CA3078148C

CA3078148C - Search method and apparatus, and non-temporary computer-readable storage medium

Info

Publication number: CA3078148C
Application number: CA3078148A
Authority: CA
Inventors: Rongquan Yang; Tingli Qin
Original assignee: 10353744 Canada Ltd
Priority date: 2017-01-20
Filing date: 2017-12-29
Publication date: 2024-11-12
Anticipated expiration: 2037-12-29
Also published as: TW201828122A; CA3078148A1; CN106933947B; WO2018133648A1; TWI669619B; CN106933947A

Abstract

A search method, a search apparatus, and a computer-readable storage medium. In an example, the method comprises: matching an obtained query term with first landmark materials in a preset landmark database, and determining multiple second landmark materials matching the query term; clustering the multiple second landmark materials according to physical distances among the geographical positions corresponding to the multiple second landmark materials, so as to obtain a clustering result; determining a correlation between the query term and a search intention according to the clustering result; and recalling matching third landmark materials according to the search intention.

Description

1 SEARCH METHOD AND APPARATUS, AND NON-TEMPORARY COMPUTER- READABLE STORAGE MEDIUM Cross-reference to related applications [01] This patent application claims the priority of the Chinese patent application entitled "SEARCH METHOD AND DEVICE, AND ELECTRONIC DEVICE" which was filed on January 20,2017, with the application number 201710042949.1. Technical Field [02] The present application relates to the field of search technology, and in particular, to a search method and a device, and a non-transitory computer readable storage medium. Background Art [03] In the field of search technology, when a query term is obtained, a search engine first determines the user's search intention on the basis of the query telin, and then selects a corresponding search strategy to perform the search operation according to the user's search intention. Summary of the Invention [04] The present application provides a search method in order to solve the problem of inaccurate search results in the prior art caused by the inability to identify the search intention matching the query term. [05] In order to solve the problem mentioned above, in a first aspect, an embodiment of the present application provides a search method, comprising: [06] matching an obtained query term with first landmark materials in a preset landmark database, and determining a plurality of second landmark materials matching the query term; Date Recue/Date Received 2023-08-10 CA 03078148 2020-02-07 2 [07] clustering the plurality of second landmark materials according to physical distances among geographical positions corresponding to the plurality of second landmark materials, so as to obtain a clustering result; [08] determining a correlation between the query term and a search intention according to the clustering result; [09] recalling matching third landmark materials according to the search intention. [10] In a second aspect, an embodiment of the present application provides a search device, comprising: [11] a processor and a non-transitory computer readable storage medium, [12] the non-transitory computer non-transitory computer readable storage medium stores machine executable instructions that can be executed by the processor, and the processor is caused by the machine executable instructions to perform: [13] matching an obtained query term with first landmark materials in a preset landmark database, and determining a plurality of second landmark materials matching the query term; [14] clustering the plurality of second landmark materials according to physical distances among geographical positions corresponding to the plurality of second landmark materials, so as to obtain a clustering result; [15] determining a correlation between the query term and a search intention according to the clustering result; [16] recalling matching third landmark materials according to the search intention. CA 03078148 2020-02-07 3 [17] In a third aspect, an embodiment of the present application provides a non-transitory computer readable storage medium that stores machine executable instructions. When called and executed by a processor of a network device, the machine executable instructions cause the processor to execute: [18] matching an obtained query term with first landmark materials in a preset landmark database, and determining a plurality of second landmark materials matching the query term; [19] clustering the plurality of second landmark materials according to physical distances among geographical positions corresponding to the plurality of second landmark materials, so as to obtain a clustering result; [20] determining a correlation between the query term and a search intention according to the clustering result; [21] recalling matching third landmark materials according to the search intention. [22] By means of matching an obtained query term with the landmark materials in a preset landmark database, and then clustering the landmark materials that have been successfully matched based on the distances between the landmark materials, and next determining the correlation of the landmark materials that are successfully matched according to a clustering result, in this case, if the correlation is greater than a preset threshold, the use's search intention can be determined to be a landmark search, and a material recall is further performed according to the clustering result. In this way, the search method disclosed in the embodiments of the present application solves the problem of inaccurate search results in the prior art caused by the inability to accurately identify the search intention matching the query term. The user's search intention can be determined by combining text matching and clustering methods of the present disclosure. In addition, in a case where the search result cannot be recalled when using other existing search strategies, the recall of the landmark materials at the cluster center point can be determined on the basis of the distances between the landmark materials, thereby improving the accuracy of the recall search result. CA 03078148 2020-02-07 4 Brief Description of the Drawings [23] In order to describe the technical solutions of the embodiments of the present application in a clear way, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings for the following description are only some embodiments of the present application. For a person of ordinary skill in the art, other drawings can be obtained based on these drawings without inventive skills involved. [24] FIG. 1 is a flowchart of an exemplary search method according to the present application; [25] FIG. 2 is a schematic structural diagram of the exemplary search logic according to the present application; [26] FIG. 3 is a schematic structural diagram of the exemplary search logic according to the present application; [27] FIG. 4 is a schematic diagram of a hardware structure of an exemplary search device according to the present application. Detailed Description of the Embodiments [28] The technical solutions of examples of the present disclosure will be described clearly and fully below in combination with drawings in the examples of the present disclosure. It is apparent that the described examples are merely part of examples of the present disclosure rather than all examples. Other examples achieved by those of ordinary skill in the art based on the examples in the present disclosure without paying creative work shall all fall into the scope of protection of the present disclosure. [29] The search materials corresponding to a search intention can be stored in a database. During a search process, the search intention corresponding to a query term can be determined on the CA 03078148 2020-02-07 basis of the text correlation between the query term and the search materials in the database. However, in order to ensure the accuracy of the recognition, strict text- related guidelines may be set, resulting in the inability to identify some search intentions of the user and the inability to recall the search result. [30] The embodiments of the present application disclose a search method. As shown in FIG. 1, the method includes steps 100 to 140. [31] Step 100 includes: matching an obtained query term with the landmark materials in a preset landmark database. [32] In specific