Method and apparatus for determining sensitivity of geographic information vocabulary

Abstract

A method and device for determining the sensitivity of a geographic information vocabulary, the method comprising: obtaining a target geographic information vocabulary; determining whether the target geographic information vocabulary hits a pre-established geographic information vocabulary database; if not, obtaining a pre-established geographic information phrase database, the geographic information phrase database including a plurality of geographic information phrases and their label information, the plurality of geographic information phrases being capable of forming the geographic information vocabulary, the label information of the geographic information phrase being used to indicate the probability of the geographic information vocabulary including the geographic information phrase being a sensitive vocabulary or a non-sensitive vocabulary; performing word segmentation on the target geographic information vocabulary to obtain a plurality of segmented words; matching each of the plurality of segmented words with the geographic information phrases in the geographic information phrase database; and determining the sensitivity of the target geographic information vocabulary based on the label information of each geographic information phrase in the geographic information phrase database that matches the segmented word successfully.

Description

Technical Field

[0001] The present application relates to the field of data security technology, and in particular to a method and device for determining the sensitivity of geographic information vocabulary. Background Art

[0002] In the modern information society, geographic information has been widely used in various scenarios, including navigation, location-based services, social networks, smart cities, and more. However, some of the content contained in geographic information may involve sensitive data such as personal privacy, national security, and commercial secrets. Therefore, how to determine the sensitivity of this geographic information and then take appropriate protection measures has become an important topic in research and technological applications. In related technologies, a database of sensitive geographic information is usually established, and the geographic information to be judged is matched with the geographic information in the database. The sensitivity of the geographic information to be judged is determined based on the matching results. However, due to the dynamic and real-time nature of geographic information, that is, geographic information is constantly updated with changes in time, location, or environment, it is difficult to establish a database of sensitive geographic information in a timely and comprehensive manner, resulting in inaccurate judgment results for sensitive geographic information. Summary of the Invention

[0003] In a first aspect, an embodiment of the present application provides a method for determining the sensitivity of geographic information vocabulary, the method comprising: obtaining a target geographic information vocabulary; determining whether the target geographic information vocabulary hits a pre-established geographic information vocabulary database, the geographic information vocabulary database including a plurality of geographic information vocabulary, each geographic information vocabulary corresponding to a point of interest, the point of interest representing a unique and deterministic geographic location, the plurality of geographic information vocabulary including sensitive vocabulary and non-sensitive vocabulary; if the target geographic information vocabulary does not hit the geographic information vocabulary database, obtaining a pre-established geographic information phrase database, the geographic information phrase database including a plurality of geographic information phrases and their label information, a plurality of geographic information phrases being able to constitute a geographic information vocabulary, the label information of a geographic information phrase being used to indicate the probability that the geographic information vocabulary including the geographic information phrase is a sensitive vocabulary or a non-sensitive vocabulary; performing word segmentation on the target geographic information vocabulary to obtain a plurality of word segments, matching each of the plurality of word segments with a geographic information phrase in the geographic information phrase database, and determining the sensitivity of the target geographic information vocabulary based on the label information of each geographic information phrase that successfully matches the word segmentation in the geographic information phrase database.

[0004] In a second aspect, an embodiment of the present application provides a device for determining the sensitivity of geographic information vocabulary, the device comprising: a first acquisition module for acquiring a target geographic information vocabulary; a determination module for determining whether the target geographic information vocabulary hits a pre-established geographic information vocabulary database, the geographic information vocabulary database including a plurality of geographic information vocabulary, each geographic information vocabulary corresponding to a point of interest, the point of interest representing a unique and deterministic geographic location, the plurality of geographic information vocabulary including sensitive vocabulary and non-sensitive vocabulary; a second acquisition module for acquiring a pre-established geographic information vocabulary if the target geographic information vocabulary does not hit the geographic information vocabulary database. A geographic information phrase database is provided, wherein the geographic information phrase database includes a plurality of geographic information phrases and their label information, a plurality of geographic information phrases can constitute a geographic information vocabulary, and the label information of the geographic information phrase is used to indicate the probability that the geographic information vocabulary including the geographic information phrase is a sensitive word or a non-sensitive word; a matching module is used to segment the target geographic information vocabulary to obtain a plurality of segmentations, match each of the plurality of segmentations with a geographic information phrase in the geographic information phrase database, and determine the sensitivity of the target geographic information vocabulary based on the label information of each geographic information phrase in the geographic information phrase database that successfully matches the segmentation.

[0005] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present application.

[0006] In a fourth aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present application when executing the computer program.

[0007] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements the method described in any embodiment of the present application when executed by a processor.

