Keyword identification method and device

Abstract

The invention discloses a keyword recognition method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: receiving to-be-identified data; the to-be-identified data comprises one or more to-be-identified keywords; for each to-be-identified keyword, address information corresponding to the to-be-identified keyword is acquired, and the address information comprises at least one of a delivery area, a hierarchical address and a storage coordinate; and identifying a target keyword from the one or more to-be-identified keywords according to the address information, so as to determine a to-be-checked keyword according to the target keyword. According to the embodiment, the problem keywords can be automatically recognized, the error rate of the keywords is reduced, the recognition accuracy and recognition efficiency of the problem keywords are improved, then the keyword-based order distribution accuracy is improved, the user experience is improved, and the operation cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for keyword recognition. Background Art

[0002] In the logistics order splitting scenario, order delivery efficiency can be improved by splitting the logistics orders. Among them, the keyword matching strategy is widely used in the logistics order splitting scenario. Keywords can be manually added through the page or generated based on the address library.

[0003] However, manually added keywords may not have geographic entity meaning. If similar address locations are corrected in batches, the keyword positions of the keywords generated by the address database will not change, resulting in low order accuracy. Therefore, keywords need to be verified. However, if all keywords are manually verified and corrected, the verification cost and efficiency will be low. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method and device for keyword recognition, which can automatically identify problem keywords, reduce the error rate of keywords, improve the recognition accuracy and efficiency of problem keywords, thereby improving the accuracy of keyword-based order splitting, improving user experience, and reducing operating costs.

[0005] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for keyword recognition is provided, comprising:

[0006] Receiving data to be identified; the data to be identified includes one or more keywords to be identified;

[0007] For each keyword to be identified, obtaining address information corresponding to the keyword to be identified, the address information including at least one of a delivery area, a hierarchical address, and a storage coordinate;

[0008] According to the address information, a target keyword is identified from the one or more keywords to be identified, so as to determine a keyword to be checked according to the target keyword.

[0009] Optionally, the address information includes the delivery area, and identifying a target keyword from the one or more keywords to be identified includes:

[0010] Filtering out a first keyword that meets a preset condition from the one or more keywords to be identified;

[0011] determining a road corresponding to the first keyword;

[0012] Determining whether the road exceeds the delivery area;

[0013] In a case where the road exceeds the delivery area, the first keyword is determined to be the target keyword.

[0014] Optionally, the address information includes the delivery area, and identifying a target keyword from the one or more keywords to be identified includes:

[0015] Acquire each delivery address corresponding to the delivery area and containing the keyword to be identified;

[0016] Determining the quantity of each delivery address;

[0017] When the number of the delivery addresses is less than or equal to a preset threshold, the keyword to be identified is determined to be the target keyword.

[0018] Optionally, the address information includes the hierarchical address, and identifying a target keyword from the one or more keywords to be identified includes:

[0019] Concatenate the keyword to be identified with the hierarchical address to obtain a concatenated address;

[0020] Sending an address diagnosis request to an address diagnosis service according to the concatenated address, and receiving a diagnosis result returned by the address diagnosis service based on the address diagnosis request;

[0021] In the case where the diagnosis result indicates that the concatenated address is an incorrect address, it is determined that the keyword to be identified is the target keyword.

[0022] Optionally, the address information includes the hierarchical address and the storage coordinates, and identifying the target keyword from the one or more keywords to be identified includes:

[0023] Concatenate the keyword to be identified with the hierarchical address to obtain a concatenated address, and determine the coordinates of the concatenated address;

[0024] Acquire each delivery address that matches the keyword to be identified, and determine the center point coordinates of each delivery address;

[0025] In the case where the coordinates of the splicing address, the storage coordinates and the center point coordinates meet preset conditions, the keyword to be identified is determined to be the target keyword.

[0026] Optionally, the preset condition is:

[0027] The distance between the coordinates of the splicing address and the stored coordinates is greater than a first preset distance, the distance between the center point coordinates and the stored coordinates is greater than the first preset distance, and the distance between the coordinates of the splicing address and the center point coordinates is less than a second preset distance.

