Retrieval method and knowledge information construction method, device and equipment, and storage medium

Abstract

The present disclosure provides a retrieval method and a knowledge information construction method, device and equipment, and a storage medium, relates to the technical field of artificial intelligence, in particular to the fields of knowledge map, intelligent search, knowledge graph and the like. The specific implementation scheme is: receiving retrieval information, wherein the retrieval information includes a point of interest upper keyword, the point of interest upper keyword represents the general term of a plurality of map points of interest, and the map point of interest is used to represent a place in a geographic information system; determining a target map point of interest corresponding to the retrieval information based on the correspondence between the point of interest upper keyword and the map point of interest; obtaining place knowledge information corresponding to the target map point of interest based on the correspondence between the map point of interest and the place knowledge information, and taking the place knowledge information as a retrieval result for the retrieval information. The present disclosure can obtain the place knowledge information corresponding to the retrieval information for the retrieval information which is not the place itself.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of artificial intelligence, and in particular, to the fields of knowledge map, intelligent search, knowledge graph, etc. BACKGROUND

[0002] With the rapid development of computer technology, people have more and more demands for generating and collecting data by using network information technology. SUMMARY

[0003] The present disclosure provides a retrieval method and a knowledge information construction method, device, equipment and storage medium.

[0004] According to a first aspect of the present disclosure, a retrieval method is provided, comprising:

[0005] receiving retrieval information, wherein the retrieval information comprises a point of interest upper keyword, the point of interest upper keyword represents a general term of a plurality of map points of interest, and the map points of interest are used to represent locations in a geographic information system;

[0006] determining a target map point of interest corresponding to the retrieval information based on a corresponding relationship between the point of interest upper keyword and the map points of interest;

[0007] obtaining location knowledge information corresponding to the target map point of interest based on a corresponding relationship between the map points of interest and the location knowledge information, and taking the location knowledge information as a retrieval result for the retrieval information.

[0008] According to a second aspect of the present disclosure, a knowledge information construction method is provided, comprising:

[0009] obtaining a plurality of information segments and map points of interest corresponding to each information segment in the plurality of information segments, and the map points of interest are used to represent locations in a geographic information system;

[0010] statistically obtaining each information segment corresponding to each map point of interest based on the map point of interest corresponding to each information segment, respectively;

[0011] generating a theme of each map point of interest by using each information segment corresponding to each map point of interest, and the theme reflects semantic information of the information segment corresponding to the map point of interest for each map point of interest;

[0012] constructing location knowledge information of each map point of interest by using the theme of each map point of interest, and obtaining a corresponding relationship between the map points of interest and the location knowledge information.

[0013] According to a third aspect of the present disclosure, a retrieval device is provided, comprising:

[0014] The first receiving module is configured to receive search information, wherein the search information comprises a point of interest (POI) keyword, and the POI keyword represents a general name of a plurality of POIs, and the POIs are used to represent locations in a geographic information system (GIS);

[0015] The determining module is configured to determine a target POI corresponding to the search information based on a correspondence between the POI keyword and the POIs.

[0016] The obtaining module is configured to obtain location knowledge information corresponding to the target POI based on a correspondence between the POIs and the location knowledge information, and use the location knowledge information as a search result for the search information.

[0017] According to a fourth aspect of the present disclosure, a knowledge information construction apparatus is provided, comprising:

[0018] The obtaining module is configured to obtain a plurality of information segments and POIs corresponding to the information segments, and the POIs are used to represent locations in a geographic information system (GIS);

[0019] The first statistical module is configured to respectively count information segments corresponding to each POI based on the POI corresponding to each information segment, and obtain the information segments corresponding to each POI.

[0020] The generating module is configured to generate a theme of each POI by using the information segments corresponding to each POI, and for each POI, the theme reflects semantic information of the information segments corresponding to the POI.

[0021] The construction module is configured to construct location knowledge information of each POI by using the theme of each POI, and obtain a correspondence between the POIs and the location knowledge information.

[0022] According to a fifth aspect of the present disclosure, an electronic device is provided, comprising:

[0023] at least one processor; and

[0024] a memory connected with the at least one processor; wherein

[0025] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the first aspect or the second aspect.

[0026] According to a sixth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method according to the first aspect or the second aspect.

[0027] According to a seventh aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method according to the first aspect or the second aspect.

[0028] The present disclosure can achieve the knowledge information of a place corresponding to the search information which is not the place itself.

[0029] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0030] The accompanying drawings are used to better understand the present scheme, and do not constitute a limitation on the present disclosure. Among them:

[0031] Figure 1A is a flow chart of the search method provided by the embodiments of the present disclosure;

[0032] Figure 1B is another flow chart of the search method provided by the embodiments of the present disclosure;

[0033] Figure 2 is a schematic diagram of the information in the related art;

[0034] Figure 3 is a schematic diagram of the knowledge information in the embodiments of the present disclosure;

[0035] Figure 4A is another schematic diagram of the knowledge information in the embodiments of the present disclosure;

[0036] Figure 4B is another schematic diagram of the knowledge information in the embodiments of the present disclosure;

[0037] Figure 5 is a flow chart of the construction of the knowledge information in the embodiments of the present disclosure;

[0038] Figure 6 is a schematic diagram of the information segment in the embodiments of the present disclosure;

[0039] Figure 7 is a schematic diagram of the construction of the knowledge information in the embodiments of the present disclosure;

[0040] Figure 8 is a schematic diagram of the search device provided by the embodiments of the present disclosure;

[0041] Figure 9 Another structural schematic diagram of the retrieval device provided by the embodiment of the present disclosure is provided.