[0008] The embodiment of the present application establishes two databases with data granularity. The database with larger data granularity is a geographic information vocabulary database, which includes a number of geographic information vocabulary, each geographic information vocabulary corresponds to a point of interest, and can represent a unique and definite geographic location; the database with smaller data granularity is a geographic information phrase database, which includes a number of geographic information phrases and their label information. The geographic information phrase is a part of the geographic information vocabulary, and multiple geographic information phrases can constitute a geographic information vocabulary. The label information can represent the probability that the geographic information vocabulary including the geographic information phrase is a sensitive word or a non-sensitive word. When determining the sensitivity of the target geographic information vocabulary, it is first determined whether the target geographic information vocabulary hits the geographic information vocabulary database. If not, multiple segmented words in the target geographic information vocabulary are matched with geographic information phrases in the geographic information phrase database, and the sensitivity of the target geographic information vocabulary is determined based on the label information of each geographic information phrase that successfully matches the segmented words in the geographic information phrase database. Since geographic information phrases are only a part of geographic information vocabulary and their granularity is smaller than that of geographic information vocabulary, geographic information phrases can be used as elements that constitute geographic information vocabulary. Even if the complete geographic information vocabulary has not yet been included in the geographic information vocabulary database, the sensitivity of the geographic information vocabulary can still be estimated based on the elements that constitute the geographic information vocabulary, rather than simply judging all geographic information vocabulary that are not included in the geographic information vocabulary database as non-sensitive words, thereby improving the accuracy of the sensitivity judgment results of geographic information vocabulary.

[0009] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings herein are incorporated into the specification and constitute a part of this application. These drawings illustrate embodiments consistent with this application and, together with the specification, are used to illustrate the technical solutions of this application.

[0011] Figure 1 This is a flowchart of a method for determining the sensitivity of geographic information vocabulary according to an embodiment of the present application.

[0012] Figure 2 It is a schematic diagram of the geographic information vocabulary database of an embodiment of the present application.

[0013] Figure 3 It is a schematic diagram of the geographic information phrase database of an embodiment of the present application.

[0014] Figure 4 It is a schematic diagram of the system architecture of an embodiment of the present application.

[0015] Figure 5Schematic diagram of a method for generating a compliant weak positive word library comparison table in an embodiment of the present application.

[0016] Figure 6 It is a schematic diagram of the overall process of an embodiment of the present application.

[0017] Figure 7 It is a block diagram of a device for determining the sensitivity of geographic information vocabulary according to an embodiment of the present application.

[0018] Figure 8 It is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0020] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of.

[0021] It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0022] In order to enable people in this technical field to better understand the technical solutions in the embodiments of the present application, and to make the above-mentioned purposes, features and advantages of the embodiments of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application are further described in detail below with reference to the accompanying drawings.

[0023] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0024] Many application scenarios may involve the collection of geographic information, which may include sensitive information. To improve data security, it is necessary to perform sensitivity assessment on geographic information. For example, in intelligent driving scenarios, vehicle-mounted sensors (such as GPS, radar, and cameras) can be used to collect geographic information of the surrounding environment for route planning and obstacle avoidance. The collected geographic information may include the names of confidential organizations, which are not suitable for public disclosure. Therefore, it is necessary to filter out the names of these confidential organizations from the collected data through sensitivity assessment and perform desensitization processing.

[0025] In related technologies, a database of sensitive geographic information is typically established. The geographic information to be identified is then matched against the geographic information in the database. The sensitivity of the identified geographic information is determined based on the matching results. For example, if the database of sensitive geographic information includes "XX Military Base," then if the geographic information to be identified also includes "XX Military Base," the identified geographic information will successfully match the "XX Military Base" in the database of sensitive geographic information, and thus the information can be identified as sensitive.

[0026] However, geographic information may be constantly updated over time, location, or environmental changes. For example, a country may secretly establish new administrative agencies in a certain location based on national developments. The update of sensitive geographic information databases often lags behind the updates of the geographic information itself. If the geographic information corresponding to newly added administrative agencies is not promptly included in the sensitive geographic information database, it will be impossible to accurately determine the sensitivity of the actual collected geographic information through database matching.

[0027] Based on this, this application provides a method for determining the sensitivity of geographic information vocabulary, see Figure 1 , the method comprising:

[0028] Step S11: Acquire target geographic information vocabulary;

[0029] Step S12: determining whether the target geographic information vocabulary matches a pre-established geographic information vocabulary database, wherein the geographic information vocabulary database includes a plurality of geographic information vocabulary, each geographic information vocabulary corresponds to a point of interest, and the point of interest represents a unique and deterministic geographic location, and the plurality of geographic information vocabulary includes sensitive vocabulary and non-sensitive vocabulary;

[0030] Step S13: If the target geographic information vocabulary does not match the geographic information vocabulary database, a pre-established geographic information phrase database is obtained, wherein the geographic information phrase database includes a plurality of geographic information phrases and their label information. Multiple geographic information phrases can constitute a geographic information vocabulary, and the label information of a geographic information phrase is used to indicate the probability that the geographic information vocabulary including the geographic information phrase is a sensitive word or a non-sensitive word.

