Regional jurisdiction unit determination method, device, equipment, medium and program

Abstract

The embodiment of the invention discloses a method, a device and equipment for determining a regional jurisdiction unit, a medium and a program. The method comprises the following steps: determining a place attribute text corresponding to at least one preset place; wherein the place attribute text is used for describing place attributes of the place; determining a semantic similarity degree value between an address text corresponding to a task execution address of the to-be-processed task and a place attribute text corresponding to at least one place; and based on the semantic similarity degree value, determining an affiliation region jurisdiction unit for executing the to-be-processed task in the region jurisdiction units to which the at least one site belongs. According to the technical scheme provided by the embodiment of the invention, the attribution region jurisdiction unit can be determined through the similarity degree between the two texts without being influenced by the integrity and accuracy of the geographic position data, and the effect of improving the accuracy and effectiveness of determining the attribution region jurisdiction unit is realized.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of address information processing technology, and in particular to a method, device, equipment, medium and program for determining a regional jurisdiction unit. Background Art

[0002] Address placement refers to determining the jurisdiction unit of the region corresponding to the task execution address of the pending task based on the region's affiliation and jurisdiction, so as to assign the pending task to the jurisdiction unit of the region for processing.

[0003] In the prior art, the spatial distance between the task execution address and each regional jurisdiction unit is usually determined, and the corresponding regional jurisdiction unit of the task to be processed is determined in each regional jurisdiction unit based on the spatial distance. However, in the process of implementing the present invention, it is found that the prior art has at least the following technical problems: due to the lack of complete and standard geographical location data of the regional jurisdiction unit, there is an error in determining the nearest regional jurisdiction unit to the task execution address, which affects the accuracy of the address location. Summary of the invention

[0004] The embodiments of the present invention provide a method, apparatus, device, medium and program for determining a regional jurisdiction unit, so as to determine the belonging regional jurisdiction unit by the degree of similarity between two texts, without being affected by the integrity and accuracy of the geographic location data, so as to achieve the purpose of improving the accuracy and effectiveness of determining the belonging regional jurisdiction unit.

[0005] According to one aspect of the present invention, a method for determining a regional jurisdiction unit is provided, comprising:

[0006] Determine a place attribute text corresponding to at least one preset place; wherein the place attribute text is used to describe the place attribute of the place;

[0007] Determine a semantic similarity value between an address text corresponding to a task execution address of the task to be processed and a place attribute text corresponding to the at least one place;

[0008] Based on the semantic similarity value, a belonging regional jurisdiction unit for executing the task to be processed is determined from the regional jurisdiction units to which the at least one location belongs.

[0009] According to another aspect of the present invention, a device for determining a regional jurisdiction unit is provided, the device comprising:

[0010] A place attribute text determination module, used to determine a place attribute text corresponding to at least one preset place; wherein the place attribute text is used to describe the place attribute of the place;

[0011] A semantic similarity value determination module, used to determine a semantic similarity value between an address text corresponding to a task execution address of a task to be processed and a place attribute text corresponding to the at least one place;

[0012] The module for determining the region-jurisdiction unit is used to determine the region-jurisdiction unit for executing the task to be processed from the region-jurisdiction units to which the at least one location belongs based on the semantic similarity value.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for determining the regional jurisdiction unit described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining a regional jurisdiction unit described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided. When the computer program is executed by a processor, the method for determining a regional administrative unit according to any embodiment of the present invention is implemented.

[0019] The technical solution of the embodiment of the present invention is to determine the place attribute text corresponding to at least one preset place; wherein the place attribute text is used to describe the place attribute of the place; determine the semantic similarity value between the address text corresponding to the task execution address of the task to be processed and the place attribute text corresponding to at least one place, so as to reflect the similarity of the two texts through the semantic similarity value; and, based on the semantic similarity value, determine the belonging regional jurisdiction unit for executing the task to be processed in the regional jurisdiction unit to which the at least one place belongs. Therefore, in the process of determining the belonging regional jurisdiction unit, the belonging regional jurisdiction unit is determined by the similarity between the two texts, which is not affected by the integrity and accuracy of the geographic location data, thereby achieving the effect of improving the accuracy and effectiveness of determining the belonging regional jurisdiction unit.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of a method for determining a regional jurisdiction unit provided according to an embodiment of the present invention;

[0023] Figure 2 is a schematic diagram of a geographical hierarchy provided according to an embodiment of the present invention;

[0024] Figure 3 is a flow chart of another method for determining a regional jurisdiction unit provided according to an embodiment of the present invention;

[0025] Figure 4 is a flow chart of determining a first candidate jurisdiction unit provided according to an embodiment of the present invention;

[0026] Figure 5 is a schematic diagram of a spatial range K nearest neighbors provided according to this embodiment;

[0027] Figure 6 is a flow chart of determining a second candidate jurisdiction unit provided according to an embodiment of the present invention;

[0028] Figure 7 is a structural schematic diagram of a device for determining a regional jurisdiction unit provided according to an embodiment of the present invention;

[0029] Figure 8 It is a structural diagram of an electronic device for implementing the method for determining a regional jurisdiction unit according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] 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 should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "etc." and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of user personal information involved in the technical solution of this disclosure are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information and network security.

[0033] Before introducing the technical solution, an example of the application scenario can be first explained. In practical applications, the pending task needs to be assigned to the regional jurisdiction unit of the area corresponding to the pending task for processing. The present technical solution can be applied to determine the attribution regional jurisdiction units corresponding to different pending tasks, so as to process the pending tasks through the attribution regional jurisdiction units. Exemplarily, the pending task may be at least one of a questionnaire consultation task, a troubleshooting task, and a data delivery task. The present technical solution determines the attribution regional jurisdiction unit based on the semantic similarity value between the address text and the place attribute text corresponding to the pending task, without considering the geographic location data of the regional jurisdiction unit, and is not affected by the accuracy and completeness of the geographic location data, which is conducive to improving the accuracy and effectiveness of determining the attribution regional jurisdiction unit.

[0034] Figure 1 This is a flow chart of a method for determining a regional jurisdiction unit according to an embodiment of the present invention. This embodiment is applicable to the case of determining the regional jurisdiction unit to which a task to be processed belongs. The method can be executed by a determination device for a regional jurisdiction unit, and the determination device for the regional jurisdiction unit can be implemented in the form of hardware and / or software.