[0042] Figure 10 Another structural schematic diagram of the retrieval device provided by the embodiment of the present disclosure is provided.

[0043] Figure 11 A structural schematic diagram of the knowledge information construction device provided by the embodiment of the present disclosure is provided.

[0044] Figure 12 Another structural schematic diagram of the knowledge information construction device provided by the embodiment of the present disclosure is provided.

[0045] Figure 13 A block diagram of an electronic device for implementing the retrieval method or the information construction method provided by the embodiment of the present disclosure is provided. DETAILED DESCRIPTION

[0046] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to be clear and concise, descriptions of well-known functions and structures are omitted in the following description.

[0047] The embodiment of the present disclosure provides a retrieval method, which can include:

[0048] Receiving retrieval information, wherein the retrieval information includes a point of interest generic keyword, the point of interest generic keyword represents a general term of a plurality of map points of interest, and the map point of interest is used to represent a location in a geographic information system;

[0049] Determining a target map point of interest corresponding to the retrieval information based on a corresponding relationship between the point of interest generic keyword and the map point of interest;

[0050] Obtaining location knowledge information corresponding to the target map point of interest based on a corresponding relationship between the map point of interest and the location knowledge information, and taking the location knowledge information as a retrieval result for the retrieval information.

[0051] In the embodiment of the present disclosure, for retrieval information including a point of interest generic keyword, a target map point of interest corresponding to the retrieval information can be determined based on a corresponding relationship between the point of interest generic keyword and the map point of interest, and then location knowledge information corresponding to the target map point of interest can be obtained based on a corresponding relationship between the map point of interest and the location knowledge information. For retrieval information that is not a location itself, location knowledge information corresponding to the retrieval information can be obtained.

[0052] The retrieval method provided by the embodiments of the present disclosure can be applied to an electronic device. Specifically, the electronic device can include a server, a terminal, and the like.

[0053] Figure 1A is a flowchart of the retrieval method provided by the embodiments of the present disclosure. Referring to Figure 1A The retrieval method provided by the embodiments of the present disclosure can include:

[0054] S101, receiving retrieval information.

[0055] The retrieval information includes a superordinate keyword of a point of interest, the superordinate keyword of the point of interest represents a collective name of a plurality of map points of interest, and the map points of interest are used to represent locations in a geographic information system.

[0056] For example, the Five Mountains are a collective name of a plurality of map points of interest: Mount Tai, Mount Huashan, Mount Hengshan, Mount Hengshan, and Mount Songshan. Therefore, the Five Mountains can be understood as a superordinate keyword of a point of interest.

[0057] In an implementation manner, the retrieval information input by a user can be received. For example, a map application (APP) is installed in the electronic device, and the user inputs the retrieval information through the map APP. In this way, the electronic device can receive the retrieval information.

[0058] S102, determining a target map point of interest corresponding to the retrieval information based on a correspondence between the superordinate keyword of the point of interest and the map point of interest.

[0059] The correspondence between the superordinate keyword of the point of interest and the map point of interest includes a plurality of map points of interest corresponding to a plurality of superordinate keywords of points of interest.

[0060] The superordinate keyword of the point of interest included in the retrieval information can be compared with the plurality of superordinate keywords of points of interest in the correspondence (the correspondence between the superordinate keyword of the point of interest and the map point of interest). Specifically, the superordinate keyword of the point of interest included in the retrieval information can be compared with the plurality of superordinate keywords of points of interest in the correspondence (the correspondence between the superordinate keyword of the point of interest and the map point of interest). If the superordinate keyword of the point of interest matches the superordinate keyword of the point of interest in the correspondence, for example, the superordinate keyword of the point of interest is the same as a superordinate keyword of a point of interest in the correspondence, the point of interest corresponding to the superordinate keyword of the point of interest that matches the superordinate keyword of the point of interest in the correspondence is taken as a target map point of interest corresponding to the superordinate keyword of the point of interest.

[0061] S103, obtaining location knowledge information corresponding to the target map point of interest based on a correspondence between the map point of interest and the location knowledge information, and taking the location knowledge information as a retrieval result for the retrieval information.

[0062] The corresponding relationship between the map interest points and the place knowledge information includes a plurality of map interest points respectively corresponding to place knowledge information. The place knowledge information corresponding to each map interest point can include information associated with the map interest point.

[0063] If the search information corresponds to one target map interest point, the target map interest point is compared with the plurality of map interest points in the corresponding relationship between the map interest points and the place knowledge information. If the target map interest point matches a map interest point in the corresponding relationship (the corresponding relationship between the map interest points and the place knowledge information), the place knowledge information of the map interest point in the corresponding relationship (the corresponding relationship between the map interest points and the place knowledge information) that matches the target map interest point is taken as the place knowledge information corresponding to the target map interest point.

[0064] If the search information corresponds to a plurality of target map interest points, each target map interest point is compared with the plurality of map interest points in the corresponding relationship between the map interest points and the place knowledge information. The specific comparison process is described above in the case of the search information corresponding to one target map interest point. In this way, the place knowledge information corresponding to each target map interest point can be obtained, and the place knowledge information corresponding to each target map interest point constitutes the target map interest points corresponding to the search information.