[0028] Optionally, determining the keywords to be checked according to the target keywords includes:

[0029] Obtain the number of calls of the target keyword within a preset time;

[0030] When the number of calls is less than or equal to a preset number threshold, it is determined that the target keyword is not the keyword to be checked.

[0031] According to another aspect of an embodiment of the present invention, there is provided a device for keyword recognition, comprising:

[0032] A receiving module receives data to be identified; the data to be identified includes one or more keywords to be identified;

[0033] An acquisition module, for each keyword to be identified, acquires address information corresponding to the keyword to be identified, wherein the address information includes at least one of a delivery area, a hierarchical address, and a storage coordinate;

[0034] The identification module identifies a target keyword from the one or more keywords to be identified according to the address information, so as to determine a keyword to be checked according to the target keyword.

[0035] According to another aspect of an embodiment of the present invention, there is provided an electronic device, including:

[0036] one or more processors;

[0037] a storage device for storing one or more programs,

[0038] When the one or more programs are executed by the one or more processors, the one or more processors implement the keyword recognition method provided by the present invention.

[0039] According to another aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the method for keyword recognition provided by the present invention is implemented.

[0040] An embodiment of the above invention has the following advantages or beneficial effects: the keyword identification method of the embodiment of the present invention receives data to be identified including one or more keywords to be identified, and then obtains address information corresponding to the keyword to be identified for each keyword to be identified, identifies the target keyword from the one or more keywords to be identified according to at least one of the delivery area, hierarchical address and storage coordinates, and determines the keyword to be checked according to the target keyword. The method uses multi-source data to identify problem keywords according to the delivery area, hierarchical address and storage coordinates, determines the keywords to be checked according to the problem keywords, and manually checks the keywords to be checked. The method can automatically identify problem keywords, reduce the error rate of keywords, and improve the recognition accuracy and efficiency of problem keywords, thereby improving the accuracy of keyword-based order distribution, improving user experience, and reducing operating costs.

[0041] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0043] Figure 1 is a schematic diagram of the main process of a keyword identification method according to an embodiment of the present invention;

[0044] Figure 2 is a schematic diagram of the main process of another keyword identification method according to an embodiment of the present invention;

[0045] Figure 3 is a flowchart of a keyword recognition method according to an embodiment of the present invention;

[0046] Figure 4 is a schematic diagram of main modules of a device for keyword recognition according to an embodiment of the present invention;

[0047] Figure 5 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0048] Figure 6 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0050] Figure 1 FIG. 1 is a schematic diagram of the main process of a keyword recognition method according to an embodiment of the present invention. Figure 1 As shown, the keyword identification method includes the following steps:

[0051] Step S101: receiving data to be identified; the data to be identified includes one or more keywords to be identified;

[0052] Step S102: for each keyword to be identified, obtaining address information corresponding to the keyword to be identified, the address information including at least one of a delivery area, a hierarchical address, and a storage coordinate;

[0053] Step S103: According to the address information, a target keyword is identified from one or more keywords to be identified, so as to determine a keyword to be checked according to the target keyword.

[0054] In an embodiment of the present invention, the keyword identification method is suitable for identifying problematic keywords used for keyword matching strategies in logistics order distribution scenarios to improve the efficiency and accuracy of logistics order distribution.

[0055] In an embodiment of the present invention, firstly, data to be identified is received, such as text data to be identified, and the data to be identified may include one or more keywords to be identified, and the keywords to be identified may be manually added, or may be obtained according to the delivery address of the order, such as words with geographical entity meaning cut out from the delivery address of the order, and the keywords to be identified are used in the order splitting scenario based on the keyword matching strategy. For each keyword to be identified, the address information corresponding to the keyword to be identified is obtained, and the address information may include at least one of the delivery area, the hierarchical address and the storage coordinates. The delivery area of ​​each keyword to be identified is the delivery area or delivery range of the site or business department corresponding to the keyword to be identified. The hierarchical address of each keyword to be identified may be the address of one or more hierarchies corresponding to the keyword to be identified, such as the hierarchical address may be a fourth-level address, such as XX Street, XX District, XX City, XX Province, or a fourth-level address and a detailed address, and the detailed address is a more detailed address under the fourth-level address, such as the detailed address may be XX Road, XX Street, etc., and the keyword to be identified may be XX Hotel, XX Community, etc. The storage coordinates of each keyword to be identified are the latitude and longitude coordinates of the keyword to be identified on the map. The keywords to be identified and the address information corresponding to the keywords to be identified are stored in the database, so as to obtain the address information of the keywords to be identified from the database. When the logistics order is split, if the delivery address of the order contains the keywords under the fourth-level address, the delivery address is assigned to the delivery area corresponding to the keyword.