[0035] like Figure 1 As shown, the method of this embodiment may specifically include:

[0036] S110: Determine a place attribute text corresponding to at least one preset place; wherein the place attribute text is used to describe the place attributes of the place.

[0037] It should be noted that the location is an actual location in the geographic space, which can be managed as an object by a regional jurisdiction unit. Exemplarily, the location may include a residential area and a point of interest, and the point of interest may include at least one of an apartment, a school, a hospital and a shopping mall. The location attributes of a location include at least one of a number, a name and a subordinate jurisdiction unit; the subordinate jurisdiction unit is the upper-level regional jurisdiction unit adjacent to the location in the geographic hierarchy data. Geographic hierarchy data is a hierarchical structure data formed by regional jurisdiction units at all levels and location according to their affiliation. The regional jurisdiction unit is the jurisdiction unit of the location. In order to more accurately locate the task to be processed in actual applications, the regional jurisdiction unit provided in this embodiment may be the upper-level regional jurisdiction unit adjacent to the location, that is, the unit that directly governs the location. Optionally, the regional jurisdiction unit includes at least one of a province, a city, a street and a community.

[0038] For a clearer and more accurate description of the location and jurisdiction, please refer to Figure 2 . Figure 2 In the figure, the rectangular box represents the regional jurisdiction unit, and the oval box represents the place. The geographical hierarchical data is a tree structure data, and the regional jurisdiction unit is divided into various levels according to the territorial jurisdiction. After arranging the regional jurisdiction units in order from high to low, the first level is the province, the second level is the city, the third level is the district, the fourth level is the street or township, and the fifth level is the community or village. For example, a province has two city-level regional jurisdiction units, City 1 and City 2, and City 1 has District 1 and District 2. City 2 can be divided into Point of Interest 1. District 2 includes Street 1, Street 2 and Point of Interest 2; Street 1 includes Community 1 and Community 2, Community 2 includes Community 1 and Community 2; Street 2 includes Point of Interest 3. Among them, provinces, cities, districts, streets and communities are all regional jurisdiction units, and communities and points of interest are places. In this embodiment, the upper-level regional jurisdiction unit adjacent to the place can be determined based on the geographical hierarchical data. For example, the upper-level regional jurisdiction unit of Community 1 and Community 2 is Community 2, and the upper-level regional jurisdiction unit of Point of Interest 3 is Street 2.

[0039] In this embodiment, at least one location can be preset in a custom setting manner according to actual application conditions. For example, the preset location is all the locations included in any province; or, the preset location is all the locations included in any city; or, the preset location is any location that meets the preset screening condition; for example, the preset screening condition is a coastal location.

[0040] In a specific implementation, the location attribute of a location includes at least one of a number, a name, and a jurisdiction unit. The implementation method of determining the location attribute text corresponding to at least one preset location includes: for each preset location, a text consisting of the number and name of the location can be used as the location attribute text; or a text corresponding to the number or name of the location can be used as the location attribute text.

[0041] Optionally, the implementation method of determining the place attribute text corresponding to at least one pre-set place also includes: for each place, based on pre-stored geographical hierarchy data, determining the jurisdiction link corresponding to the place, and generating the place attribute text corresponding to the place based on the place identifier and jurisdiction link of the place.

[0042] The geographical hierarchical data is a hierarchical structure data formed by the subordinate relationship between the various levels of regional jurisdiction units and places. The geographical hierarchical data can be divided into at least one jurisdiction link, each jurisdiction link corresponds to a place, and the jurisdiction link is the link between the root node and the last level child node in the geographical hierarchical data. For example, if the place is Figure 2 The jurisdiction link corresponding to the point of interest 1 is "province-city 2-point of interest 1". The place identifier includes the number and / or name of the place.

[0043] In a specific implementation, for each location, the location can be used as the end point of the jurisdiction link, and a link with the location as the last-level child node is determined in the geographic hierarchy data as the jurisdiction link corresponding to the location. The text consisting of the location identifier and the jurisdiction link of the location can be used as the location attribute text of the location.

[0044] This embodiment generates a place attribute text based on the place identification and jurisdiction link of the place. Therefore, the place attribute text can not only reflect the attribute information of the place, but also reflect the subordinate relationship between the regional jurisdiction unit and the place, so as to accurately determine the place's belonging regional jurisdiction unit.

[0045] S120: Determine a semantic similarity value between an address text corresponding to a task execution address of a task to be processed and a place attribute text corresponding to at least one location.

[0046] Among them, the pending tasks may be tasks that need to be assigned to the location jurisdiction unit for processing. For example, the pending tasks may include at least one of a questionnaire consultation task, a troubleshooting task, and a data delivery task. The task execution address is the address where the pending task is executed. Exemplarily, when the pending task is a questionnaire consultation task, the task execution address may be the community address of the residential community where the questionnaire needs to be answered. When the pending task is a troubleshooting task, the task execution address is the community address of the residential community where the fault is to be troubleshooted.

[0047] In a specific implementation, the semantic similarity value between the place attribute text and the address text corresponding to each place can be determined respectively. The address text is a text in natural language that describes the geographical location. The semantic similarity value is used to reflect the degree of semantic association between the place attribute text and the address text. The higher the semantic similarity value, the higher the degree of association between the place attribute text and the address text, and the more similar the address information expressed between the place attribute text and the address text; the lower the semantic similarity value, the lower the degree of association between the place attribute text and the address text, and the greater the difference in address information expressed between the place attribute text and the address text. Exemplarily, when the semantic association value is greater than a preset threshold, it can be determined that the place attribute text and the address text are texts corresponding to the same address. Those skilled in the art can set the specific value of the preset threshold according to the actual application situation. For example, the preset threshold can be 90%.

[0048] Optionally, the method of determining the semantic similarity value between the place attribute text and the address text may include: determining the semantic similarity value between the place attribute text and the address text by a cosine similarity algorithm; or determining the semantic similarity value between the place attribute text and the address text by a deep learning method.

[0049] In this embodiment, the specific implementation method of determining the semantic similarity value between the address text corresponding to the task execution address of the task to be processed and the place attribute text corresponding to at least one location and place includes: performing word segmentation processing on the address text corresponding to the task execution address to obtain at least one word element; for the place attribute text corresponding to each location and place, determining the word element importance value of each word element corresponding to the address text to the place attribute text, and determining the semantic similarity value between the address text corresponding to the task execution address and the place attribute text based on the word element importance value corresponding to each word element.