[0065] The construction of the corresponding relationship between the map interest points and the place knowledge information will be described in detail below, and will not be described here.

[0066] In an optional embodiment, as Figure 1B may also include:

[0067] S104, the place knowledge information is displayed by using the map.

[0068] Displaying the place knowledge information by using the map can also be understood as providing the place knowledge information as a map answer to the user.

[0069] The place knowledge information can include information associated with the target map interest point. For example, position information of the target map interest point, overall information of the target map interest point, such as a picture including the overall appearance of the target map interest point, and the like.

[0070] In an implementation manner, the place knowledge information of the target map interest point can be displayed in the map. For example, the target map interest point is marked by a box in the map, that is, the position information of the target map interest point is displayed in the map.

[0071] Displaying the place knowledge information by using the map can intuitively display the place knowledge information of the target map interest point in the map, so that the user can clearly view the information associated with the target map interest point in the map.

[0072] For example, the search information is "where are the Five Mountains"; the interest point upper keyword included in the search information is "Five Mountains"; the target map interest points corresponding to the search information are Mount Tai, Mount Hua, Mount Heng, Mount Hengshan, and Mount Song; the location knowledge information corresponding to the target map interest points is the location information of Mount Tai, Mount Hua, Mount Heng, Mount Hengshan, and Mount Song, and the location knowledge information is displayed by using a map, and Mount Tai, Mount Hua, Mount Heng, Mount Hengshan, and Mount Song are marked by boxes in the map. The answer of the map type can clearly and intuitively show the user where the Five Mountains are.

[0073] In the related art, when the search information is not a location itself, the related information is searched by using a search engine, and the answer given by the search engine is presented in the form of a static picture and text. This form is not clear and intuitive. For example, Figure 2 The answer corresponding to "where are the Five Mountains" is displayed in the form of text, and the answer corresponding to "where are the Five Mountains" is displayed in the form of a static picture. Based on the two forms of answers, the user cannot clearly and intuitively determine the specific location of the Five Mountains.

[0074] In the embodiments of the present disclosure, the search information including the interest point upper keyword can be used for searching, and the location knowledge information of the target map interest points corresponding to the search information can be displayed in a map. In this way, the search in the map based on the search information that is not a location can be implemented, and the related location knowledge information can be displayed in the map. It can also be understood that the map type answer is provided for the search information that is not a location, and the user is provided with a more clear and intuitive search answer.

[0075] At the same time, the user can search based on the keyword other than the location in the map, and the keyword other than the location, such as the search information "Five Mountains", can be directly used to provide the user with the map type answer. The user does not need to first query the answer in the form of text or the answer in the form of a static picture by using the search engine based on the search information, and then manually determine the location from the answer in the form of text or the answer in the form of a static picture, and then search in the map based on the location. The embodiments of the present disclosure not only facilitate the user operation, but also solve the problem that multiple answers need to be read to understand the overall situation. The embodiments of the present disclosure can directly search based on the search information to obtain the map type answer, and directly understand the information related to the search information through the map type answer.

[0076] In addition, the two forms of answers provided by the related technology also limit the further operation of the user. For example, the simple text answer cannot clearly and intuitively let the user know where the specific location is and how far it is from the user. The static picture form of answer is more intuitive than the simple text, but the degree is limited. The user cannot randomly zoom in to see more detailed levels (such as specific location, what is nearby), and cannot directly have further operation (how far from the user, how to go).

[0077] The retrieval method provided by the embodiments of the present disclosure can further include:

[0078] Receiving an interactive operation for the location knowledge information; and displaying information for the interactive operation.

[0079] The interactive operation can include clicking, zooming, and the like.

[0080] Further operations can be performed on the displayed location knowledge information. For example, the user can click the box labeling Mount Hengshan, and after the electronic device receives the clicking operation, the electronic device can display detailed information of Mount Hengshan in the map, such as introduction pictures, rankings, location information, and the like, as shown in Figure 3 .

[0081] A display interface can be provided, and the location knowledge information is displayed in the display interface. In addition to the location knowledge information itself, the display interface can also include an operation option, and the interactive operation is performed through the operation option. The user can initiate route planning. For example, in addition to displaying the location information of the target map point of interest, the display interface also includes a "go there" option. A clicking operation is received for the "go there" option. The location information is taken as a starting point or an end point. A route planning interface is displayed. If the location information is taken as the starting point, an end point input through the route planning interface is received. If the location information is taken as the end point, a starting point input through the route planning interface is received. In this way, the electronic device can display the planned route based on the starting point and the end point, such as a driving navigation route, a bus route, and the like, as shown in Figure 4A . For example, the display interface includes a "surrounding" option. A clicking operation is received for the "surrounding" option. A map near the location information is displayed, as shown in Figure 4B . Alternatively, the display interface displaying the knowledge information can be zoomed in to view the content near the location information, such as a store, a hotel, and the like.

[0082] In this way, the further interactive operation of the user for the location knowledge information can be supported, which is more clear and intuitive, and can help the user better understand the location-related knowledge and improve the user experience.

[0083] In the embodiments of the present disclosure, the corresponding target map interest point can be determined by using the super-keyword of the interest point, and then the knowledge information corresponding to the target map interest point can be obtained based on the correspondence between the super-keyword of the interest point and the map interest point, and the place knowledge information can be displayed by using the map, that is, the related knowledge information can be displayed in the map for the super-keyword of the interest point, and a clearer and more intuitive answer can be provided for the super-keyword of the interest point, and compared with the related art in which only the interest point itself can be searched to display the answer in the map, the range of searchable words supported by the map search is expanded in the embodiments of the present disclosure.

