dictionaries are obtained. In each dictionary, the string in the hierarchical address data is defined as the key, and its frequency of occurrence in the Top10 is defined as the value. When the value is greater than the threshold set by the user, it means that the address data at this level appears frequently in the Top 10, which means that the recommended address data is likely to be correct. After confirming the correctness of the matching result, the keys of N dictionaries are matched in the order of the address level to obtain the unique reference address data.

[0029] Furthermore, the input address data is completed using the unique reference address data obtained above, and the input address data is split into multiple hierarchical address data based on a pre-established hierarchical splitting model; based on a pre-established statistical completion model, it is determined whether the character string in the hierarchical address data completely matches the character string in the reference address data, and if so, the obtained recommended address data is output; if not, based on a pre-established Softf-Find algorithm model, the hierarchical address data is fault-tolerantly matched, and specifically, a ratio threshold between the character string of the hierarchical address data and the character string of the reference address data, or a threshold for the number of identical character strings, is set; the numerical values ​​actually calculated between the character string of the hierarchical address data and the character string of the reference address data are compared with the ratio threshold or the number threshold, and if they are greater than or equal to the ratio threshold or the number threshold, the statistical completion model completes the hierarchical address data; if they are less than the ratio threshold or the number threshold, the statistical completion model cannot complete the data.

[0030] Specifically, as an optional implementation, after the introduction of the Softf-Find algorithm model, the matching requirements are relaxed from complete matching to "(more than half + 1) characters matching or at least 3 characters matching" to achieve fault-tolerant matching. If the fault-tolerant matching is successful, the candidate matching address is entered; if the fault-tolerant matching still fails, it means that the address entered by the user may have too many errors, the matching effect is poor, and it cannot be completed.

[0031] 103. Determine an address priority parameter corresponding to each candidate matching address according to the number of visits to each candidate matching address by the target user in a historical time period.

[0032] Specifically, it includes: selecting a target time period within a historical time period, determining the number of visits to each candidate matching address; assigning a score to each candidate matching address based on a pre-established scoring model that is positively correlated with the number of visits; and arranging the candidate matching addresses in descending order of scores. The scoring model is established through the following steps: establishing a scale coefficient ranging from 0 to 1 to control the upper limit of the score value; establishing a function for characterizing the change of the score value with the number of visits; establishing a sharp coefficient to control the sensitivity of the score value; and establishing a scoring model based on the scale coefficient, function and sharp coefficient.

[0033] Given a set of addresses, the number of user visits {y0-y j},y j Represents the i-th sample, and the scoring model is as follows:

[0034] Scale is the scale factor, ranging from 0 to 1, which controls the upper limit of this score. The access count scores of all addresses will be constrained between 0 and Scale, and the total score is Scale. T is the temperature coefficient / sharpness coefficient, which is used to control the sensitivity to larger access counts. When T is very small, even addresses with similar access counts will have significant score differences.

[0035] 104. Determine a target matching address corresponding to the input address data from a plurality of candidate matching addresses according to the address priority parameter.

[0036] In step 103, the candidate matching addresses have been arranged in descending order according to the scores. The arrangement order represents the order of personalized recommended addresses. The user can select the address data with the highest preference from multiple candidate matching addresses.

[0037] In the embodiment of the present invention, the input address data input by the target user is obtained; based on the matching algorithm, multiple candidate matching addresses are determined according to the input address data; the address priority parameter corresponding to each candidate matching address is determined according to the number of visits of the target user to each candidate matching address in the historical time period; and the target matching address corresponding to the input address data is determined from the multiple candidate matching addresses according to the address priority parameter. It can be seen that the implementation of the present invention can provide the target matching address according to the user's query habits, play the role of personalized recommendation address, and effectively improve the user's experience.

[0038] Embodiment 2 See also Figure 3 , Figure 3 FIG. 1 is a schematic diagram of a structure of an address query device based on user habits disclosed in an embodiment of the present invention. Figure 3 As shown, the address query device based on user habits may include: The acquisition module 201 is used to acquire the input address data input by the target user; An output module 202, configured to determine a plurality of candidate matching addresses based on the input address data based on a matching algorithm; The calculation module 203 is used to calculate and determine the address priority parameter corresponding to each candidate matching address according to the number of visits of the target user to each candidate matching address in the historical time period; The selection module 204 is used to determine a target matching address corresponding to the input address data from a plurality of candidate matching addresses according to the address priority parameter.

[0039] It can be seen that the implementation Figure 3 The described device can provide target matching addresses according to the user's query habits, achieve the effect of personalized address recommendation, and effectively improve the user's usage experience.

[0040] Specifically, the details of the module function steps in the above-mentioned device and the technical advantages can be referred to the corresponding description in the first embodiment, and this embodiment will not be repeated here.