[0056] Then, based on the address information, i.e., at least one of the delivery area, hierarchical address and storage coordinates, the target keyword, i.e., the problem keyword, is identified from one or more keywords to be identified, so that the keyword to be verified can be determined based on the target keyword, so as to perform manual verification on the keyword to be verified, thereby narrowing the scope of manual verification, improving the efficiency of keyword recognition, and reducing labor costs.

[0057] In the embodiment of the present invention, the address information includes a delivery area, and identifying a target keyword from one or more keywords to be identified includes:

[0058] Filtering out a first keyword that meets a preset condition from one or more keywords to be identified;

[0059] determining a road corresponding to the first keyword;

[0060] Determine whether the road exceeds the delivery area;

[0061] In the case where the road exceeds the delivery area, the first keyword is determined to be the target keyword.

[0062] In an embodiment of the present invention, the keyword to be identified may be a keyword with a larger scope, that is, the delivery range of the keyword to be identified across sites or sales departments, that is, the delivery area, which is generally XX Road, XX Street, and may be caused by manual maintenance. For example, the keyword "XX South Street" is maintained in Sales Department A, and XX South Street is across Sales Departments A and B, so "XX South Street" is a keyword with a larger scope. The address information of the keyword to be identified may include the delivery area. When the target keyword is identified from one or more keywords to be identified, the first keyword can be firstly screened out according to a preset condition. The preset condition can be that the keyword ends with a preset word. For example, the preset word can be a street, road, avenue, etc., that is, the first keyword is a keyword that ends with a preset word, such as the first keyword is XX Avenue. Then the first keyword is matched with each road to determine the road corresponding to the first keyword. The road may include the road name. Thus, the road name corresponding to the first keyword can be determined through matching. Then, through GIS (Geographic Information System) spatial analysis, it is determined whether the road name corresponding to the first keyword exceeds the delivery area of ​​the keyword to be identified, that is, whether the road name crosses sites, that is, whether it crosses the delivery range of the business department. If it crosses the delivery range of the business department, it means that the range of the keyword to be identified is too large, and the keyword to be identified is determined to be the target keyword, that is, the problem keyword; if it does not cross the delivery range of the business department, that is, the keyword to be identified corresponds to the delivery range of one business department, it means that the range of the keyword to be identified is normal, and it is determined that the keyword to be identified is not the target keyword.

[0063] In the embodiment of the present invention, the address information includes a delivery area, and identifying a target keyword from one or more keywords to be identified includes:

[0064] Obtaining each delivery address corresponding to the delivery area and containing the keyword to be identified;

[0065] Determine the quantity of each delivery address;

[0066] When the number of each delivery address is less than or equal to a preset threshold, the keyword to be identified is determined to be a target keyword.

[0067] In an embodiment of the present invention, the delivery address based on the order can generate keywords by itself. The delivery addresses may be manually maintained in batches to the wrong business department, so the self-generated keywords correspond to the wrong business department. Subsequently, the delivery address of the wrong location is manually maintained to the correct business department, and the keywords are still maintained in the wrong business department, so it is necessary to identify this part of the problem keywords. The address information of the keyword to be identified may include the delivery area of ​​the keyword to be identified. When the target keyword is identified from one or more keywords to be identified, or when the road does not exceed the delivery area, the number of each delivery address containing the keyword to be identified in the delivery area is obtained according to the delivery area of ​​the keyword to be identified, and it is determined whether the number of each delivery address is less than or equal to the preset threshold. If it is less than or equal to the preset threshold, it is determined that the keyword to be identified is the target keyword. If it is greater than the preset threshold, it is determined that the keyword to be identified is not the target keyword. The preset threshold can be set by default, such as 0, that is, the number of delivery addresses containing the keyword in the site where the keyword is located is counted. If the number is 0, the keyword is a problem keyword.