[0084] The embodiments of the present disclosure also provide a knowledge information construction method, as shown in Figure 5 The method can further include the following steps:

[0085] In S501, a plurality of information segments and a map interest point corresponding to each information segment in the plurality of information segments are obtained.

[0086] The map interest point is used to represent a place in a geographic information system.

[0087] The plurality of information segments and the map interest point corresponding to each information segment in the plurality of information segments can be generated based on labeling or machine production.

[0088] The POI attribution of each information segment can be labeled. For example, if an information segment has no clear POI attribution, the POI attribution of the information segment is “no POI attribution”, which can be understood as that the map interest point corresponding to the information segment is empty; if an information segment has a clear single POI attribution, the POI attribution of the information segment is labeled as the POI, which can be understood as that the map interest point corresponding to the information segment is the POI; if an information segment has multiple POI attributions, the POI attribution of the information segment is labeled as multiple POIs, which can be understood as that the map interest point corresponding to the information segment is multiple POIs.

[0089] The information segment can be a document (DOC) segment.

[0090] In an implementable manner, a plurality of information segments can be obtained; for each information segment, a word segmentation processing is performed on the information segment to obtain a plurality of words of the information segment; and in response to the plurality of words including at least one map interest point, the at least one map interest point is taken as the map interest point corresponding to the information segment.

[0091] The word segmentation processing can adopt any implementable word segmentation manner, and the word segmentation processing is not limited in the embodiments of the present disclosure.

[0092] After obtaining the plurality of words of the information segment, it can be judged for each word whether the word is a map interest point, and if so, it can be determined that the map interest point corresponding to the information segment includes the word. In this way, the map interest point corresponding to the information segment can be obtained.

[0093] By segmenting the information segment, the map interest point corresponding to the information segment can be automatically determined based on all the words included in the information segment, and the accuracy of the determined map interest point corresponding to the information segment can be improved.

[0094] S502, according to the map interest point corresponding to each information segment, respectively, the information segment corresponding to each map interest point is counted, and each information segment corresponding to each map interest point is obtained.

[0095] In one implementation, for each map interest point, the information segment corresponding to the map interest point in the plurality of information segments is the information segment of the map interest point.

[0096] For example, the information segment 1 corresponds to the map interest point 1; the information segment 2 corresponds to the map interest point 2; the information segment 3 corresponds to the map interest point 1, and the information segment 4 corresponds to the map interest point. The information segments corresponding to the map interest points 1 and 2 are counted to obtain that the information segment corresponding to the map interest point 1 includes the information segment 1 and the information segment 3, and the information segment corresponding to the map interest point 2 includes the information segment 2.

[0097] In another implementation, for each map interest point, the information segment corresponding to the map interest point in the plurality of information segments is the information segment of the map interest point.

[0098] The information segment corresponding to the map interest point is empty, which includes the information segment associated with the interest point upper keyword of the map interest point.

[0099] The interest point upper keyword of the map interest point is used to represent the collective name of a plurality of map interest points including the map interest point.

[0100] For example, the information segment 1 corresponds to the map interest point 1; the information segment 2 corresponds to the map interest point 2; the information segment 3 corresponds to the map interest point 1, and the information segment 4 corresponds to the map interest point. The information segments corresponding to the map interest points 1 and 2 are counted to obtain that the information segment corresponding to the map interest point 1 includes the information segment 1, the information segment 3 and the information segment 4, and the information segment corresponding to the map interest point 2 includes the information segment 2 and the information segment 4.

[0101] In this way, the information segment associated with the super-keyword of the map interest point and the information segment corresponding to the map interest point are taken as the information segment of the map interest point together, so as to enrich the information segment of the map interest point and provide a basis for enriching the theme of the map interest point.

[0102] S503, generating the theme of each map interest point by using the information segment corresponding to each map interest point.

[0103] The theme reflects the semantic information of the information segment corresponding to the map interest point.

[0104] After obtaining the information segment corresponding to each map interest point, the theme of each map interest point can be generated by using a preset theme model.

[0105] The theme model can be understood as a statistical model for clustering the implicit semantic structure of a text set in a non-supervised learning manner. For example, the theme model can include a latent Dirichlet allocation (LDA) model.

[0106] For each map interest point, the theme of the map interest point can include one or more themes, each theme can include one or more keywords, and for each theme, a score of each keyword can be generated when the theme includes multiple keywords, and the score can be used to represent the probability of using the keyword to represent the theme.

[0107] S504, constructing the place knowledge information of each map interest point by using the theme of each map interest point, and obtaining the corresponding relationship between the map interest point and the place knowledge information.

[0108] For each map interest point, in one implementation manner, the theme of the map interest point can be taken as the place knowledge information of the map interest point. In another implementation manner, the theme of the map interest point can be used to obtain information associated with the theme, and the theme of the map interest point and the information associated with the theme can be taken as the place knowledge information of the map interest point.