[0050] In order to fully and in detail reflect the information of the address text in the process of determining the semantic similarity value, the address text corresponding to the task execution address can be segmented to obtain at least one word element. The semantic similarity value between the address text and the place attribute text is determined by comparing each word element with the place attribute text. For example, when the address text is "×× City ×× District ××× Community", the word elements corresponding to the address text are determined to be "×× City", "×× District", "×××" and "Community".

[0051] In this embodiment, the semantic similarity value between the address text and the place attribute text can be determined based on the word-unit importance value of each word-unit to the place attribute text. The word-unit importance value reflects the correlation between the word-unit and the place attribute text. The higher the word-unit importance value, the higher the correlation between the word-unit and the place attribute text; conversely, the lower the correlation between the word-unit and the place attribute text. The way to determine the word-unit importance value of each word-unit to the place attribute text can be:

[0052] S(token i )=f(token i )×IDF(token i )

[0053] Among them, token i represents the i-th word, f(token i ) indicates an indicator function. If the token exists in the place attribute text i , then f(token i ) has a value of 1; if the token does not exist in the place attribute text i , then f(token i ) is 0. IDF(token i ) is the inverse document frequency, indicating token i The importance of each place attribute text in the corpus. Among them, IDF (token i ) is determined by:

[0054]

[0055] Among them, P represents the total number of places, Q represents the number of tokens included i The number of place attribute text, including tokens i The more place attribute text there is, the more tokens i The lower the importance of the token, the lower the importance of the token. i The higher the importance.

[0056] In a specific implementation, based on the word-gram importance value corresponding to each word-gram, the implementation method of determining the semantic similarity value between the address text corresponding to the task execution address and the place attribute text includes: determining the maximum value of the word-gram importance value of each word-gram corresponding to the address text, and using the maximum value as the semantic similarity value between the address text and the place attribute text. Alternatively, based on the word-gram importance value corresponding to each word-gram, determining the semantic similarity value between the address text corresponding to the task execution address and the place attribute text includes: determining the sum of the word-gram importance values ​​of each word-gram corresponding to the address text, and determining the sum as the semantic similarity value between the address text corresponding to the task execution address and the place attribute text.

[0057] Specifically, the sum of the word-unit importance values ​​of each word-unit is determined. The larger the sum, the greater the correlation between the place attribute text and the address text; conversely, the smaller the correlation between the place attribute text and the address text. Further, the sum can be used as the semantic similarity value between the address text and the place attribute text.

[0058] In this embodiment, the sum of the word-gram importance values ​​of each word-gram is used as the semantic similarity value, so that the relevance between each word-gram and the place attribute text can be fully reflected through the semantic similarity value.

[0059] S130. Based on the semantic similarity value, determine a regional jurisdiction unit to which at least one location belongs for executing the task to be processed.

[0060] In this embodiment, the geographical hierarchical data can be used to determine the upper-level regional jurisdiction unit adjacent to the place with the largest semantic similarity value as the belonging regional jurisdiction unit. Alternatively, the semantic location score value between the regional jurisdiction unit to which at least one place belongs and the task execution address can be determined based on the semantic similarity value, and the regional jurisdiction unit with the largest semantic location score value can be determined as the belonging regional jurisdiction unit. It should be noted that the higher the semantic location score value, the more the task execution address matches the regional jurisdiction unit; conversely, the less the task execution address matches the regional jurisdiction unit. The regional jurisdiction unit to which the place proposed in this embodiment belongs may be the upper-level regional jurisdiction unit adjacent to the place in the geographical hierarchical data.

[0061] The technical solution of the embodiment of the present invention is to determine the place attribute text corresponding to at least one preset place; wherein the place attribute text is used to describe the place attribute of the place; determine the semantic similarity value between the address text corresponding to the task execution address of the task to be processed and the place attribute text corresponding to at least one place, so as to reflect the similarity of the two texts through the semantic similarity value; and, based on the semantic similarity value, determine the belonging regional jurisdiction unit for executing the task to be processed in the regional jurisdiction unit to which the at least one place belongs. Therefore, in the process of determining the belonging regional jurisdiction unit, the belonging regional jurisdiction unit is determined by the similarity between the two texts, which is not affected by the integrity and accuracy of the geographic location data, thereby achieving the effect of improving the accuracy and effectiveness of determining the belonging regional jurisdiction unit.

[0062] Figure 3 It is a flowchart of another method for determining a regional jurisdiction unit provided in accordance with an embodiment of the present invention. Based on the above embodiment, this embodiment, before determining the belonging regional jurisdiction unit, further includes: determining the spatial distance between the task execution address and the regional jurisdiction unit to which at least one location belongs; the specific implementation method of determining the belonging regional jurisdiction unit includes determining the semantic location score value between the regional jurisdiction unit to which at least one location belongs and the task execution address: based on the spatial distance and the semantic location score value, determining the belonging regional jurisdiction unit. Among them, the explanations of the terms that are the same or corresponding to the above embodiments are not repeated here. Figure 3 As shown, the method includes:

[0063] S210: Determine a place attribute text corresponding to at least one preset place; wherein the place attribute text is used to describe the place attributes of the place.

[0064] S220: Determine the semantic similarity value between the address text corresponding to the task execution address of the task to be processed and the place attribute text corresponding to at least one place.

[0065] S230: Determine the spatial distance between the task execution address and the regional jurisdiction unit to which at least one location belongs.

[0066] Among them, the spatial distance reflects the distance between the spatial coordinates of the task execution address and the regional jurisdiction unit.

[0067] In a specific implementation, for each location, the upper-level regional jurisdiction unit adjacent to the location can be determined based on the geographic hierarchy data as the regional jurisdiction unit to which the location belongs. The geographical location area of ​​the regional jurisdiction unit to which at least one location belongs, and the coordinate position corresponding to the task execution address are determined. The geographical location area is the latitude and longitude area corresponding to the regional jurisdiction unit on the spherical coordinate system, and the coordinate position is the latitude and longitude coordinates corresponding to the task execution address on the spherical coordinate system.