implementation, the preset landmark database may include a plurality of first landmark materials, in which each of the plurality of first landmark materials can include at least: the name of a landmark, the geographical position of the landmark. The geographical position of the landmark is usually represented by the latitude and longitude coordinates of the landmark. In order to improve the robustness of text matching, the landmark name may also include corresponding short names, full names, aliases, Chinese character names, numeric names, and the like. For example, the landmark names in a landmark database may include the landmarks in the form of "Beijing Eighteenth Middle School (No. 18 Middle School)," "Peking University (Peking University)," and the like. [33] The query term can be a query term manually entered by a user through an input interface of a search platform, or it can be a keyword corresponding to a link extracted by the page program after a user clicks a link on a search platform page, or it can be a keyword selected by a user through a search channel of a search platform, such as the name of the business, the name of the landmark, and the like. The present application does not limit the way to obtain the query term. [34] After obtaining the query term, the search engine next performs a matching operation in the preset landmark database according to the obtained query term. For example, the obtained query term is fuzzy matched with the name of each one of the first landmark materials in the preset landmark database (short names, full names, aliases, Chinese character names, numeric names, CA 03078148 2020-02-07 6 and the like), and then the first landmark materials corresponding to the name of the landmark materials whose text correlation meets a preset condition are selected to be the second landmark materials that match the query term. In an example, after the fuzzy match, a plurality of second landmark materials matching the query term can be obtained. [35] Step 110 includes: clustering the second landmark materials matching the query term based on the physical distances between the geographical positions of the second landmark materials. [36] According to the geographical positions of the second landmark materials, the obtained multiple second landmark materials matching the query term are clustered, and the second landmark materials with similar distances are clustered into a cluster to obtain a plurality of clusters. A plurality of second landmark materials may be included in each cluster. In specific implementation, clustering algorithms such as K-MEANS algorithm, K-MEDOIDS algorithm, and CLARANS algorithm may be used to cluster second landmark materials matching query terms according to geographical positions. [37] In an example, the specific method for clustering the second landmark materials based on the distance between the second landmark materials is as follows: the second landmark materials matching the query term are used as cluster samples, and preset landmarks are used. The distance threshold Dth between materials is used as a constraint, and the distance between any two cluster samples is iteratively calculated and judged until all cluster samples are clustered into at least one cluster. [38] Input: second landmark materials matching the query term; [39] Features: the distance between two second landmark materials; [40] Specific algorithm: calculate the distances between every two samples of the cluster samples (second landmark materials), and take the minimum distance Dmin therefrom. If the minimum distance Dmin is within a preset distance threshold Dth, merge two samples corresponding to the minimum distance Dmin, such as samples A and B, that is, generate a cluster CA 03078148 2020-02-07 7 sample C according to the two samples A and B corresponding to the minimum distance Dmin, and then delete the two samples A and B corresponding to the minimum distance Dmin. When generating a cluster sample C (landmark materials) according to the two cluster samples A and B corresponding to the minimum distance Dmin, the latitude and longitude coordinates of the central point of the geographical positions of the two cluster samples are taken as the geographical position of the generated cluster sample C. [41] Repeat the process of calculating distance and merging samples as mentioned above until all cluster samples are clustered into one cluster, or the distance between the two closest cluster samples is greater than the preset distance threshold Dth. [42] After the foregoing clustering process, at least one cluster corresponding to the cluster samples will be obtained, where each cluster includes at least one geographical position, and the geographical position may be the geographical position of the second landmark materials, or, according to the second landmark geographical positions of materials generated, geographical positions of the cluster samples. According to the geographical positions of each cluster obtained by clustering, the landmark materials corresponding to each cluster can be determined. In specific implementation, the geographical positions in each cluster obtained by traversing the clusters can be taken, and the second landmark materials closest to the geographical positions can be taken as the landmark materials in the preset landmark database corresponding to each cluster. [43] Step 120 includes: determining the correlation between the query term and the search intention according to the clustering result. [44] The degree of aggregation of the clustering result reflects the correlation between the query term and the landmark search. In the specific implementation, the ratio of the number of corresponding second landmark materials in the largest cluster obtained by clustering to the number of second landmark materials matching the query term represents the degree of aggregation of the clustering result, which is used as the correlation between the query term and the search intention (for example, a landmark search). The correlation between the query term CA 03078148 2020-02-07 8 and the search intention is the correlation of a plurality of second landmark materials in the clustering result. In an example, the correlation between the query term and the landmark search can be determined directly based on the clustering result. The larger the number of corresponding landmark materials in the largest cluster obtained by clustering, the higher the degree of aggregation of the landmark materials that are successfully matched, the stronger the correlation. [45] In the specific implementation, each geographical position contained in one cluster obtained by clustering corresponds to a landmark material. According to the clustering result, the correlation between the query term and the landmark search can be determined in a process which includes: determining the ratio of the number of landmark materials in the largest cluster obtained by clustering to the number of the second landmark materials which are successfully matched with the query term; and then using the ratio obtained as the correlation between the query term and the landmark search. [46] Step 130 includes: if the correlation is greater than a preset threshold, determining that the user's search intention is a landmark search. [47] In an example, if the correlation of the plurality of second landmark materials which are successfully matched in the clustering result is greater than a preset threshold, it is determined that the search intention is a landmark search. [48] In the specific implementation, the preset threshold may be a value less than 1, such as 70%. If the determined correlation is greater than a preset threshold, it is determined that the user's search intention is a landmark search, otherwise, the user's search intention is not considered to be a landmark search. For example, if in the clustering result the proportion of the number of landmark materials corresponding to the geographical positions contained in the largest cluster and the number of second landmark materials matching the query term is greater than 70%, then the user's search intention is determined to be a landmark search. Otherwise, it would be considered that the user's search intention is not a landmark search. CA 03078148 2020-02-07 9 [49] In an example, the threshold can be set as a value between 60% and 90%. If the preset threshold is set to a lower value, it means that the judgment