[0109] In the embodiments of the present disclosure, based on the plurality of information segments and the map interest points corresponding to each information segment in the plurality of information segments, the location knowledge information of each map interest point is constructed. It can also be understood that the theme of each POI is mined based on each POI, and the mapping relationship between knowledge and POI is obtained through the final knowledge generation. In this way, after the target map interest point corresponding to the search information is determined, the location knowledge information corresponding to the target map interest point can be obtained based on the corresponding relationship between the map interest point and the location knowledge information, so as to obtain the location knowledge information corresponding to the search information for the search information that is not the location itself. Further, the related location knowledge information is displayed on the map, and the search information corresponding to the knowledge information can be displayed on the map, and a clearer and more intuitive answer is provided for the search information that is not the location itself.

[0110] The knowledge related to the map interest point is automatically constructed, the powerful interaction capability of the electronic map is used to provide the map type answer for the user, the user's doubts related to the location are more clearly, intuitively and comprehensively answered, and the further map requirements such as route planning of the user are facilitated. The location knowledge can be automatically mined based on the network data, and the user can be provided with the knowledge presentation with better interaction without constructing the map again.

[0111] In an implementation manner, S504 can include: aggregating the associated themes in the themes of each map interest point; and constructing the knowledge information of the themes of each map interest point based on the aggregated themes, to obtain the corresponding relationship between the interest point and the location knowledge information.

[0112] The associated themes can include themes that are semantically repeated or semantically close. Specifically, each theme can be semantically matched with other themes, such as calculating a semantic vector of each theme, calculating the similarity between the semantic vectors corresponding to each theme, and if the similarity between the semantic vectors corresponding to two themes is greater than a first similarity threshold and less than a second similarity threshold, the two themes are semantically close. If the similarity between the semantic vectors corresponding to two themes is greater than the second similarity threshold, the two themes are repeated, and the second similarity threshold is greater than the first similarity threshold. The specific value can be determined according to actual requirements or experience.

[0113] There can be associated themes in the themes of different map interest points. For example, the themes of the map interest point 1 include theme A and theme B; the themes of the map interest point 2 include theme C and theme D, and theme A and theme C are semantically close themes. Therefore, the knowledge information of the map interest point 1 can be constructed in combination with theme C, that is, the knowledge information of the map interest point 1 is constructed by using theme A, theme B and theme C.

[0114] The themes of a map interest point can be associated, for example, the themes of the map interest point 3 include theme E, theme F and theme G, theme E and theme F are semantic repeated themes, one of the themes can be deleted, for example, theme E is deleted, the aggregated themes of the map interest point 3 include theme F, and the knowledge information of the map interest point 3 is constructed by using theme F.

[0115] By theme aggregation, the problems of repeated knowledge and incomplete knowledge POI set can be avoided.

[0116] In an optional embodiment, a theme can be represented by a theme keyword, and the theme keyword includes an interest point generic keyword, which represents the general term of a plurality of map interest points.

[0117] The corresponding map interest points of each interest point generic keyword can be counted, and the corresponding relationship between the interest point generic keyword and the map interest point is obtained.

[0118] The interest point generic keyword in the theme of each map interest point can be selected, and all map interest points are taken as the statistical sample, if the corresponding theme of a map interest point includes the interest point generic keyword, the map interest point corresponding to the interest point generic keyword includes the map interest point.

[0119] In the process of mining the theme of each map interest point by using a plurality of information segments and the corresponding interest points of each information segment in the plurality of information segments, and constructing the knowledge information of each map interest point by using the theme of each map interest point, the corresponding map interest points of each interest point generic keyword can also be counted from the perspective of the interest point generic keyword, that is, the interest point generic keyword table can be used as an index condition to find the map interest points of the interest point generic keyword, and the knowledge information is constructed from multiple perspectives, such as the map interest point perspective and the interest point generic keyword perspective, which enriches the dimension of the knowledge information and facilitates retrieval.

[0120] In an implementation manner, the obtained corresponding relationship between the theme and the map interest point can be verified. For example, the theme is represented by a theme keyword, and the theme keyword includes an interest point generic keyword, in this case, the corresponding relationship between the theme and the map interest point can be understood as the corresponding relationship between the interest point generic keyword and the map interest point. Specifically, the interest point information of the interest point generic keyword can be obtained, for example, the correct answer of the map interest point corresponding to the interest point generic keyword obtained from a encyclopedia or the like; the map interest points contained in the interest point generic keyword are verified based on the interest point information; and the map interest points contained in the interest point generic keyword are taken as the knowledge information of the interest point generic keyword in response to the fact that the map interest points contained in the interest point generic keyword are consistent with the interest point information.

[0121] In one specific example, the construction process of the knowledge information of the embodiments of the present disclosure can be completed by the following modules: a sample construction module, a POI-topic generation module, and a knowledge generation module. Specifically, the electronic device includes the sample construction module, the POI-topic generation module, and the knowledge generation module.

[0122] The sample construction module performs S501 and S502, the POI-topic generation module performs S503, and the knowledge generation module performs S504.

[0123] In order to automatically mine knowledge information, not just rely on expert systems to output knowledge, based on a large number of POI-related inputs.

[0124] Sample construction module: In order to capture the knowledge of POI itself and the upper knowledge and remove impurities as much as possible, the sample construction module organizes different inputs for different POIs. Specifically, it includes two steps: POI attribution labeling and sample organization.

[0125] POI attribution labeling: Based on labeling or machine production, a large number of DOC segments and their corresponding POI attributions are output as samples.