[0068] In a specific implementation, the spatial distance between the task execution address and the regional jurisdiction unit is determined based on the geographical location area and the coordinate position. Optionally, the distance between each point in the geographical location area and the coordinate position can be determined, and the minimum distance among the distances corresponding to each point is used as the spatial distance between the task execution address and the regional jurisdiction unit. Alternatively, the spatial distance between the task execution address and the regional jurisdiction unit to which at least one location belongs is determined, including: performing a forward geocoding operation on the task execution address to obtain the coordinate position corresponding to the task execution address; determining the spatial distance between the coordinate position and the center point position of at least one regional jurisdiction unit. The spatial distance includes the Euclidean distance and / or Manhattan distance between the coordinate position and the center point position.

[0069] It should be noted that forward geocoding refers to converting the provided address information into corresponding longitude and latitude coordinates through the geocoding service. This encoding method is particularly important in map applications, navigation systems, location search and other scenarios because it can achieve accurate positioning of the location.

[0070] In this embodiment, the method of determining the center point position of the regional administrative unit may include: determining the geometric centroid position of the geographical location area of ​​the regional administrative unit, and using the geometric centroid position as the center point position of the regional administrative unit.

[0071] In order to determine the spatial distance more accurately, the distance between the center point position and the coordinate point position may be used as the spatial distance. Specifically, the Euclidean distance and / or Manhattan distance between the center point position and the coordinate point position may be determined as the spatial distance.

[0072] This embodiment extracts the center point position of the regional administrative unit, and uses the distance between the center point position and the coordinate position as the spatial distance, thereby simplifying the process of determining the spatial distance between the regional administrative unit and the human task execution address. In addition, the center point position can effectively represent the location status of the entire geographical location area, which is more accurate than determining the spatial distance through edge points or random points.

[0073] S240. Based on the semantic similarity value, determine the semantic placement score value between the regional jurisdiction unit to which at least one location belongs and the task execution address.

[0074] Among them, the semantic location score reflects the degree of association between the task execution address and the regional jurisdiction unit; the higher the semantic location score, the higher the degree of association between the task execution address and the regional jurisdiction unit, and the higher the probability that the pending task corresponding to the task execution address will be executed by the regional jurisdiction unit; conversely, the lower the degree of association between the task execution address and the regional jurisdiction unit, the lower the probability that the pending task corresponding to the task execution address will be executed by the regional jurisdiction unit.

[0075] In this embodiment, for each regional jurisdiction unit, the semantic location score value between the regional jurisdiction unit and the task execution address may be determined based on the semantic similarity value corresponding to the location and place governed by the regional jurisdiction unit.

[0076] Optionally, the regional jurisdiction unit includes a multi-venue jurisdiction unit and / or a single-venue jurisdiction unit; the multi-venue jurisdiction unit is a regional jurisdiction unit that governs multiple locations, and the single-venue jurisdiction unit is a regional jurisdiction unit that governs one location.

[0077] In order to accurately determine the semantic placement score value between the regional jurisdiction unit and the task execution address for different regional jurisdiction units. Specifically, based on the semantic similarity value, the specific implementation method of determining the semantic placement score value between the regional jurisdiction unit to which at least one place belongs and the task execution address includes: for each regional jurisdiction unit, selecting the semantic similarity value corresponding to any place under the jurisdiction of the regional jurisdiction unit as the semantic placement score value between the regional jurisdiction unit and the task execution address. Alternatively, the specific implementation method of determining the semantic placement score value between the regional jurisdiction unit to which at least one place belongs and the task execution address includes: for a multi-place jurisdiction unit, determining the maximum value of the semantic similarity values ​​corresponding to each place under the jurisdiction of the multi-place jurisdiction unit, and determining the maximum value as the semantic placement score value between the multi-place jurisdiction unit and the task execution address; for a single-place jurisdiction unit, determining the semantic similarity value corresponding to the place under the jurisdiction of the single-place jurisdiction unit as the semantic placement score value between the single-place jurisdiction unit and the task execution address.

[0078] It should be noted that, for the same pending task, the higher the semantic similarity value between the location attribute text of the location and the address text corresponding to the pending task, the higher the probability that the pending task will be executed by the regional jurisdiction unit to which the location belongs, that is, the higher the semantic placement score. In addition, since the tasks corresponding to each location under the jurisdiction of the multi-location jurisdiction unit must be executed by the multi-location jurisdiction unit, it can be seen that for the same pending task, whether the pending task is executed by the multi-location jurisdiction unit depends on the maximum value of the semantic similarity values ​​corresponding to the locations under the jurisdiction of the multi-location jurisdiction unit.

[0079] In order to more accurately reflect the semantic location score value corresponding to the regional jurisdiction unit, for the multi-location jurisdiction unit, the maximum value of the semantic similarity values ​​corresponding to the various locations under the jurisdiction of the multi-location jurisdiction unit can be selected, and the maximum value can be determined as the semantic location score value between the multi-location jurisdiction unit and the task execution address.

[0080] In addition, for a single-place jurisdiction unit, the semantic similarity value corresponding to the only location governed by the single-place jurisdiction unit can be directly used as the semantic placement score value between the single-place jurisdiction unit and the task execution address.

[0081] In this embodiment, specific implementation methods for determining the semantic placement score value are provided for two different situations: a multi-location jurisdiction unit and a single-location jurisdiction unit. Moreover, for a multi-location jurisdiction unit, the maximum value of the semantic similarity values ​​corresponding to each location under the jurisdiction of the multi-location jurisdiction unit is determined as the semantic placement score value, which can more accurately reflect the probability of the multi-location jurisdiction unit executing the task to be processed.

[0082] S250. Based on the spatial distance and semantic location score corresponding to at least one regional jurisdiction unit, determine the belonging regional jurisdiction unit for executing the task to be processed in the regional jurisdiction units.

[0083] Among them, the belonging regional jurisdiction unit is the upper-level regional jurisdiction unit adjacent to the location and is used to execute the tasks to be processed.

[0084] In a specific implementation, the method of determining the belonging regional jurisdiction unit includes: for each regional jurisdiction unit, based on the first preset weight of the spatial distance and the second preset weight of the semantic location score value, the weighted sum of the spatial distance and the semantic location score value corresponding to the regional jurisdiction unit can be determined, and the regional jurisdiction unit with the largest sum value is determined as the belonging regional jurisdiction unit. Alternatively, among the regional jurisdiction units, the regional jurisdiction unit with the largest spatial distance is determined as the spatial largest jurisdiction unit; the regional jurisdiction unit with the largest semantic location score value is determined as the semantic largest jurisdiction unit. If the spatial largest jurisdiction unit is the same as the semantic largest jurisdiction unit, the spatial largest jurisdiction unit can be determined as the belonging regional jurisdiction unit.