condition of clustering result is low, and the search accuracy will be reduced accordingly. If the preset threshold is set to a higher value, which indicates a high judgment condition of clustering result, the accuracy of the search will be increased correspondingly, which may result in fewer matching search results. [50] In the specific implementation, if a ratio of the number of the largest cluster obtained through the clustering, that is, the cluster containing the largest number of geographical positions (corresponding to landmark materials) to the total number of the geographical positions (equivalent to the total number of cluster samples) is greater than 70%, it would be considered that the degree of aggregation of landmarks is high. As a result, it would be determined that the user's search intention is a landmark search. Then, the landmark material closest to the central point of the largest cluster obtained by the clustering can be taken as the landmark found for the user's search. [51] Step 140 includes: if the search intention of the user is a landmark search, determining the third landmark materials according to the clustering result, and recalling the third landmark materials. [52] In specific implementation, the process of determining the third landmark materials includes: determining the central point of the geographical positions of the largest cluster obtained from the clustering process; and determining a landmark material closest to the central point of the geographical positions of the largest cluster as the third landmark material. [53] After the foregoing clustering process, a plurality of clusters corresponding to the cluster samples can be obtained. Each cluster includes a plurality of landmark materials, and each landmark material corresponds to one geographical position, and the geographical positions are the original geographical positions of the landmark materials, or the geographical positions generated on the basis of the geographical positions of landmark materials. According to the geographical positions in each cluster obtained by the clustering process, the landmark materials corresponding to each cluster can be determined. In specific implementation, the central point of CA 03078148 2020-02-07 to the geographical positions in the largest cluster obtained by clustering is firstly determined, and then the cluster samples are traversed to determine the second landmark material of the cluster samples which is closest to the central point of the geographical positions. Next, the landmark material is recalled as the third landmark material found for the user. The process of determining the central point of the geographical positions in the largest cluster obtained by clustering is a process of determining the central point of the plurality of geographical positions in the largest cluster. Moreover, the process of determining the cluster sample closest to the central point of the geographical positions is a process of respectively calculating the distances between the central point of the geographical positions and the plurality of geographical positions and determining the minimum distance. [54] If it is determined that the user's search intention is not a landmark search, a default search strategy will be used to perform a material recall. [55] By means of matching an obtained query term with the landmark materials in a preset landmark database, and then clustering the landmark materials that have been successfully matched based on the distances between the landmark materials, and next determining the correlation between the query term and landmark search according to a clustering result; in this case, if the correlation is greater than a preset threshold, the use's search intention can be determined to be a landmark search, and if the user's search intention is a landmark search, a material recall is further performed according to the clustering result. In this way, the search method disclosed in the embodiments of the present application is able to determine the search intention of the user, can accurately identify the search intention of the user, and the landmark materials at the recalled cluster central point can be determined according to the distances of the landmark materials, which can improve the accuracy of the recall search result. [56] On the basis of the method shown in FIG. 1, a search method is further disclosed in one example of the present application. In this method, the step of matching an obtained query term with first landmark materials in a preset landmark database includes: performing fuzzy match with the query term and each one of the first landmark materials in the landmark database on the basis of text correlation. CA 03078148 2020-02-07 11 [57] In specific implementation, when the obtained query term is matched with the name of each one of the first landmark materials in the preset landmark database based on text correlation, a first text correlation judgment threshold and a second text correlation judgment threshold are set in advance, in which the first text correlation judgment threshold is a text correlation judgment threshold that determines whether the query term matches the landmark name, and the second text correlation judgment threshold is a text correlation judgment threshold for determining whether the query term matches the search materials in the database in a search strategy (for example, business strategy, landmark strategy). For example, the first text correlation judgment threshold is lower than the second text correlation judgment threshold. [58] Taking the query term of "west gate of Renda" as an example, it is supposed that the existing search materials include the search materials of "Renda," a text correlation judgment threshold is set and then the text correlation between the two terms "west gate of Renda" and "Renda" is determined according to a search strategy (for example, business strategy, landmark strategy, and the like). The text correlation judgment threshold may be set to be relatively strict; for example, the text correlation judgment threshold is set to be a text correlation score of higher than 90 points; as a result, the query term "west gate of Renda" cannot be successfully matched with the search materials of "Renda." [59] In this embodiment, a relatively loose first text correlation judgment threshold may be set, for example, the first text correlation judgment threshold is set to be a text correlation score of higher than 80 points. In this case, when the query term "west gate of Renda" is used to match the landmark materials in a preset landmark database, such as "Renda," "People's University west gate barbecue restaurant," and the like, since a loose first text correlation judgment threshold is set, the query term "west gate of Renda" can be successfully matched with the landmark materials in the preset landmark database, such as "Renda," "People's University west gate barbecue restaurant," and the like. [60] In specific implementation, the query terms may be pre-processed, such as extracting the core words therefrom, and then the query term can be performed with fuzzy search with the CA 03078148 2020-02-07 12 landmark materials. Taking the query term of "west gate of Renda" as an example, the unimportant word "west gate" may be discarded, and the core word "Renda" extracted to perform matching with the landmark materials in a preset landmark database; in this case, the landmark material "Building No. 1 of the dormitory of Renda" can also be successfully matched. [61] On the basis of text correlation, fuzzy matching of the obtained query term with each landmark material in the preset landmark database can be performed so as to ensure that the recalled landmark materials meet the text correlation, as well as the basic user experience. [62] The methods provided in the present application have been described above. The device provided in the present application will be described below: [63] In reference to FIG. 4, FIG. 4 is a hardware structure diagram of a search provided by some embodiments of the present application. The search device 40 may include a processor 41 and a non-transitory computer readable storage medium 42, in which the processor 41 and the non- transitory computer readable storage medium 42 may communicate via a system bus 43; In addition, by means of reading and executing the machine-executable instructions corresponding to the search logic 20 