[0068] In an embodiment of the present invention, each site or business department has a corresponding address library, which includes all addresses within the delivery range (i.e., delivery area) corresponding to the site or business department, each address includes a four-level address and a detailed address, and the detailed address may include a keyword. When a target keyword is identified from one or more keywords to be identified, the number of addresses containing the keyword to be identified within the delivery range of the site where the keyword to be identified is located can be obtained, and it is determined whether the number of addresses containing the keyword to be identified is less than or equal to a preset threshold. If not, the keyword to be identified is the target keyword, that is, the keyword to be identified is a problem keyword without an address library, that is, the keyword to be identified is in the wrong site or business department.

[0069] In the embodiment of the present invention, Figure 2 As shown, identifying a target keyword from one or more keywords to be identified includes:

[0070] Step S201: concatenate the keyword to be identified with the hierarchical address to obtain a concatenated address;

[0071] Step S202: sending an address diagnosis request to an address diagnosis service according to the concatenated address, and receiving a diagnosis result returned by the address diagnosis service based on the address diagnosis request;

[0072] Step S203: when the diagnosis result indicates that the concatenated address is an incorrect address, determining that the keywords to be identified are target keywords.

[0073] In the embodiment of the present invention, since keywords are generally points of interest, i.e., AOIs (Areas Of Interests), with geographical significance, such as XX Park, XX Hotel, XX Community, etc., some keywords are irrelevant to the geographical location and are false keywords, and these keywords need to be identified. When the target keyword is identified from one or more keywords to be identified, or when the number of each delivery address is greater than a preset threshold, for each keyword to be identified, the keyword to be identified is spliced ​​with the hierarchical address of the keyword to be identified to obtain a spliced ​​address; then an address diagnosis request is sent to the address diagnosis service, i.e., the address diagnosis service is called, and the spliced ​​address is diagnosed using the address diagnosis service to obtain a diagnosis result. If the diagnosis result indicates that the spliced ​​address is an incorrect address, the keyword to be identified is determined to be a target keyword, i.e., a keyword irrelevant to the geographical location. If the diagnosis result indicates that the spliced ​​address is a correct address, it is determined that the keyword to be identified is not a target keyword. Among them, the address diagnosis service is a service (or program) used to diagnose whether the delivery address of the user's order is a deliverable and receivable address, and to verify whether the delivery address is a real and valid address. The address diagnosis service can provide services in the form of a jsf (a distributed service framework) interface.

[0074] In the embodiment of the present invention, the address information includes a hierarchical address and a storage coordinate, and identifying a target keyword from one or more keywords to be identified includes:

[0075] Concatenate the keyword to be identified with the hierarchical address to obtain a concatenated address, and determine the coordinates of the concatenated address;

[0076] Obtaining each delivery address that matches the keyword to be identified, and determining the center point coordinates of each delivery address;

[0077] When the coordinates of the splicing address, the storage coordinates and the center point coordinates meet the preset conditions, the keyword to be identified is determined to be the target keyword.

[0078] In an embodiment of the present invention, the problem keyword may also be a keyword with a wrong location. When the target keyword is identified from one or more keywords to be identified, or when the diagnosis result indicates that the spliced ​​address is the correct address, the geocoding service is called to determine the coordinates of the spliced ​​address, such as A (X1, Y1), wherein the geocoding service is a service for obtaining the corresponding longitude and latitude position coordinates according to the address, and the service can be provided through the jsf interface, and the address can be a four-level address and a detailed address, or a four-level address and a keyword; then, each delivery address matching the keyword to be identified is obtained, and each delivery address can be a delivery address within the delivery area containing the keyword to be identified, and then each delivery address is clustered to obtain the center point coordinates of each delivery address, such as B (X2, Y2), and the storage coordinates C (X3, Y3) of the keyword to be identified are obtained, and then A, B and C meet the preset conditions. If they meet, it is determined that the keyword to be identified is the target keyword, that is, the keyword with a wrong location. If not, it is determined that the keyword to be identified is not the target keyword.