[0085] Alternatively, based on the spatial distance and semantic location score value corresponding to at least one regional jurisdiction unit, the belonging regional jurisdiction unit for executing the pending task is determined in the regional jurisdiction unit, including: determining the target jurisdiction unit in the regional jurisdiction unit to which at least one location belongs; for each target jurisdiction unit, determining the matching degree value between the target jurisdiction unit and the task execution address based on the spatial distance, semantic location score value and preset distance scaling factor corresponding to the target jurisdiction unit; based on the matching degree value corresponding to each target jurisdiction unit, determining the belonging regional jurisdiction unit for executing the pending task in the target jurisdiction unit.

[0086] Optionally, all the regional jurisdiction units to which each location belongs may be determined as the target jurisdiction unit; or, multiple location jurisdiction units in each regional jurisdiction unit may be determined as the target jurisdiction unit. Alternatively, determining the target jurisdiction unit in the regional jurisdiction unit to which at least one location belongs includes: determining a regional jurisdiction unit whose spatial distance meets a preset distance condition as the first candidate jurisdiction unit in the regional jurisdiction unit to which at least one location belongs; determining a regional jurisdiction unit whose semantic location score value meets a preset semantic condition as the second candidate jurisdiction unit in at least one regional jurisdiction unit; and determining the target jurisdiction unit from the first candidate jurisdiction unit and the second candidate jurisdiction unit.

[0087] In this embodiment, the preset distance conditions include: the spatial distance is less than the preset distance threshold; and / or the spatial distance ranking value is less than the first preset ranking threshold; the preset semantic conditions include: the semantic placement score value is greater than the preset score threshold; and / or the semantic placement score ranking value is greater than the second preset ranking threshold; wherein the spatial distance ranking value is the sequence value corresponding to the spatial distance in the first sequence obtained after sorting each spatial distance in order from small to large; the semantic placement score ranking value is the sequence value corresponding to the semantic placement score value in the second sequence obtained after sorting each semantic placement score value in order from small to large.

[0088] It should be noted that the smaller the spatial distance or the smaller the spatial distance ranking value, the closer the coordinate distance between the regional jurisdiction unit and the task execution address; the larger the semantic placement score value or the larger the semantic placement score ranking value, the greater the semantic association between the regional jurisdiction unit and the task execution address. Therefore, the preset distance condition can be set as: the spatial distance is less than the preset distance threshold, and / or the spatial distance ranking value is less than the first preset ranking threshold. Through the preset distance condition, the first candidate jurisdiction unit with a closer coordinate distance to the task execution address is screened out. And, through the preset semantic condition, the second candidate jurisdiction unit with a greater degree of semantic association with the task execution address is screened out.

[0089] In addition, those skilled in the art may determine the preset distance threshold, the first preset sorting threshold, the preset score threshold, and the second preset sorting threshold according to actual application conditions. For example, the first preset sorting threshold and the second preset sorting threshold may be determined according to the total number of areas under the jurisdiction of the region. For example, the value corresponding to one-third of the total number may be used as the first preset sorting threshold and the second preset sorting threshold.

[0090] In actual applications, when the first candidate jurisdiction unit is determined by a preset distance threshold, there may be no regional jurisdiction unit whose spatial distance is greater than the preset distance threshold. In this case, in order to ensure that the first candidate jurisdiction unit is screened out, the spatial distance ranking value of the regional jurisdiction unit can be further determined, and the regional jurisdiction unit whose spatial distance ranking value is greater than the first preset ranking threshold is used as the first candidate jurisdiction unit. In the case of determining the second candidate jurisdiction unit by a preset score threshold, when there is no regional jurisdiction unit whose semantic placement score value is greater than the preset score threshold, the semantic placement score ranking value of each regional jurisdiction unit can be further determined, and the regional jurisdiction unit whose semantic placement score ranking value is greater than the second preset ranking threshold is determined as the second candidate jurisdiction unit.

[0091] This embodiment provides a method for setting a preset distance condition and a preset semantic condition, thereby ensuring that at least one first candidate jurisdiction unit and a second candidate jurisdiction unit can be determined through the preset distance condition and the preset semantic condition.

[0092] In order to have a clearer and more complete understanding of the detailed process of determining the first candidate jurisdiction unit, please refer to Figure 4 Specifically, input the address text and the set of regional jurisdiction units. The regional jurisdiction unit in the set can be the unit to which the location belongs, or it can be a regional jurisdiction unit pre-set by technicians in this field according to the actual application. Further, forward geocoding is performed on the address text to obtain the longitude and latitude coordinates corresponding to the address text. According to the longitude and latitude coordinates, query the K closest to the task execution address in space. dThe regional jurisdiction units are used as the first candidate jurisdiction units, and the first candidate jurisdiction units form a spatial location candidate set, and the spatial location candidate set is output. d is a positive integer. For example, K d If the value of is 3, the three regional jurisdiction units with the closest spatial distance to the task execution address can be determined as the first candidate jurisdiction units.

[0093] Figure 5 is a schematic diagram of a spatial range K nearest neighbors provided according to this embodiment. Figure 5 As shown, the regional jurisdiction units include community 1, community 2, community 3, community 4 and community 5. The spatial distances between different communities are ranked as follows: Among them, is the spatial distance of community 4, is the spatial distance of community 2, is the spatial distance of community 3, is the spatial distance of community 4, is the spatial distance of community 5. d When the value of is 3, the three regional jurisdiction units closest to the longitude and latitude coordinates q corresponding to the address text corresponding to the task execution address include: Community 1, Community 2, and Community 3.

[0094] In order to have a clearer and more complete understanding of the detailed process of determining the second candidate jurisdiction unit, please refer to Figure 6 Specifically, the address text and geographic level data can be input. The address text is segmented and sliced ​​to obtain at least one word unit associated with the address text, and each word unit constitutes a word unit set. Each pre-set location is traversed and the semantic location candidate set is initialized. i represents the number of the currently traversed locations, and the initial value of i is 1.