[0126] If a DOC segment has no explicit POI attribution, the POI attribution of the DOC segment is "no POI attribution", which can be understood as the interest point corresponding to the DOC segment being empty; if a DOC segment has a single explicit POI attribution, the POI attribution of the DOC segment is labeled as the POI, which can be understood as the interest point corresponding to the DOC segment being the POI; if a DOC segment has multiple POI attributions, the POI attribution of the DOC segment is labeled as multiple POIs, which can be understood as the interest point corresponding to the DOC segment being multiple POIs.

[0127] Sample organization: According to the POI attribution labeling result, the segments belonging to the POI and the segments without POI attribution are used as the input of the POI, where the segment is a DOC segment, as described in Figure 6 In order to capture the knowledge of Tai Shan itself, segment 2 is needed, in order to capture the upper knowledge (Five Mountains) of Tai Shan, segment 1 without POI attribution is needed, in addition, in order to remove impurities as much as possible, segments 3, 4, 5, and 6 with explicit POI attribution and not belonging to Tai Shan cannot be used.

[0128] Thus, the information segments corresponding to each POI are obtained, which can also be understood as the input in the theme process of the POI to be determined, specifically: the input of the POI of Mount Tai is segment 1 and segment 2, similarly, the input of the POI of Mount Huashan is segment 1 and segment 3, the input of the POI of Songshan is segment 1 and segment 4, the input of the POI of Mount Hengshan is segment 1 and segment 6.

[0129] POI-theme generation module: based on the POI-doc set obtained by the sample construction module, a common theme model (such as LDA) can be used to learn the theme of each POI, and the possible output results based on this step are that a POI has J themes, and each theme has K keywords:

[0130] POI i ={theme j :{word k :score}}

[0131] Wherein, POI i represents the POI i, theme j represents the theme of POI i , word k represents the keyword of theme j , and score represents the score of the keyword, which can be used to represent the probability of keyword word k representing theme theme j , j = 0, 1, …, J, k = 0, 1, …, K.

[0132] For example, the possible output results based on this step are:

[0133] Mount Tai: theme 0 (Five Mountains 0.044, Famous Mountains 0.019); theme 1 (Emperor 0.028, Sacrifice 0.011).

[0134] Palace Museum: theme 0 (Emperor 0.037, Forbidden City 0.027); theme 2 (History 0.033, Cultural Relics 0.027).

[0135] Knowledge generation module: based on the large number of POIs and their corresponding themes generated by the POI-theme generation module, and through the theme aggregation and knowledge discrimination modules, the final knowledge and its corresponding POI set.

[0136] The subject aggregation, the subject and the keyword generated by the POI-subject generation module exist in the case of semantic repetition or proximity (such as emperor, emperor), which can be aggregated by synonym or clustering to avoid the problems of repeated knowledge, incomplete POI set and the like. The subject aggregation has been described in detail in the above embodiments, and the above embodiments can be referred to.

[0137] In one example, as shown in Figure 7 For POI1, the corresponding information segments of POI1 include segment 1 and segment 2, and for POI2, the corresponding information segments of POI2 include segment 1 and segment 3. By using segment 1 and segment 2, the corresponding subjects of POI1 obtained by the subject model include subject 1, subject 2 and subject 3, and by using segment 1 and segment 3, the corresponding subjects of POI2 obtained by the subject model include subject 1 and subject 4. The knowledge information of POI1 and POI2 is constructed by using the corresponding subjects of POI1 and POI2, for example, the subject 1 is included in the corresponding subjects of POI1, and the subject 1 is also included in the corresponding subjects of POI2, and the subject 1 included in the corresponding subjects of POI2 can be aggregated into the corresponding subjects of POI1 to determine the knowledge 1 corresponding to POI, and the knowledge information corresponding to POI2 is constructed by using the subject 4 included in the corresponding subjects of POI2.

[0138] The above place knowledge information can include knowledge 1 and knowledge 2.

[0139] Knowledge correctness verification: some subjects have explicit correct answers, and the correct results can not be obtained by the above method, and structured knowledge data such as encyclopedia can be introduced for verification. For example, which places are the "Five Mountains", and there is a correct answer, and assuming that the input sample is insufficient, only the POI set of "Five Mountains" is obtained by the above steps, which is Mount Tai and Mount Hua, and the subject and the POI set cannot be output as knowledge. In the embodiment of the present disclosure, when the map interest points of "Five Mountains" obtained by the above steps are consistent with the places included in "Five Mountains" obtained from structured knowledge data such as encyclopedia, the corresponding relationship between "Five Mountains" and the map interest points of "Five Mountains" is output.

[0140] Based on the above steps, the mapping relationship between geographical knowledge and POI can be automatically constructed, that is, the corresponding relationship between the map interest points and the place knowledge information is obtained.

[0141] Based on each POI, the subject of the POI itself is mined, the mapping relationship between knowledge and POI is obtained by the final knowledge generation, the place knowledge can be automatically mined based on the whole network data, and the user does not need to construct again in the map, so as to provide the user with excellent interactive knowledge presentation.

[0142] The mapping relationship between the knowledge and the POI is obtained, so that, based on the correspondence between the theme and the interest point, after the target interest point corresponding to the search information is determined, the knowledge information corresponding to the target interest point can be acquired based on the correspondence between the interest point and the knowledge information, the related knowledge information is displayed by using the map, the next step of the interactive operation on the knowledge information on the map can be directly implemented, which is more clear and intuitive and can help the user better understand the knowledge related to the location.