[0079] In the embodiment of the present invention, after the center point coordinates of each delivery address are determined, the keyword to be identified is determined to be the target keyword when at least two of the coordinates of the spliced ​​address, the storage coordinates and the center point coordinates meet preset conditions.

[0080] In an embodiment of the present invention, the preset condition may be that the distance between the coordinates of the splicing address and the stored coordinates or the distance between the center point coordinates and the stored coordinates is greater than a first preset distance; the preset condition may also be that the distance between the coordinates of the splicing address and the stored coordinates or the distance between the center point coordinates and the stored coordinates is greater than the first preset distance, and the distance between the coordinates of the splicing address and the center point coordinates is less than a second preset distance.

[0081] In the embodiment of the present invention, the preset condition may be: the distance between the coordinates of the splicing address and the stored coordinates is greater than the first preset distance, the distance between the center point coordinates and the stored coordinates is greater than the first preset distance, and the distance between the coordinates of the splicing address and the center point coordinates is less than the second preset distance. Wherein, the distance is a straight-line distance, the first preset distance is greater than the second preset distance, and the first preset distance and the second preset distance can be customized, such as the first preset distance is 1000 meters, and the second preset distance is 500 meters, that is, if the straight-line distance between A, B and C is greater than 1000 meters, and the straight-line distance between B and C is greater than 500 meters, it means that the position of the keyword to be identified is wrong and it is determined to be the target keyword.

[0082] In the embodiment of the present invention, determining the keywords to be checked according to the target keywords includes:

[0083] Get the number of calls of the target keyword within the preset time;

[0084] When the number of calls is less than or equal to the preset number threshold, it is determined that the target keyword is not a keyword to be checked.

[0085] In an embodiment of the present invention, after the target keyword is identified from one or more keywords to be identified, the target keyword can be manually checked, or the keyword to be checked can be further determined based on the target keyword, and the keyword to be checked can be manually checked, thereby reducing the scope of manual checking. When determining the keyword to be checked based on the target keyword, the number of calls to the target keyword within a preset time can be obtained, that is, the number of times the delivery address of the order successfully matches the target keyword and the delivery area corresponding to the target keyword is obtained, that is, the number of times the target keyword is used to split the order. If the number of calls is less than or equal to the preset number threshold, no manual check is required and it is not a keyword to be checked. If the number of calls is greater than the preset number threshold, it is a keyword to be checked and manual check is required to improve the recognition accuracy of the problem keyword.

[0086] Figure 3 The present invention is a flowchart of a keyword recognition method according to an embodiment of the present invention. Input the keyword to be recognized; determine whether the scope of the keyword to be recognized is too large, that is, determine the road that matches the keyword to be recognized, and determine whether the road crosses the delivery range of the sales department through GIS spatial analysis; if so, it means that the scope of the keyword to be recognized is too large, and the keyword to be recognized is a problem keyword; if not, determine whether the site where the keyword to be recognized is located has a delivery address containing the keyword to be recognized; if not, the keyword to be recognized is a problem keyword; if yes, determine whether the keyword to be recognized represents geographic information, that is, splice the keyword to be recognized with the fourth-level address, call the address diagnosis service for diagnosis, and determine whether it is a deliverable, real and valid address according to the diagnosis result, if not, the keyword to be recognized is a problem keyword, if yes, determine whether the location of the keyword to be recognized is correct, that is, whether the storage coordinates of the keyword to be recognized are correct, if not, the keyword to be recognized is a problem keyword, if yes, it is not a problem keyword, and the process ends.

[0087] The keyword identification method of the embodiment of the present invention receives data to be identified including one or more keywords to be identified, then obtains address information corresponding to the keyword to be identified for each keyword to be identified, identifies a target keyword from the one or more keywords to be identified based on at least one of a delivery area, a hierarchical address, and a storage coordinate, and determines a keyword to be checked based on the target keyword. The method uses multi-source data to identify problem keywords based on the delivery area, hierarchical address, and storage coordinates, determines the keywords to be checked based on the problem keywords, and manually checks the keywords to be checked. The method can automatically identify problem keywords, reduce the error rate of keywords, and improve the recognition accuracy and efficiency of problem keywords, thereby improving the accuracy of keyword-based order distribution, improving user experience, and reducing operating costs.