[0095] For the currently traversed place, if i is less than or equal to the absolute value of the total number of places P, then based on the word set, determine the semantic similarity value between the address text and the place attribute text of the currently traversed place. Based on the semantic similarity value, determine the semantic placement score value of the regional jurisdiction unit to which the currently traversed place belongs. Specifically, determine whether the regional jurisdiction unit to which the currently traversed place belongs already has a semantic placement score value. If so, determine whether the semantic similarity value is greater than the existing semantic placement score value; if greater, the semantic similarity value is updated to the semantic placement score value of the regional jurisdiction unit. If less than or equal to, the current semantic placement score value is still maintained. If there is no semantic placement score value, the determined semantic similarity value is directly used as the semantic placement score value of the regional jurisdiction unit. Furthermore, the jurisdictional units of the region are recorded, and the i+1th place is traversed, that is, the next traversal is performed until i is greater than the absolute value of the total number of places P, and then the semantic placement scores corresponding to each jurisdictional unit are sorted from large to small, and the largest L jurisdictional units are determined as the second candidate jurisdictional units. The semantic placement candidate set is composed of each second candidate jurisdictional unit, and the semantic placement candidate set is output. Wherein, L is a positive integer.

[0096] In a specific implementation, after the first candidate jurisdictional unit and the second candidate jurisdictional unit are determined, the target jurisdictional unit may be determined by: determining both the first candidate jurisdictional unit and the second candidate jurisdictional unit as the target jurisdictional unit; or, determining the repeated jurisdictional unit between the first candidate jurisdictional unit and the second candidate jurisdictional unit as the target jurisdictional unit.

[0097] This embodiment provides a method for determining a target jurisdictional unit, thereby determining a regional jurisdictional unit with a greater degree of semantic association and a closer coordinate distance as the target jurisdictional unit among the regional jurisdictional units to which at least one location belongs, thereby narrowing the screening scope of the belonging regional jurisdictional unit and facilitating improving the efficiency of determining the belonging jurisdictional unit.

[0098] In this embodiment, for each target administrative unit, the formula for determining the matching degree value between the target administrative unit and the task execution address is:

[0099] Score = exp(-α*d qr )* sq r

[0100] Among them, Score represents the matching degree value, and α represents the preset distance scaling factor, which is used to adjust the influence of spatial distance on the matching degree value. The smaller the value of α is, the more sensitive the matching degree value is to the change of spatial distance. The value range of α can be (0, 1). qrRepresents the spatial distance of the target jurisdiction unit, s qr Indicates the semantic placement score value corresponding to the target jurisdiction unit. The matching degree value reflects the relevance between the target jurisdiction unit and the task execution address. The higher the matching degree value, the higher the relevance; conversely, the lower the relevance.

[0101] In a specific implementation, the target jurisdiction unit with the largest matching degree value may be determined as the belonging regional jurisdiction unit for executing the task to be processed.

[0102] In this embodiment, the matching degree value is determined by the spatial distance and the semantic location score value, so that the matching degree value takes into account the influence of the spatial distance and the influence of the semantic location score value. In addition, the target jurisdiction unit with the largest matching degree value is determined as the belonging area jurisdiction unit, so that the determined belonging area jurisdiction unit can match the task execution address in terms of both spatial distance and semantics, which is conducive to accurately and efficiently completing the execution process of the pending task.

[0103] Figure 7 1 is a schematic diagram of the structure of a device for determining a regional jurisdiction unit according to an embodiment of the present invention, and the device is used to execute the method for determining a regional jurisdiction unit provided in any of the above embodiments. The device and the method for determining a regional jurisdiction unit in the above embodiments belong to the same inventive concept, and the details not described in detail in the embodiment of the device for determining a regional jurisdiction unit can be referred to the embodiment of the method for determining a regional jurisdiction unit. Figure 7 As shown, the device comprises:

[0104] The place attribute text determination module 10 is used to determine the place attribute text corresponding to at least one preset place; wherein the place attribute text is used to describe the place attribute of the place;

[0105] A semantic similarity value determination module 11, used to determine a semantic similarity value between an address text corresponding to a task execution address of a task to be processed and a place attribute text corresponding to at least one place;

[0106] The belonging regional jurisdiction unit determination module 12 is used to determine the belonging regional jurisdiction unit for executing the task to be processed from the regional jurisdiction units to which at least one location belongs based on the semantic similarity value.

[0107] Based on any optional technical solution in the embodiments of the present invention, optionally, the device further includes:

[0108] A spatial distance determination module, used for determining the spatial distance between the task execution address and the regional jurisdiction unit to which the at least one location belongs before determining the belonging regional jurisdiction unit for executing the task to be processed from the regional jurisdiction units to which the at least one location belongs based on the semantic similarity value;

[0109] The module 12 for determining the jurisdiction unit of the region includes:

[0110] A semantic placement score value determination submodule, used to determine a semantic placement score value between a regional jurisdiction unit to which at least one location belongs and a task execution address based on a semantic similarity value;

[0111] The belonging regional jurisdiction unit determination submodule is used to determine the belonging regional jurisdiction unit for executing the task to be processed in the regional jurisdiction units based on the spatial distance and semantic location score value corresponding to at least one regional jurisdiction unit.

[0112] Based on any optional technical solution in the embodiments of the present invention, optionally, the spatial distance determination module includes:

[0113] The coordinate position determination submodule is used to perform a forward geocoding operation on the task execution address to obtain the coordinate position corresponding to the task execution address;

[0114] The spatial distance determination submodule is used to determine the spatial distance between the coordinate position and the center point position of at least one regional administrative unit; wherein the spatial distance includes the Euclidean distance and / or Manhattan distance between the coordinate position and the center point position.

[0115] Based on any optional technical solution in the embodiment of the present invention, optionally, the home region jurisdiction unit determination submodule includes:

[0116] A target jurisdiction unit determination unit, used to determine a target jurisdiction unit from among the regional jurisdiction units to which at least one location belongs;

[0117] A matching degree value determination unit, for determining, for each target jurisdiction unit, a matching degree value between the target jurisdiction unit and the task execution address based on the spatial distance, semantic location score value and preset distance scaling coefficient corresponding to the target jurisdiction unit;

[0118] The belonging area jurisdiction unit determination unit is used to determine the belonging area jurisdiction unit for executing the task to be processed in the target jurisdiction unit based on the matching degree value corresponding to each target jurisdiction unit.