stored in the non-transitory computer readable storage medium 42, the processor 41 can execute the search method described above. [64] The non-transitory computer readable storage medium 42 referred to herein may be any type of electronic, magnetic, optical, or other physical storage device; it may contain or store information such as executable instructions, data, and so on. For example, the non-transitory computer readable storage medium 92 may be a RAM (random access memory), a volatile memory, a non-volatile memory, a flash memory, a storage drive (such as a hard disk drive), a solid state hard disk, any type of storage disk (such as optical disk, DVD, and the like), a similar storage medium, or a combination thereof. [65] As shown in FIG. 2, functionally, the search logic 20 may include: CA 03078148 2020-02-07 13 [66] a text matching module 200, which is used for matching an obtained query term with first landmark materials in a preset landmark database, and determining a plurality of second landmark materials matching the query term; [67] a clustering module 210, which is used for clustering the plurality of second landmark materials according to physical distances among geographical positions corresponding to the plurality of second landmark materials, so as to obtain a clustering result; [68] a correlation determining module 220, which is used for determining a correlation between the query term and a search intention according to the clustering result; [69] a material recalling module 240, which is used for determining the third landmark materials according to the clustering result if the correlation is greater than a preset threshold, and then recalling the third landmark materials. [70] In an example, the search device further includes an intent identifying module 230. [71] The intention identifying module 230 is used for determining that the search intention of the user is a landmark search if the correlation is greater than a preset threshold. [72] The material recalling module 240 is used for determining the third landmark materials according to the clustering result if the correlation is greater than a preset threshold, and then recalling the third landmark materials. [73] In an example, as shown in FIG. 3, the correlation determining module 220 includes: [74] a ratio determining unit 2201, which is used for determining a ratio of a number of landmark materials corresponding to the largest cluster in the clustering result to a number of the second landmark materials; CA 03078148 2020-02-07 14 [75] a correlation determining unit 2202, which is used for using the ratio as the correlation between the query term and the landmark search. [76] Optionally, the text matching module 200 is specifically configured to perform: fuzzy match with the query term and each one of the first landmark materials in the landmark database on the basis of text correlation. [77] In an example, as shown in FIG. 3, the material recalling module 240 includes: [78] a central point determining unit 2401, which is used for determining the central point of the geographical positions of the largest cluster in the clustering result; [79] a landmark material recalling unit 2402, which is used for using a landmark material closest to the central point of the geographical positions of the largest cluster to be the third landmark material. [80] In an example, when clustering the plurality of second landmark materials, the second landmark materials are used as cluster samples. [81] The clustering module 210 is used for calculating distances between every two cluster samples of the cluster samples to obtain a minimum distance; if the minimum distance is less than the distance threshold, generating a new cluster sample according to the two cluster samples corresponding to the minimum distance, and deleting the two cluster samples corresponding to the minimum distance, wherein a geographical position corresponding to the newly generated cluster sample is the central point of the geographical positions of the two cluster samples; when remaining cluster samples are aggregated into one cluster, or distances between every two remaining cluster samples are greater than the distance threshold, the clustering is completed; otherwise, calculating again the distances between every two cluster samples of the cluster samples. = CA 03078148 2020-02-07 [82] For specific implementation of the modules of the search device disclosed in this embodiment, please refer to the relevant parts of Embodiment 1 and Embodiment 2 provided above, and details will not be provided herein again. [83] When using the search device disclosed in this embodiment, an obtained query term is matched with the landmark materials in a preset landmark database, and then the landmark materials that are successfully matched are clustered on the basis of the distances between the landmark materials, and then according to the obtained clustering result, the correlation of the landmark materials that are successfully matched is determined. Finally, if the correlation is greater than a preset threshold, the user's search intention is determined to be a landmark search, and a material recall is then performed according to the clustering result. hi this way, the search device of the present disclosure solves the problems in the prior art that the search intention matching the query term cannot be accurately identified and the search results cannot be recalled. The user's search intention can be determined by means of combining text matching and clustering methods. Hence, the user's search intention can be accurately identified. In addition, in the case where the search result cannot be recalled using other existing search strategies, it is determined that the landmark material at the clustering central point can be recalled according to the distances between the landmark materials, thereby improving the accuracy of recalled search result. [84] The present application further discloses an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, which is characterized in that when the processor executes the computer program, the search method described in the first and second embodiments of the present application can be implemented. The electronic device may be a PC, a mobile terminal, a personal digital assistant, a tablet computer, or the like. [85] The present application also discloses a computer-readable storage medium having a computer program stored thereon; when the computer program is executed by a processor, the steps of the search method according to the first and second embodiments of the present application can be implemented. CA 03078148 2020-02-07 16 [86] The embodiments in this specification are described in a progressive manner, in which each embodiment focuses on the differences thereof from other embodiments. The same or similar parts between the embodiments may refer to each other. For the device embodiments, since it is basically similar to the method embodiments, the description thereof is relatively simple. For the related contents, please refer to the description in the method embodiments. [87] The search method and device provided in the present application have been described in detail as above. Specific examples are used in the present disclosure to explain the principle and implementation of the present application. The description of these embodiments is only used to help understand the method of the present application, as well as its core ideas. At the same time, for a person of ordinary skill in the art, on the basis of the idea of the present application, there may be changes in the specific implementation and the application scope. In summary, the contents of the description should not be construed as a limitation to the present application. [88] Through the description of the above embodiments, a person skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary universal hardware platform; of course, it may also be implemented by hardware. Based on the above understanding, the above-mentioned technical solutions, in particular their essential part or their part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, and the like, and certain instructions are included therein to cause a computer device (which may be a personal computer, a server, a network device, or the like) to perform the methods described in various embodiments or certain parts of the embodiments. [89] The embodiments which describe the