[0041] Embodiment 3 See also Figure 4 , Figure 4 FIG. 1 is a schematic diagram of the structure of another address query device based on user habits disclosed in an embodiment of the present invention. Figure 4 As shown, the address query device based on user habits may include: A memory 301 storing executable program codes; A processor 302 coupled to the memory 301; The processor calls the executable program code stored in the memory 301 to execute the steps of the address query method based on user habits described in the first embodiment of the present invention.

[0042] Embodiment 4 The embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps of the address query method based on user habits described in the first embodiment of the present invention.

[0043] Embodiment 5 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the address query method based on user habits described in the first embodiment.

[0044] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0045] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data. Finally, it should be noted that the method and device for address query based on user habits disclosed in the embodiment of the present invention disclose only the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention. The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Therefore, any modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An address query method based on user habits, characterized in that: The method comprises: Get the input address data entered by the target user; Based on the matching algorithm, a plurality of candidate matching addresses are determined according to the input address data; Determine an address priority parameter corresponding to each candidate matching address according to the number of visits of the target user to each candidate matching address in a historical time period; According to the address priority parameter, a target matching address corresponding to the input address data is determined from the multiple candidate matching addresses.

2. The address query method according to claim 1, characterized in that: The determining, according to the number of visits of the target user to each candidate matching address in a historical time period, an address priority parameter corresponding to each candidate matching address includes: Selecting a target time period within the historical time period, and determining the number of visits to each of the candidate matching addresses; Assigning a score to each of the candidate matching addresses based on a pre-established scoring model that is positively correlated with the number of visits; The candidate matching addresses are arranged in descending order of scores.

3. The address query method according to claim 1, characterized in that: The method of determining a plurality of candidate matching addresses based on the input address data based on a matching algorithm includes: Based on a pre-established hierarchical splitting model, splitting the input address data into multiple hierarchical address data; Matching each of the hierarchical address data with reference address data in a pre-established address database to obtain a plurality of recommended address data; Based on a pre-established character completion model, the hierarchical address data is compared with the recommended address data and completed in order from low to high levels. If the hierarchical address data at the lowest level successfully matches the recommended address data, the recommended address data is output as a candidate matching address.

4. The address query method according to claim 1, characterized in that: The method of determining a plurality of candidate matching addresses based on the input address data based on a matching algorithm includes: Based on a pre-established hierarchical splitting model, splitting the input address data into multiple hierarchical address data; Matching each of the hierarchical address data with reference address data in a pre-established address database to obtain a plurality of recommended address data; Based on a pre-established statistical completion model, the hierarchical address data is compared with the recommended address data to determine whether the frequency of occurrence of the character string in the hierarchical address data in the recommended address data is greater than a threshold preset by the statistical completion model. If the judgment is yes, the input address data is completed; if the judgment is no, the statistical completion model cannot complete the input address data.

5. The address query method according to claim 4, characterized in that: The step of comparing the hierarchical address data with the reference address data in the database based on a pre-established statistical completion model to complete the address data includes: Based on a pre-established statistical completion model, determining whether the character string in the hierarchical address data completely matches the character string in the reference address data, and if so, outputting the obtained recommended address data; If the judgment is no, then based on the pre-established Softf-Find algorithm model, the hierarchical address data is subjected to fault-tolerant matching.

6. The address query method according to claim 2, characterized in that: The scoring model is established by the following steps: Establish a scale coefficient ranging from 0 to 1 to control the upper limit of the score value; Establish a function to characterize the change of score value with the number of visits; Establishing a sharpness coefficient to control the sensitivity of the score value; A scoring model is established based on the scale coefficient, the function and the sharpness coefficient.

7. The address query method according to claim 5, characterized in that: The step of performing fault-tolerant matching on the hierarchical address data based on the pre-established Softf-Find algorithm model comprises: Setting a ratio threshold of the character string of the hierarchical address data to the character string of the reference address data, or a number threshold of identical character strings; The numerical value actually calculated between the character string of the hierarchical address data and the character string of the reference address data is compared with the ratio threshold or the number threshold. If it is greater than or equal to the ratio threshold or the number threshold, the statistical completion model completes the hierarchical address data; if it is less than the ratio threshold or the number threshold, the statistical completion model cannot complete it.

8. An address query device based on user habits, characterized in that: The device comprises: An acquisition module, used to acquire input address data input by a target user; An output module, configured to determine a plurality of candidate matching addresses according to the input address data based on a matching algorithm; A calculation module, used to calculate and determine the address priority parameter corresponding to each candidate matching address according to the number of visits of the target user to each candidate matching address in a historical time period; The selection module is used to determine the target matching address corresponding to the input address data from the multiple candidate matching addresses according to the address priority parameter.

9. An address query device based on user habits, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the address query method based on user habits as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the address query method based on user habits as described in any one of claims 1-7.

Images