[0088] According to another aspect of the embodiment of the present invention, Figure 4 As shown, a device 400 for keyword recognition is provided, comprising:

[0089] The receiving module 401 receives data to be identified; the data to be identified includes one or more keywords to be identified;

[0090] An acquisition module 402, for each keyword to be identified, acquires address information corresponding to the keyword to be identified, the address information including at least one of a delivery area, a hierarchical address, and a storage coordinate;

[0091] The identification module 403 identifies a target keyword from one or more keywords to be identified according to the address information, so as to determine a keyword to be checked according to the target keyword.

[0092] In an embodiment of the present invention, the address information includes a delivery area, and the identification module 403 is further used to: filter out a first keyword that meets a preset condition from one or more keywords to be identified; for each first keyword, determine the road corresponding to the first keyword; determine whether the road exceeds the delivery area; and if the road exceeds the delivery area, determine the first keyword as a target keyword.

[0093] In an embodiment of the present invention, the address information includes a delivery area, and the identification module 403 is further used to: obtain each delivery address corresponding to the delivery area and containing the keyword to be identified; determine the number of each delivery address; when the number of each delivery address is less than or equal to a preset threshold, determine that the keyword to be identified is a target keyword.

[0094] In an embodiment of the present invention, the address information includes a hierarchical address, and the identification module 403 is further used to: splice the keyword to be identified with the hierarchical address to obtain a spliced ​​address; send an address diagnosis request to the address diagnosis service according to the spliced ​​address, and receive the diagnosis result returned by the address diagnosis service based on the address diagnosis request; when the diagnosis result indicates that the spliced ​​address is an incorrect address, determine that the keyword to be identified is a target keyword.

[0095] In an embodiment of the present invention, the address information includes a hierarchical address and storage coordinates, and the identification module 403 is further used to: splice the keyword to be identified with the hierarchical address to obtain a spliced ​​address, and determine the coordinates of the spliced ​​address; obtain each delivery address matching the keyword to be identified, and determine the center point coordinates of each delivery address; when the coordinates of the spliced ​​address, the storage coordinates and the center point coordinates meet preset conditions, determine that the keyword to be identified is a target keyword.

[0096] In an embodiment of the present invention, the preset conditions are: the distance between the coordinates of the splicing address and the stored coordinates is greater than the first preset distance, the distance between the center point coordinates and the stored coordinates is greater than the first preset distance, and the distance between the coordinates of the splicing address and the center point coordinates is less than the second preset distance.

[0097] In the embodiment of the present invention, the identification module 403 is further used to: obtain the number of calls of the target keyword within a preset time; when the number of calls is less than or equal to a preset number threshold, determine that the target keyword is not a keyword to be checked.

[0098] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the keyword recognition method provided by the present invention.

[0099] According to another aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the method for keyword recognition provided by the present invention is implemented.

[0100] Figure 5 An exemplary system architecture 500 is shown to which the method or apparatus for keyword identification according to an embodiment of the present invention may be applied.

[0101] like Figure 5As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0102] Users can use terminal devices 501, 502, 503 to interact with server 505 through network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0103] The terminal devices 501 , 502 , and 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0104] The server 505 may be a server that provides various services, such as a backend management server (only an example) that provides support for shopping websites browsed by users using the terminal devices 501, 502, and 503. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.

[0105] It should be noted that the keyword recognition method provided in the embodiment of the present invention is generally executed by the server 505 , and accordingly, the keyword recognition device is generally set in the server 505 .

[0106] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0107] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 of a terminal device suitable for implementing an embodiment of the present invention. Figure 6 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0108] like Figure 6As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0109] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0110] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0111] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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 above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0112] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0113] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, they may be described as: a processor includes a receiving module, an acquisition module, and an identification module. The names of these modules do not constitute limitations on the modules themselves in some cases. For example, the receiving module may also be described as a "module for receiving data to be identified."