subject matter or functional operations in the present disclosure can be implemented in one of the following devices: a digital electronic circuit, tangible products of computer software or firmware, which include the computer hardware that contains the structures disclosed in the present disclosure or the structural equivalents thereof, or a combination of one or a plurality of the foregoing. The embodiments of the subject matter CA 03078148 2020-02-07 17 described in the present disclosure may be implemented as one or a plurality of computer programs, that is, one or a plurality of modules of computer program instructions encoded on a tangible non-transitory program carrier to be executed or controlled by a data processing device. Alternatively or additionally, the program instructions may be encoded on a manually generated propagation signal, such as an electrical, optical or electromagnetic signal generated by a machine. The signal is generated to encode and transmit the information to a suitable receiver device for execution by a data processing device. The computer storage medium may be a machine readable storage device, a machine readable storage substrate, a random or serial access memory device, or a combination of the foregoing. [90] The processes and logic flows described in the present disclosure can be performed by one or a plurality of programmable computers executing one or a plurality of computer programs, so as to perform the functions by operating on input data and generating output. The processes and logic flows may also be performed by a dedicated logic circuit such as an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit), and the device may also be implemented as a dedicated logic circuit. [91] A computer that is suitable for executing the computer program may include, for example, a general purpose and/or special purpose microprocessor, or any other type of central processing unit. Generally, the central processing unit can receive instructions and data from a read-only memory and/or a random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing the instructions and data. Usually, a computer may also include one or a plurality of mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks; alternatively, a computer may be operatively coupled to a mass storage device to receive data from or transfer data to it, or maybe both. However, a computer does not have to have such a device. In addition, the computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, a portable storage device such as a universal serial bus (USB) flash drive, and the like. CA 03078148 2020-02-07 18 [92] The computer readable medium suitable for storing computer program instructions and data include all forms of non-volatile memory, media and storage devices. Examples include semiconductor memory devices (such as EPROMs, EEPROMs, and flash devices), magnetic disks (such as internal hard disks, removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and the memory may be supplemented by, or incorporated in, certain special purpose logic circuits. [93] Although the present disclosure contains many specific implementation details, they should not be construed as limiting the scope of the present invention or the scope of protection thereof; rather, they are mainly used to describe the features of a particular embodiment of a particular invention. Certain features that are described in a plurality of embodiments in the present disclosure may also be implemented in combination in a single embodiment. On the other hand, various features described in a single embodiment may also be implemented separately in a plurality of different embodiments or in any suitable sub-combinations. In addition, while features can function in certain combinations as described above and are even so initially claimed, one or a plurality of features from the combinations to be protected may be removed from the combination in some cases. Moreover, the combinations to be protected may point to a sub-combination or a variant of a sub-combination. [94] Similarly, although the operations are depicted in a particular order in the drawings, this should not be construed as requiring those operations to be performed in the particular order shown or performed sequentially or that all illustrated operations be performed in order to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product, or packaged into a plurality of software products. [95] Thus, some specific embodiments of the subject matter have been described. Other embodiments may be within the scope of the following claims. In some cases, the actions recited CA 03078148 2020-02-07 19 in the claims may be performed in a different order and still achieve the desired results. In addition, the processes depicted in the figures are not necessarily required to be in the specific order or sequence shown in order to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous. [96] It should be noted that in the present disclosure, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation. They do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including" or any other variation thereof are intended to encompass non-exclusive inclusion such that a process, method, article, or device that includes a series of elements includes not only those elements; that is, it may also include other elements that are not explicitly listed, or it may include elements that are inherent to such a process, method, article, or device. Without more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the process, method, article, or equipment including these elements. [97] The methods and devices provided in the embodiments of the present invention have been described in detail above. Specific examples are used herein to explain the principles and implementation of the present invention. The description for the above embodiments is only used to help understand the method of the present invention and its core ideas; at the same time, for a person of ordinary skill in the art, according to the idea of the present invention, there may be changes in certain specific implementation and the application scope. In summary, the contents of the present disclosure should not be construed as a limitation to the present invention.

Claims

20 Claims: 1. An apparatus for searching, the apparatus comprising: a text matching module configured to match an obtained query term with a plurality of first landmark materials in a preset landmark database, and determining a plurality of second landmark materials matching the query term; a clustering module configured to implement a k-means algorithm, a k-medoids algorithm or a CLARANS algorithm to cluster the plurality of second landmark materials according to each physical distance between each of the plurality of second landmark materials and a geographical position corresponding to each of the plurality of second landmark materials, so as to obtain a clustering result; a correlation determining module configured to determine a correlation between the query term and a search intention according to the clustering result; and a material recalling module configured to recall a matched third landmark material that is closest to a central point of a plurality of geographical positions of a largest cluster in the clustering result.
2. The apparatus of claim 1, wherein the correlation between the query term and the search intention is a correlation among the second landmark materials in the clustering result.
3. The apparatus of any one of claims 1 to 2, wherein the apparatus further includes an intention identifying module configured to, where if a correlation among a plurality of successfully matched second landmark materials in the clustering result is greater than a preset threshold, determine that the search intention is a landmark search.
4. The apparatus of any one of claims 1 to 3, wherein the material recalling module is further configured to, where if the search intention is a landmark search, determine the matched third landmark materials according to the clustering result. Date Recue/Date Received 2024-03-01 21
5. The apparatus of any one of claims 1 to 4, wherein the correlation determining module further includes a ratio determining unit configured to determine a ratio of a number of a plurality of landmark materials corresponding to a largest cluster in the clustering result to a number of the plurality of the second landmark materials.