[0119] Based on any optional technical solution in the embodiment of the present invention, optionally, the tag administration unit determining unit includes:

[0120] A first candidate jurisdiction unit determination subunit, configured to determine, among the regional jurisdiction units to which at least one location belongs, a regional jurisdiction unit whose spatial distance satisfies a preset distance condition as a first candidate jurisdiction unit;

[0121] A second candidate jurisdiction unit determination subunit, configured to determine, from at least one regional jurisdiction unit, a regional jurisdiction unit whose semantic location score value satisfies a preset semantic condition as a second candidate jurisdiction unit;

[0122] The target jurisdiction unit determination subunit is used to determine the target jurisdiction unit from the first candidate jurisdiction unit and the second candidate jurisdiction unit.

[0123] On the basis of any optional technical solution in the embodiments of the present invention, optionally, the preset distance condition includes: the spatial distance is less than a preset distance threshold; and / or the spatial distance ranking value is less than a first preset ranking threshold;

[0124] The preset semantic conditions include: the semantic placement score value is greater than a preset score threshold; and / or the semantic placement score ranking value is greater than a second preset ranking threshold;

[0125] Among them, the spatial distance sorting value is the sequence value corresponding to the spatial distance in the first sequence obtained after sorting each spatial distance in the order from small to large; the semantic placement score sorting value is the sequence value corresponding to the semantic placement score value in the second sequence obtained after sorting each semantic placement score value in the order from small to large.

[0126] Based on any optional technical solution in the embodiment of the present invention, optionally, the regional jurisdiction unit includes a multi-venue jurisdiction unit and / or a single-venue jurisdiction unit; the multi-venue jurisdiction unit is a regional jurisdiction unit that governs multiple locations, and the single-venue jurisdiction unit is a regional jurisdiction unit that governs one location;

[0127] The submodule for determining the semantic placement score value includes:

[0128] A first semantic location score value determination unit is used to determine, for the multi-location jurisdiction unit, the maximum value of the semantic similarity values ​​corresponding to the various locations governed by the multi-location jurisdiction unit, and determine the maximum value as the semantic location score value between the multi-location jurisdiction unit and the task execution address;

[0129] The second semantic location score value determination unit is used to determine the semantic similarity value corresponding to the place under the jurisdiction of the single place jurisdiction unit as the semantic location score value between the single place jurisdiction unit and the task execution address.

[0130] Based on any optional technical solution in the embodiment of the present invention, optionally, the place attribute text determination module 10 includes:

[0131] A jurisdiction link determination submodule is used to determine the jurisdiction link corresponding to each location based on pre-stored geographical hierarchical data, and generate a location attribute text corresponding to the location based on the location identifier and the jurisdiction link of the location;

[0132] Among them, geographical hierarchy data refers to the hierarchical structure data formed by regional jurisdiction units and locations at all levels according to their affiliation.

[0133] Based on any optional technical solution in the embodiment of the present invention, optionally, the semantic similarity value determination module 11 includes:

[0134] The word segmentation processing submodule is used to perform word segmentation processing on the address text corresponding to the task execution address to obtain at least one word unit;

[0135] The semantic similarity value determination submodule is used to determine the word-gram importance value of each word-gram corresponding to the address text to the place attribute text corresponding to each location and venue, and based on the word-gram importance value corresponding to each word-gram, determine the semantic similarity value between the address text corresponding to the task execution address and the place attribute text.

[0136] Based on any optional technical solution in the embodiments of the present invention, optionally, the semantic similarity value determination submodule includes:

[0137] The sum value determination unit is used to determine the sum value of the word-gram importance value of each word-gram corresponding to the address text, and determine the sum value as the semantic similarity value between the address text corresponding to the task execution address and the place attribute text.

[0138] The technical solution of the embodiment of the present invention is to determine the place attribute text corresponding to at least one preset place; wherein the place attribute text is used to describe the place attribute of the place; determine the semantic similarity value between the address text corresponding to the task execution address of the task to be processed and the place attribute text corresponding to at least one place, so as to reflect the similarity of the two texts through the semantic similarity value; and, based on the semantic similarity value, determine the belonging regional jurisdiction unit for executing the task to be processed in the regional jurisdiction unit to which the at least one place belongs. Therefore, in the process of determining the belonging regional jurisdiction unit, the belonging regional jurisdiction unit is determined by the similarity between the two texts, which is not affected by the integrity and accuracy of the geographic location data, thereby achieving the effect of improving the accuracy and effectiveness of determining the belonging regional jurisdiction unit.

[0139] It is worth noting that in the embodiment of the above-mentioned device for determining the regional jurisdiction unit, the various units and modules included are divided only according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0140] Figure 8 1 is a schematic diagram of the structure of an electronic device that implements the method for determining the regional jurisdiction unit of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0141] like Figure 8 As shown, the electronic device 20 includes at least one processor 21, and a memory connected to the at least one processor 21, such as a read-only memory (ROM) 22, a random access memory (RAM) 23, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 21 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 22 or the computer program loaded from the storage unit 28 to the random access memory (RAM) 23. In RAM23, various programs and data required for the operation of the electronic device 20 can also be stored. The processor 21, ROM22 and RAM23 are connected to each other through a bus 24. An input / output (I / O) interface 25 is also connected to the bus 24.

[0142] A number of components in the electronic device 20 are connected to the I / O interface 25, including: an input unit 26, such as a keyboard, a mouse, etc.; an output unit 27, such as various types of displays, speakers, etc.; a storage unit 28, such as a disk, an optical disk, etc.; and a communication unit 29, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 29 allows the electronic device 20 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0143] The processor 21 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 21 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 21 executes the various methods and processes described above, such as the determination method of the regional jurisdiction unit.

[0144] In some embodiments, the method for determining the regional jurisdiction unit may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 28. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 20 via the ROM 22 and / or the communication unit 29. When the computer program is loaded into the RAM 23 and executed by the processor 21, one or more steps of the method for determining the regional jurisdiction unit described above may be performed. Alternatively, in other embodiments, the processor 21 may be configured to perform the method for determining the regional jurisdiction unit in any other appropriate manner (e.g., by means of firmware).

[0145] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0146] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0147] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0148] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0149] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0150] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0151] This embodiment also provides a computer program product, including a computer program, which, when executed by a processor, implements the method for determining a regional jurisdiction unit as provided in any embodiment of the present application.