[0031] Step S14: Segment the target geographic information vocabulary to obtain multiple segmentations, match each of the multiple segmentations with a geographic information phrase in the geographic information phrase database, and determine the sensitivity of the target geographic information vocabulary based on the label information of each geographic information phrase that successfully matches the segmentation in the geographic information phrase database.

[0032] Taking into account that sensitive geographic information vocabulary (i.e., sensitive vocabulary) often includes specified elements, this application establishes a geographic information vocabulary database based on the complete geographic information vocabulary, and at the same time, establishes a geographic information phrase database based on the elements that make up the geographic information vocabulary (i.e., geographic information phrases). When the target geographic information vocabulary to be judged fails to hit the geographic information vocabulary database, the target geographic information vocabulary is segmented, and the multiple segmented words obtained are matched with the elements that make up the geographic information vocabulary, and the sensitivity of the target geographic information vocabulary is judged in the element dimension. Compared with the method of simply relying on the geographic information vocabulary database to judge the sensitivity of the target geographic information vocabulary, this application can effectively improve the accuracy of the sensitivity judgment results of geographic information vocabulary when the geographic information vocabulary database is not updated in a timely manner. The specific implementation method of this application is illustrated below.

[0033] In step S11, a target geographic information vocabulary may be obtained. The target geographic information vocabulary corresponds to a point of interest (POI), which represents a unique and definite geographic location. In other words, the target geographic information vocabulary corresponds to a unique and definite geographic location. For example, the target geographic information vocabulary may be an address, such as "No. XX, XX Street, XX District, XX City, XX Province," or a unique and definite name of a surface or building, such as "Forbidden City" or "Eiffel Tower."

[0034] The method for acquiring target geographic information vocabulary can vary depending on the actual application scenario. For example, in intelligent driving scenarios, target geographic information vocabulary can be collected by on-board sensors. In intelligent traffic management systems, surveillance cameras installed at intersections or highways can be combined with computer vision technology to identify information such as traffic flow and road conditions, thereby acquiring target geographic information vocabulary. In map and location-based service applications, target geographic information vocabulary can be acquired by connecting to open map service interfaces.

[0035] In step S12, a pre-established geographic information vocabulary database may be obtained. The geographic information vocabulary database includes a plurality of geographic information vocabulary, each of which corresponds to a point of interest. The geographic information vocabulary in the geographic information vocabulary database may include sensitive vocabulary and non-sensitive vocabulary. Sensitive vocabulary refers to sensitive geographic information vocabulary that cannot be disclosed, while non-sensitive vocabulary refers to non-sensitive geographic information vocabulary that can be disclosed.

[0036] In some embodiments, label information can be added to each geographic information vocabulary in the geographic information vocabulary database to indicate whether the geographic information vocabulary is a sensitive vocabulary or a non-sensitive vocabulary. In other embodiments, different geographic information vocabulary databases can be established for sensitive vocabulary and non-sensitive vocabulary, respectively. For example, a positive vocabulary database and a negative vocabulary database can be established, wherein the geographic information vocabulary included in the positive vocabulary database are all non-sensitive vocabulary, and the geographic information vocabulary in the negative vocabulary database are all sensitive vocabulary.

[0037] The geographic information vocabulary database can also be updated at a certain frequency, for example, deleting existing geographic information vocabulary in the geographic information vocabulary database, adding new geographic information vocabulary to the geographic information vocabulary database, and / or changing the type of geographic information vocabulary, such as migrating non-sensitive vocabulary in the positive vocabulary database to the negative vocabulary database.

[0038] In some embodiments, the geographic information vocabulary database also includes version information for indicating the current version of the geographic information vocabulary database. Different versions of the geographic information vocabulary database may have different contents. Adding version information facilitates management of updated geographic information vocabulary databases.

[0039] In some embodiments, the geographic information vocabulary database also includes a file flag indicating the validity of the geographic information vocabulary database. During use, the file flag in the geographic information vocabulary database can be read and matched against a preset valid file flag. If a match is successful, the geographic information vocabulary database is considered valid, and sensitivity determination of the target geographic information vocabulary can be performed based on the geographic information vocabulary database.