[0143] Corresponding to the search method provided in the above embodiment, the embodiment of the present disclosure further provides a search device, as shown in Figure 8 may include:

[0144] The first receiving module 801 is configured to receive search information, wherein the search information includes an interest point upper keyword, the interest point upper keyword represents a general term of a plurality of map interest points, and the map interest point is used to represent a location in a geographic information system;

[0145] The determination module 802 is configured to determine a target map interest point corresponding to the search information based on a correspondence between the interest point upper keyword and the map interest point.

[0146] The acquisition module 803 is configured to acquire location knowledge information corresponding to the target map interest point based on a correspondence between the map interest point and the location knowledge information, and take the location knowledge information as a search result for the search information.

[0147] Optionally, as shown in Figure 9 the search device further includes:

[0148] The first display module 901 is configured to display the knowledge information by using the map.

[0149] Optionally, as shown in Figure 10 further includes:

[0150] The second receiving module 1001 is configured to receive an interactive operation for the location knowledge information.

[0151] The second display module 1002 is configured to display information for the interactive operation.

[0152] Corresponding to the knowledge information construction method provided in the above embodiment, the embodiment of the present disclosure further provides a knowledge information construction device, as shown in Figure 11 may include:

[0153] The acquisition module 1101 is configured to acquire a plurality of information segments and a map interest point corresponding to each information segment in the plurality of information segments, and the map interest point is used to represent a location in a geographic information system.

[0154] The first statistical module 1102 is configured to statistically process information segments corresponding to each map interest point according to the map interest points corresponding to the information segments, to obtain each information segment corresponding to each map interest point;

[0155] The generating module 1103 is configured to generate a theme of each map interest point by using each information segment corresponding to each map interest point, and the theme reflects semantic information of the information segment corresponding to the map interest point for each map interest point.

[0156] The constructing module 1104 is configured to construct place knowledge information of each map interest point by using the theme of each map interest point, to obtain a corresponding relationship between the map interest point and the place knowledge information.

[0157] Optionally, the constructing module 1104 is specifically configured to aggregate themes that exist in the theme of each map interest point; and construct knowledge information of the theme of each map interest point based on the aggregated themes, to obtain the corresponding relationship between the map interest point and the place knowledge information.

[0158] Optionally, the theme is represented by a theme keyword, and the theme keyword includes an interest point generic keyword, the interest point generic keyword representing a general term of a plurality of map interest points.

[0159] As shown in Figure 12 The knowledge information constructing apparatus further includes:

[0160] The second statistical module 1201 is configured to statistically process map interest points corresponding to each interest point generic keyword in the theme of each map interest point, to obtain a corresponding relationship between the interest point generic keyword and the map interest point.

[0161] Optionally, the first statistical module 1102 is specifically configured to, for each map interest point, take information segments in which a corresponding map interest point is the map interest point and a corresponding map interest point is empty as information segments of the map interest point from the plurality of information segments, wherein the information segments in which the corresponding map interest point is empty include information segments associated with an interest point generic keyword of the map interest point, and the interest point generic keyword of the map interest point is used to represent a general term of a plurality of map interest points including the map interest point.

[0162] Optionally, the acquiring module 1101 is specifically configured to acquire the plurality of information segments; perform word segmentation processing on each information segment to obtain a plurality of words of the information segment; and in response to the plurality of words including at least one map interest point, take the at least one map interest point as a map interest point corresponding to the information segment.

[0163] In the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0164] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0165] Figure 13 A schematic block diagram of an example electronic device 1300 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0166] As shown in Figure 13 The electronic device 1300 includes a computing unit 1301 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 1302 or a computer program loaded from a storage unit 1308 into a random access memory (RAM) 1303. Various programs and data required for the operation of the device 1300 can also be stored in the RAM 1303. The computing unit 1301, the ROM 1302, and the RAM 1303 are connected to each other through a bus 1304. An input / output (I / O) interface 1305 is also connected to the bus 1304.

[0167] Various components in the electronic device 1300 are connected to the I / O interface 1305, including an input unit 1306, such as a keyboard, a mouse, etc.; an output unit 1307, such as various types of displays, speakers, etc.; a storage unit 1308, such as a magnetic disk, an optical disk, etc.; and a communication unit 1309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1309 allows the device 1300 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0168] The computing unit 1301 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1301 performs various methods and processes described above, such as the retrieval method or the knowledge information construction method. For example, in some embodiments, the retrieval method or the knowledge information construction method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1308. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 1300 via the ROM 1302 and / or the communication unit 1309. When the computer program is loaded onto the RAM 1303 and executed by the computing unit 1301, one or more steps of the retrieval method or the knowledge information construction method described above can be performed. Alternatively, in other embodiments, the computing unit 1301 can be configured to perform the retrieval method or the knowledge information construction method by any other suitable means, such as by means of firmware.

[0169] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0170] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0171] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0172] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0173] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0174] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0175] It should be understood that the various forms of flow shown above can be re-ordered, added to, or have steps deleted, using the steps. For example, the steps described in the present disclosure can be executed in parallel, in series, or in a different order, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, which are not limited herein.