6. The apparatus of any one of claims 1 to 5, wherein the correlation determining module further includes a correlation determining unit configured to set the ratio as a correlation between a query term and a landmark search.
7. The apparatus of any one of claims 1 to 6, wherein the text matching module is further configured to perform a fuzzy match with the query term and each of the plurality of the first landmark materials in the preset landmark database on the basis of text correlation.
8. The apparatus of any one of claims 1 to 7, wherein the material recalling module further includes a central point determining unit configured to determine the central point of the plurality of geographical positions of the largest cluster in the clustering result.
9. The apparatus of any one of claims 1 to 8, wherein the material recalling module further includes a landmark material recalling unit configured to set a landmark material as the third landmark material.
10. The apparatus of any one of claims 1 to 9, wherein the plurality of second landmark materials is set as cluster samples when clustering the plurality of second landmark materials.
11. The apparatus of any one of claims 1 to 10, wherein the clustering module is further configured to calculate distances between every two cluster samples from cluster samples to obtain a minimum distance.
12. The apparatus of any one of claims 1 to 11, wherein the clustering module is further configured to, where if a minimum distance is less than a distance threshold, generate anew cluster sample Date Recue/Date Received 2024-03-01 22 according to two cluster samples corresponding to the minimum distance.
13. The apparatus of any one of claims 1 to 12, wherein the clustering module is further configured to, delete two cluster samples corresponding to a minimum distance.
14. The apparatus of any one of claims 1 to 13, wherein a geographical position corresponding to a newly generated cluster sample is a central point of a plurality of geographical positions of two cluster samples.
15. The apparatus of any one of claims 1 to 14, wherein the clustering module is further configured to, when remaining cluster samples are aggregated into one cluster, complete a clustering.
16. The apparatus of any one of claims 1 to 14, wherein the clustering module is further configured to, when distances between every two remaining cluster samples are greater than a distance threshold, complete a clustering.
17. The apparatus of any one of claims 1 to 16, wherein the clustering module is further configured to, where if distances between every two remaining cluster samples are less than a distance threshold, calculate again distances between every two cluster samples of cluster samples.
18. The apparatus of any one of claims 1 to 17, wherein each of the plurality of first landmark materials includes a name of a landmark.
19. The apparatus of claim 18, wherein the name of the landmark includes an abbreviation of the landmark.
20. The apparatus of any one of claims 18 to 19, wherein the name of the landmark includes a full name of the landmark.
21. The apparatus of any one of claims 18 to 20, wherein the name of the landmark includes aliases of the landmark. Date Recue/Date Received 2024-03-01 23
22. The apparatus of any one of claims 1 to 21, wherein each of the plurality of first landmark materials further includes a geographical position of a landmark.
23. The apparatus of any one of claims 1 to 22, wherein the geographical position includes a latitude and a longitude.
24. The apparatus of any one of claims 1 to 23, wherein the query term is manually inputted by a user through an input interface of a search platform.
25. The apparatus of any one of claims 1 to 23, wherein the query term is a keyword corresponding to a link extracted by a page program after a user clicks a link on a search platform page.
26. The apparatus of any one of claims 1 to 23, wherein the query term is a keyword selected by a user through a search channel of a search platform.
27. An electronic device for searching, the electronic device includes: a memory storing data; and a processor configured to: match an obtained query term with a plurality of first landmark materials in a preset landmark database, and determining a plurality of second landmark materials matching the query term; implement a k-means algorithm, a k-medoids algorithm or a CLARANS algorithm to cluster the plurality of second landmark materials according to each physical distance between each of the plurality of second landmark materials and a geographical position corresponding to each of the plurality of second Date Recue/Date Received 2024-03-01 24 landmark materials, so as to obtain a clustering result; determine a correlation between the query term and a search intention according to the clustering result; and recall a matched third landmark material that is closest to a central point of a plurality of geographical positions of a largest cluster in the clustering result.
28. The electronic device of claim 27, wherein the correlation between the query term and the search intention is a correlation among the second landmark materials in the clustering result.
29. The electronic device of any one of claims 27 to 28, wherein the processor is further configured to, where if a correlation among a plurality of successfully matched second landmark materials in the clustering result is greater than a preset threshold, determine that the search intention is a landmark search.
30. The electronic device of any one of claims 27 to 29, wherein the processor is further configured to, where if the search intention is a landmark search, determine the matched third landmark materials according to the clustering result.
31. The electronic device of any one of claims 27 to 30, wherein the processor is further configured to determine a ratio of a number of a plurality of landmark materials corresponding to a largest cluster in the clustering result to a number of the plurality of the second landmark materials.
32. The electronic device of any one of claims 27 to 31, wherein the processor is further configured to set the ratio as a correlation between a query term and a landmark search.
33. The electronic device of any one of claims 27 to 32 wherein the processor is further configured to perform a fuzzy match with the query term and each of the plurality of the first landmark materials in the preset landmark database on the basis of text correlation. Date Recue/Date Received 2024-03-01 25
34. The electronic device of any one of claims 27 to 32, wherein the processor is further configured to determine the central point of the plurality of geographical positions of the largest cluster in the clustering result.
35. The electronic device of any one of claims 27 to 34, wherein the processor is further configured to set a landmark material as the third landmark material.
36. The electronic device of any one of claims 27 to 35, wherein the plurality of second landmark materials is set as cluster samples when clustering the plurality of second landmark materials.
37. The electronic device of any one of claims 27 to 36, wherein the processor is further configured to calculate distances between every two cluster samples from cluster samples to obtain a minimum distance.