[0114] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: receiving data to be identified; the data to be identified includes one or more keywords to be identified; for each keyword to be identified, obtaining address information corresponding to the keyword to be identified, the address information includes at least one of a delivery area, a hierarchical address, and a storage coordinate; according to the address information, identifying a target keyword from one or more keywords to be identified, so as to determine a keyword to be checked according to the target keyword.

[0115] According to the technical solution of the embodiment of the present invention, the keyword identification method of the embodiment of the present invention receives data to be identified including one or more keywords to be identified, and then obtains address information corresponding to the keyword to be identified for each keyword to be identified, identifies the target keyword from the one or more keywords to be identified according to at least one of the delivery area, hierarchical address and storage coordinates, and determines the keyword to be checked according to the target keyword. The method uses multi-source data to identify problem keywords according to the delivery area, hierarchical address and storage coordinates, determines the keywords to be checked according to the problem keywords, and manually checks the keywords to be checked. The method can automatically identify problem keywords, reduce the error rate of keywords, and improve the recognition accuracy and efficiency of problem keywords, thereby improving the accuracy of keyword-based order distribution, improving user experience, and reducing operating costs.

[0116] 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 may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for keyword recognition, characterized in that: include: Receiving data to be identified; the data to be identified includes one or more keywords to be identified; For each keyword to be identified, obtaining address information corresponding to the keyword to be identified, the address information including at least one of a delivery area, a hierarchical address, and a storage coordinate; According to the address information, a target keyword is identified from the one or more keywords to be identified, so as to determine a keyword to be checked according to the target keyword.

2. The method according to claim 1, characterized in that The address information includes the delivery area, and identifying a target keyword from the one or more keywords to be identified includes: Filtering out a first keyword that meets a preset condition from the one or more keywords to be identified; For each first keyword, determining a road corresponding to the first keyword; Determining whether the road exceeds the delivery area; In a case where the road exceeds the delivery area, the first keyword is determined to be the target keyword.

3. The method according to claim 1, characterized in that The address information includes the delivery area, and identifying a target keyword from the one or more keywords to be identified includes: Acquire each delivery address corresponding to the delivery area and containing the keyword to be identified; Determining the quantity of each delivery address; When the number of the delivery addresses is less than or equal to a preset threshold, the keyword to be identified is determined to be the target keyword.

4. The method according to claim 1, characterized in that: The address information includes the hierarchical address, and identifying a target keyword from the one or more keywords to be identified includes: Concatenate the keyword to be identified with the hierarchical address to obtain a concatenated address; Sending an address diagnosis request to an address diagnosis service according to the concatenated address, and receiving a diagnosis result returned by the address diagnosis service based on the address diagnosis request; In the case where the diagnosis result indicates that the concatenated address is an incorrect address, it is determined that the keyword to be identified is the target keyword.

5. The method according to claim 1, characterized in that The address information includes the hierarchical address and the storage coordinates, and identifying a target keyword from the one or more keywords to be identified includes: Concatenate the keyword to be identified with the hierarchical address to obtain a concatenated address, and determine the coordinates of the concatenated address; Acquire each delivery address that matches the keyword to be identified, and determine the center point coordinates of each delivery address; In the case where the coordinates of the splicing address, the storage coordinates and the center point coordinates meet preset conditions, the keyword to be identified is determined to be the target keyword.

6. The method according to claim 5, characterized in that The preset conditions are: The distance between the coordinates of the splicing address and the stored coordinates is greater than a first preset distance, the distance between the center point coordinates and the stored coordinates is greater than the first preset distance, and the distance between the coordinates of the splicing address and the center point coordinates is less than a second preset distance.

7. The method according to claim 1, characterized in that Determine the keywords to be checked according to the target keywords, including: Obtain the number of calls of the target keyword within a preset time; When the number of calls is less than or equal to a preset number threshold, it is determined that the target keyword is not the keyword to be checked.

8. A device for keyword recognition, characterized in that: include: A receiving module receives data to be identified; The data to be identified includes one or more keywords to be identified; An acquisition module, for each keyword to be identified, acquires address information corresponding to the keyword to be identified, wherein the address information includes at least one of a delivery area, a hierarchical address, and a storage coordinate; The identification module identifies a target keyword from the one or more keywords to be identified according to the address information, so as to determine a keyword to be checked according to the target keyword.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images