[0152] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0153] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0154] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a regional jurisdiction unit, characterized in that: include: Determine a place attribute text corresponding to at least one preset place; wherein the place attribute text is used to describe the place attribute of the place; Determine a semantic similarity value between an address text corresponding to a task execution address of the task to be processed and a place attribute text corresponding to the at least one place; Based on the semantic similarity value, a belonging regional jurisdiction unit for executing the task to be processed is determined from the regional jurisdiction units to which the at least one location belongs.

2. The method according to claim 1, characterized in that Before determining the belonging regional jurisdiction unit for executing the to-be-processed task from the regional jurisdiction units to which the at least one location belongs based on the semantic similarity value, the method further includes: Determine the spatial distance between the task execution address and the regional jurisdiction unit to which at least one location belongs; The determining, based on the semantic similarity value, a region jurisdiction unit for executing the task to be processed from the region jurisdiction unit to which the at least one location belongs, includes: Based on the semantic similarity value, determining a semantic location score value between the regional jurisdiction unit to which the at least one location belongs and the task execution address; Based on the spatial distance and the semantic location score value corresponding to at least one of the regional jurisdiction units, a belonging regional jurisdiction unit for executing the task to be processed is determined in the regional jurisdiction unit.

3. The method according to claim 2, characterized in that The determining of the spatial distance between the task execution address and the regional jurisdiction unit to which at least one location belongs includes: Performing a forward geocoding operation on the task execution address to obtain a coordinate position corresponding to the task execution address; Determine the spatial distance between the coordinate position and the center point position of at least one of the regional administrative units; wherein the spatial distance includes the Euclidean distance and / or the Manhattan distance between the coordinate position and the center point position.

4. The method according to claim 2, characterized in that: The determining, based on the spatial distance and the semantic location score value corresponding to at least one of the regional jurisdiction units, a belonging regional jurisdiction unit for executing the task to be processed in the regional jurisdiction unit includes: Determining a target jurisdictional unit among the regional jurisdictional units to which the at least one location belongs; For each of the target administrative units, based on the spatial distance corresponding to the target administrative unit, the semantic location score value and a preset distance scaling factor, determine a matching degree value between the target administrative unit and the task execution address; Based on the matching degree value corresponding to each target jurisdiction unit, a belonging regional jurisdiction unit for executing the task to be processed is determined in the target jurisdiction unit.

5. The method according to claim 4, characterized in that The step of determining a target jurisdiction unit from among the regional jurisdiction units to which the at least one location belongs includes: Among the regional jurisdiction units to which the at least one location belongs, determining a regional jurisdiction unit whose spatial distance satisfies a preset distance condition as a first candidate jurisdiction unit; In the at least one regional jurisdiction unit, a regional jurisdiction unit whose semantic location score value meets a preset semantic condition is determined as a second candidate jurisdiction unit; The target jurisdiction unit is determined among the first candidate jurisdiction unit and the second candidate jurisdiction unit.

6. The method according to claim 5, characterized in that The preset distance condition includes: the spatial distance is less than a preset distance threshold; and / or the spatial distance ranking value is less than a first preset ranking threshold; The preset semantic conditions include: the semantic placement score value is greater than a preset score threshold; and / or the semantic placement score ranking value is greater than a second preset ranking threshold; Among them, the spatial distance sorting value is the sequence value corresponding to the spatial distance in the first sequence obtained after sorting each spatial distance in order from small to large; the semantic placement score sorting value is the sequence value corresponding to the semantic placement score value in the second sequence obtained after sorting each semantic placement score value in order from small to large.

7. The method according to claim 2, characterized in that The regional jurisdiction unit includes a multi-venue jurisdiction unit and / or a single-venue jurisdiction unit; the multi-venue jurisdiction unit is a regional jurisdiction unit that governs multiple locations, and the single-venue jurisdiction unit is a regional jurisdiction unit that governs one location; The determining, based on the semantic similarity value, a semantic location score value between the regional jurisdiction unit to which the at least one location belongs and the task execution address includes: For the multi-venue jurisdiction unit, determine the maximum value of the semantic similarity values ​​corresponding to the various locations governed by the multi-venue jurisdiction unit, and determine the maximum value as the semantic placement score value between the multi-venue jurisdiction unit and the task execution address; For the single-place jurisdiction unit, the semantic similarity value corresponding to the location governed by the single-place jurisdiction unit is determined as the semantic placement score value between the single-place jurisdiction unit and the task execution address.

8. The method according to claim 1, characterized in that The step of determining the location attribute text corresponding to at least one preset location includes: For each of the places, based on the pre-stored geographical hierarchy data, a jurisdiction link corresponding to the place is determined, and based on the place identifier of the place and the jurisdiction link, a place attribute text corresponding to the place is generated; The geographical hierarchical data are hierarchical structure data formed by various levels of regional jurisdiction units and locations according to their affiliation.

9. The method according to claim 1, characterized in that: The step of determining the semantic similarity value between the address text corresponding to the task execution address of the task to be processed and the place attribute text corresponding to the at least one place includes: Performing word segmentation processing on the address text corresponding to the task execution address to obtain at least one word unit; For the place attribute text corresponding to each of the locations, determine the word-gram importance value of each word-gram corresponding to the address text to the place attribute text; based on the word-gram importance value corresponding to each of the word-grams, determine the semantic similarity value between the address text corresponding to the task execution address and the place attribute text.

10. The method according to claim 9, characterized in that The determining, based on the word-gram importance value corresponding to each word-gram, the semantic similarity value between the address text corresponding to the task execution address and the place attribute text comprises: The sum of the word-gram importance values ​​of each word-gram corresponding to the address text is determined, and the sum is determined as the semantic similarity value between the address text corresponding to the task execution address and the place attribute text.

11. A device for determining a regional jurisdiction unit, characterized in that: include: A place attribute text determination module, used to determine a place attribute text corresponding to at least one preset place; wherein the place attribute text is used to describe the place attribute of the place; A semantic similarity value determination module, used to determine a semantic similarity value between an address text corresponding to a task execution address of a task to be processed and a place attribute text corresponding to the at least one place; The module for determining the region-jurisdiction unit is used to determine the region-jurisdiction unit for executing the task to be processed from the region-jurisdiction units to which the at least one location belongs based on the semantic similarity value.

12. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method for determining a regional jurisdiction unit according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the method for determining the regional jurisdiction unit according to any one of claims 1-10 when executed by a processor.

14. A computer program product, comprising a computer program, which, when executed by a processor, implements the method for determining a regional jurisdiction unit according to any one of claims 1 to 10.

Images