38. The electronic device of any one of claims 27 to 37, wherein the processor is further configured to, where if a minimum distance is less than a distance threshold, generate a new cluster sample according to two cluster samples corresponding to the minimum distance.
39. The electronic device of any one of claims 27 to 38, wherein the processor is further configured to, delete two cluster samples corresponding to a minimum distance.
40. The electronic device of any one of claims 27 to 39, wherein a geographical position corresponding to a newly generated cluster sample is a central point of a plurality of geographical positions of two cluster samples.
41. The electronic device of any one of claims 27 to 40, wherein the processor is further configured to, when remaining cluster samples are aggregated into one cluster, complete a clustering.
42. The electronic device of any one of claims 27 to 40, wherein the processor is further configured to, when distances between every two remaining cluster samples are greater than a distance threshold, complete a clustering. Date Recue/Date Received 2024-03-01 26
43. The electronic device of any one of claims 27 to 42, wherein the processor is further configured to, where if distances between every two remaining cluster samples are less than a distance threshold, calculate again distances between every two cluster samples of cluster samples.
44. The electronic device of any one of claims 27 to 43, wherein each of the plurality of first landmark materials includes a name of a landmark.
45. The electronic device of claim 44, wherein the name of the landmark includes an abbreviation of the landmark.
46. The electronic device of any one of claims 44 to 45, wherein the name of the landmark includes a full name of the landmark.
47. The electronic device of any one of claims 44 to 46, wherein the name of the landmark includes aliases of the landmark.
48. The electronic device of any one of claims 27 to 47, wherein each of the plurality of first landmark materials further includes a geographical position of a landmark.
49. The electronic device of any one of claims 27 to 48, wherein the geographical position includes a latitude and a longitude.
50. The electronic device of any one of claims 27 to 49, wherein the query term is manually inputted by a user through an input interface of a search platform.
51. The electronic device of any one of claims 27 to 50, wherein the query term is a keyword corresponding to a link extracted by a page program after a user clicks a link on a search platform page.
52. The electronic device of any one of claims 27 to 50, wherein the query term is a keyword Date Recue/Date Received 2024-03-01 27 selected by a user through a search channel of a search platform.
53. A non-transitory computer-readable storage medium storing computer- executable instructions that, when executed by one or more processors of an apparatus for searching, causes the one or more processors to perform the method of: matching an obtained query term with a plurality of first landmark materials in a preset landmark database, and determining a plurality of second landmark materials matching the query term; implementing a k-means algorithm, a k-medoids algorithm or a CLARANS algorithm to cluster the plurality of second landmark materials according to each physical distance between each of the plurality of second landmark materials and a geographical position corresponding to each of the plurality of second landmark materials, so as to obtain a clustering result; determining a correlation between the query term and a search intention according to the clustering result; and recalling a matched third landmark material that is closest to a central point of a plurality of geographical positions of a largest cluster in the clustering result.
54. The computer-readable storage medium of claim 53, wherein the correlation between the query term and the search intention is a correlation among the second landmark materials in the clustering result.
55. The computer-readable storage medium of any one of claims 53 to 54, wherein the computer- readable storage medium further includes the instructions for, where if a correlation among a plurality of successfiffly matched second landmark materials in the clustering result is greater than a preset threshold, determining that the search intention is a landmark search. Date Recue/Date Received 2024-03-01 28
56. The computer-readable storage medium of any one of claims 53 to 55, wherein the computer- readable storage medium further includes the instructions for, where if the search intention is a landmark search, deteimining the matched third landmark materials according to the clustering result.
57. The computer-readable storage medium of any one of claims 53 to 56, wherein the computer- readable storage medium further includes the instructions for determining a ratio of a number of a plurality of landmark materials corresponding to a largest cluster in the clustering result to a number of the plurality of the second landmark materials.
58. The computer-readable storage medium of claim 57, wherein the computer- readable storage medium further includes the instructions for setting the ratio as a correlation between a query term and a landmark search.
59. The computer-readable storage medium of any one of claims 53 to 58, wherein the computer- readable storage medium further includes the instructions for performing a fuzzy match with the query term and each of the plurality of the first landmark materials in the preset landmark database on the basis of text correlation.
60. The computer-readable storage medium of any one of claims 53 to 59, wherein the computer- readable storage medium further includes the instructions for determining the central point of the plurality of geographical positions of the largest cluster in the clustering result.
61. The computer-readable storage medium of any one of claims 53 to 60, wherein the computer- readable storage medium further includes the instructions for setting a landmark material as the third landmark material.
62. The computer-readable storage medium of any one of claims 53 to 61, wherein the computer- readable storage medium further includes the instructions for, when clustering the plurality of second landmark materials, setting the plurality of second landmark materials as cluster samples. Date Recue/Date Received 2024-03-01 29
63. The computer-readable storage medium of any one of claims 53 to 62, wherein the computer- readable storage medium further includes the instructions for calculating distances between every two cluster samples from cluster samples to obtain a minimum distance.
64. The computer-readable storage medium of any one of claims 53 to 63, wherein the computer- readable storage medium further includes the instructions for, where if a minimum distance is less than a distance threshold, generating a new cluster sample according to two cluster samples corresponding to the minimum distance.
65. The computer-readable storage medium of any one of claims 53 to 64, wherein the computer- readable storage medium further includes the instructions for, deleting two cluster samples corresponding to a minimum distance.
66. The computer-readable storage medium of any one of claims 53 to 65, wherein a geographical position corresponding to a newly generated cluster sample is a central point of a plurality of geographical positions of two cluster samples.
67. The computer-readable storage medium of any one of claims 53 to 66, wherein the computer- readable storage medium further includes the instructions for, when remaining cluster samples are aggregated into one cluster, completing a clustering.