[0176] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A knowledge information construction method, comprising: obtaining a plurality of information segments; for each information segment, performing word segmentation on the information segment to obtain a plurality of words of the information segment; in response to the plurality of words including at least one map point of interest, taking the at least one map point of interest as a corresponding map point of interest of the information segment, the map point of interest being used to represent a location in a geographic information system; for each map point of interest, taking information segments of the plurality of information segments corresponding to the map point of interest and having a null corresponding map point of interest as information segments of the map point of interest, wherein the information segments having the null corresponding map point of interest include information segments associated with a point of interest upper keyword of the map point of interest, the point of interest upper keyword being used to represent a collective term of a plurality of map points of interest including the map point of interest; generating a theme of each map point of interest by using information segments corresponding to the map point of interest, wherein the theme of each map point of interest reflects semantic information of the information segments corresponding to the map point of interest; for each map point of interest, obtaining information associated with the theme of the map point of interest by using the theme of the map point of interest, and taking the theme of the map point of interest and the information associated with the theme of the map point of interest as location knowledge information of the map point of interest to obtain a corresponding relationship between the map point of interest and the location knowledge information.

2. The method of claim 1, wherein, The method further comprises: aggregating themes associated in the themes of the map points of interest; constructing knowledge information of the themes of the map points of interest based on the aggregated themes to obtain the corresponding relationship between the map points of interest and the location knowledge information.

3. The method of claim 1, wherein, The theme is represented by a theme keyword, and the theme keyword includes a point of interest upper keyword, the point of interest upper keyword representing a collective term of a plurality of map points of interest; The method further comprises: for each point of interest upper keyword in the themes of the map points of interest, counting map points of interest corresponding to each point of interest upper keyword to obtain a corresponding relationship between the point of interest upper keyword and the map points of interest. 4.A retrieval method, comprising: receiving retrieval information, wherein the retrieval information includes a point of interest upper keyword, the point of interest upper keyword representing a collective term of a plurality of map points of interest, the map points of interest being used to represent locations in a geographic information system; determining a target map point of interest corresponding to the retrieval information based on a corresponding relationship between the point of interest upper keyword and the map points of interest; obtaining location knowledge information corresponding to the target map point of interest based on a corresponding relationship between the map points of interest and the location knowledge information, and taking the location knowledge information as a retrieval result for the retrieval information, wherein the corresponding relationship between the map points of interest and the location knowledge information is obtained according to the method of any one of claims 1 to 3. 5.The method of claim 4, further comprising: displaying the location knowledge information by using a map.

6. The method of claim 5, further comprising: receiving an interaction operation for the location knowledge information; displaying information for the interaction operation.

7. A knowledge information construction apparatus, comprising: an obtaining module, configured to obtain a plurality of information segments; for each information segment, performing a word segmentation process on the information segment to obtain a plurality of words of the information segment; in response to the plurality of words comprising at least one map point of interest, taking the at least one map point of interest as a corresponding map point of interest of the information segment, the map point of interest being used to represent a location in a geographic information system; a first statistical module, configured to, for each map point of interest, take, from the plurality of information segments, information segments in which a corresponding map point of interest is the map point of interest and a corresponding map point of interest is empty, as information segments of the map point of interest, wherein the information segments in which the corresponding map point of interest is empty comprise information segments associated with a point-of-interest superordinate keyword of the map point of interest, the point-of-interest superordinate keyword being used to represent a collective of a plurality of map points of interest including the map point of interest; a generating module, configured to generate a theme of each map point of interest by using information segments corresponding to the map point of interest respectively, and for each map point of interest, the theme reflects semantic information of the information segments corresponding to the map point of interest; a construction module, configured to, for each map point of interest, obtain information associated with the theme of the map point of interest by using the theme of the map point of interest, and take the theme of the map point of interest and the information associated with the theme of the map point of interest as location knowledge information of the map point of interest, to obtain a corresponding relationship between the map point of interest and the location knowledge information.

8. The apparatus of claim 7, wherein, The construction module is specifically configured to aggregate themes that exist in the themes of the map points of interest respectively, and construct knowledge information of the themes of the map points of interest based on the aggregated themes, to obtain the corresponding relationship between the map points of interest and the location knowledge information.

9. The apparatus of claim 7, wherein the theme is represented by a theme keyword, and the theme keyword comprises a point-of-interest superordinate keyword, the point-of-interest superordinate keyword being used to represent the collective of the plurality of map points of interest; The apparatus further comprises: a second statistical module, configured to, for the point-of-interest superordinate keyword in the theme of each map point of interest, count map points of interest corresponding to each point-of-interest superordinate keyword respectively, to obtain a corresponding relationship between the point-of-interest superordinate keyword and the map points of interest.

10. A retrieval apparatus, comprising: a first receiving module, configured to receive retrieval information, wherein the retrieval information comprises a point-of-interest superordinate keyword, the point-of-interest superordinate keyword being used to represent the collective of the plurality of map points of interest, the map points of interest being used to represent locations in a geographic information system; a determination module, configured to determine a target map point of interest corresponding to the retrieval information based on a corresponding relationship between the point-of-interest superordinate keyword and the map points of interest. An obtaining module is configured to obtain place knowledge information corresponding to the target map interest point based on a corresponding relationship between map interest points and place knowledge information, and use the place knowledge information as a search result for the search information, wherein the corresponding relationship between map interest points and place knowledge information is obtained by the device according to any one of claims 7 to 9. 11.The apparatus of claim 10, further comprising: a first display module configured to display the knowledge information on a map. 12.The apparatus of claim 11, further comprising: a second receiving module configured to receive an interactive operation for the place knowledge information; a second display module configured to display information for the interactive operation. 13.An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-6. 15.A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-6.

Images