68. The computer-readable storage medium of any one of claims 53 to 66, wherein the computer- readable storage medium further includes the instructions for, when distances between every two remaining cluster samples are greater than a distance threshold, completing a clustering.
69. The computer-readable storage medium of any one of claims 53 to 68, wherein the computer- readable storage medium further includes the instructions for, where if distances between every two remaining cluster samples are less than a distance threshold, calculating again distances between every two cluster samples of cluster samples. Date Recue/Date Received 2024-03-01 30
70. The computer-readable storage medium of any one of claims 53 to 69, wherein each of the plurality of first landmark materials includes a name of a landmark.
71. The computer-readable storage medium of claim 70, wherein the name of the landmark includes an abbreviation of the landmark.
72. The computer-readable storage medium of any one of claims 70 to 71, wherein the name of the landmark includes a full name of the landmark.
73. The computer-readable storage medium of any one of claims 70 to 72, wherein the name of the landmark includes aliases of the landmark.
74. The computer-readable storage medium of any one of claims 53 to 73, wherein each of the plurality of first landmark materials further includes a geographical position of a landmark.
75. The computer-readable storage medium of any one of claims 53 to 74, wherein the geographical position includes a latitude and a longitude.
76. The computer-readable storage medium of any one of claims 53 to 75, wherein the query term is manually inputted by a user through an input interface of a search platform.
77. The computer-readable storage medium of any one of claims 53 to 75, wherein the query term is a keyword corresponding to a link extracted by a page program after a user clicks a link on a search platform page.
78. The computer-readable storage medium of any one of claims 53 to 75, wherein the query term is a keyword selected by a user through a search channel of a search platform.
79. A method for searching, wherein the method includes: matching an obtained query term with a plurality of first landmark materials in a preset Date Recue/Date Received 2024-03-01 31 landmark database, and determining a plurality of second landmark materials matching the query term; clustering, by a k-means algorithm, a k-medoids algorithm or a CLARANS algorithm, the plurality of second landmark materials according to each physical distance between each of the plurality of second landmark materials and a geographical position corresponding to each of the plurality of second landmark materials, so as to obtain a clustering result; determining a correlation between the query term and a search intention according to the clustering result; and recalling a matched third landmark material that is closest to a central point of a plurality of geographical positions of a largest cluster in the clustering result.
80. The method of claim 79, wherein the correlation between the query term and the search intention is a correlation among the second landmark materials in the clustering result.
81. The method of any one of claims 79 to 80, wherein the method further includes, where if a correlation among a plurality of successfully matched second landmark materials in the clustering result is greater than a preset threshold, determining that the search intention is a landmark search.
82. The method of any one of claims 79 to 81, wherein the method further includes, where if the search intention is a landmark search, determining the matched third landmark materials according to the clustering result.
83. The method of any one of claims 79 to 82, wherein the method further includes determining a ratio of a number of a plurality of landmark materials corresponding to a largest cluster in the clustering result to a number of the plurality of the second landmark materials.
84. The method of claim 83, wherein the method further includes setting the ratio as a correlation Date Recue/Date Received 2024-03-01 32 between a query tenn and a landmark search.
85. The method of any one of claims 79 to 84, wherein the method further includes performing a fuzzy match with the query term and each of the plurality of the first landmark materials in the preset landmark database on the basis of text correlation.
86. The method of any one of claims 79 to 85, wherein the method further includes determining the central point of the plurality of geographical positions of the largest cluster in the clustering result.
87. The method of any one of claims 79 to 86, wherein the method further includes setting a landmark material as the third landmark material.
88. The method of any one of claims 79 to 87, wherein the method further includes, when clustering the plurality of second landmark materials, setting the plurality of second landmark materials as cluster samples.
89. The method of any one of claims 79 to 88, wherein the method further includes calculating distances between every two cluster samples from cluster samples to obtain a minimum distance.
90. The method of any one of claims 79 to 89, wherein the method further includes, where if a minimum distance is less than a distance threshold, generating a new cluster sample according to two cluster samples corresponding to the minimum distance.
91. The method of any one of claims 79 to 90, wherein the method further includes, deleting two cluster samples corresponding to a minimum distance.
92. The method of any one of claims 79 to 91, wherein a geographical position corresponding to a newly generated cluster sample is a central point of a plurality of geographical positions of two cluster samples. Date Recue/Date Received 2024-03-01 33
93. The method of any one of claims 79 to 92, wherein the method further includes, when remaining cluster samples are aggregated into one cluster, completing a clustering.
94. The method of any one of claims 79 to 92, wherein the method further includes, when distances between every two remaining cluster samples are greater than a distance threshold, completing a clustering.
95. The method of any one of claims 79 to 94, wherein the method further includes, where if distances between every two remaining cluster samples are less than a distance threshold, calculating again distances between every two cluster samples of cluster samples.
96. The method of any one of claims 79 to 95, wherein each of the plurality of first landmark materials includes a name of a landmark.
97. The method of claim 96, wherein the name of the landmark includes an abbreviation of the landmark.
98. The method of any one of claims 96 to 97, wherein the name of the landmark includes a full name of the landmark.
99. The method of any one of claims 96 to 98, wherein the name of the landmark includes aliases of the landmark.
100.The method of any one of claims 79 to 99, wherein each of the plurality of first landmark materials further includes a geographical position of a landmark.
101.The method of any one of claims 79 to 100, wherein the geographical position includes a latitude and a longitude.
102.The method of any one of claims 79 to 101, wherein the query term is manually inputted by a Date Recue/Date Received 2024-03-01 34 user through an input interface of a search platform.
103.The method of any one of claims 79 to 101, wherein the query term is a keyword corresponding to a link extracted by a page program after a user clicks a link on a search platform page.
104.The method of any one of claims 79 to 101, wherein the query term is a keyword selected by a user through a search channel of a search platform. Date Recue/Date Received 2024-03-01