[0040] In some embodiments, each geographic information vocabulary in the geographic information vocabulary database can be encrypted. Specifically, the geographic information vocabulary can be encrypted into an irreversible digital unique identifier through encryption technology. Encryption methods include but are not limited to hash algorithms, hash encryption, symmetric encryption algorithms, or asymmetric encryption algorithms. Furthermore, during encryption, since the geographic information vocabulary in the negative vocabulary database is not publicly available, only the geographic information vocabulary in the negative vocabulary database can be encrypted. Alternatively, both the geographic information vocabulary in the positive vocabulary database and the geographic information vocabulary in the negative vocabulary database can be encrypted.

[0041] The geographic information vocabulary database of some embodiments is as follows Figure 2 As shown, it includes header information and table data, wherein the header information includes file flags and file version information, and the table data is used to record geographic information vocabulary, and each geographic information vocabulary corresponds to a corresponding digital unique identifier. In the example where the geographic information vocabulary database includes a positive vocabulary database and a negative vocabulary database, both the positive vocabulary database and the negative vocabulary database can be used. Figure 2 The data structure shown.

[0042] After obtaining the target geographic information vocabulary, it can be determined whether the target geographic information vocabulary matches the geographic information vocabulary database. If the target geographic information vocabulary is identical to any geographic information vocabulary in the geographic information vocabulary database, it can be determined that the target geographic information vocabulary matches the geographic information vocabulary database. If the target geographic information vocabulary is different from any geographic information vocabulary in the geographic information vocabulary database, it can be determined that the target geographic information vocabulary does not match the geographic information vocabulary database.

[0043] In the example where the geographic information vocabulary database includes a positive vocabulary database and a negative vocabulary database, it is possible to first determine whether the target geographic information vocabulary hits the positive vocabulary database. If not, it is then determined whether the target geographic information vocabulary hits the negative vocabulary database. Alternatively, it is also possible to first determine whether the target geographic information vocabulary hits the negative vocabulary database. If not, it is then determined whether the target geographic information vocabulary hits the positive vocabulary database. Alternatively, the steps of determining whether the target geographic information vocabulary hits the positive vocabulary database and determining whether the target geographic information vocabulary hits the negative vocabulary database can be performed simultaneously.

[0044] If the target geographic information vocabulary hits the geographic information vocabulary database, the sensitivity of the target geographic information vocabulary can be determined based on the type of geographic information vocabulary that the target geographic information vocabulary hits in the geographic information vocabulary database. For example, if the type of the geographic information vocabulary hit is a sensitive word, the target geographic information vocabulary can be determined to be a sensitive word. If the type of the geographic information vocabulary hit is a non-sensitive word, the target geographic information vocabulary can be determined to be a non-sensitive word.

[0045] In the example where the geographic information vocabulary database includes a positive vocabulary database and a negative vocabulary database, if the target geographic information vocabulary hits a non-sensitive word in the positive vocabulary database, the target geographic information vocabulary can be directly determined to be a non-sensitive word. Similarly, if the target geographic information vocabulary hits a non-sensitive word in the negative vocabulary database, the target geographic information vocabulary can be directly determined to be a sensitive word.

[0046] If the target geographic information vocabulary does not hit the positive vocabulary database and the negative vocabulary database, it can be determined that the target geographic information vocabulary does not hit the geographic information vocabulary database. In this case, step S13 can be executed.

[0047] In some embodiments, each geographic information vocabulary in the geographic information vocabulary database is pre-encrypted. In this case, the target geographic information vocabulary can be encrypted based on the encryption method of each geographic information vocabulary in the geographic information vocabulary database, and then a determination can be made as to whether the encrypted target geographic information vocabulary matches the pre-established geographic information vocabulary database. This can reduce the risk of geographic information vocabulary leakage in the geographic information vocabulary database.

[0048] In step S13, a pre-established geographic information phrase database can be obtained. This database includes several geographic information phrases and their label information. Geographic information phrases are elements that make up a geographic information vocabulary, and multiple geographic information phrases can form a geographic information vocabulary. Geographic information vocabulary includes, but is not limited to, at least some of the following elements: elements representing countries, elements representing provinces, elements representing cities, elements representing districts, elements representing streets, elements representing building information (such as building names or numbers), elements representing scenic spot names, etc. For example, a geographic information vocabulary may be "XX Province XX City XX Street XX Park." Each geographic information phrase may include one or more of the above elements. For example, one geographic information phrase may be "XX Park," another geographic information phrase may be "XX City XX Street," and yet another geographic information phrase may be "XX Province XX City." Geographic information phrases correspond to one or more regions, and each region may include multiple points of interest. That is, the geographic location corresponding to a geographic information phrase is non-unique and uncertain. For example, the geographic information phrase "XX Park" may refer to either XX Park in City A or XX Park in City B. For another example, the geographic information phrase "XX province XX city" includes multiple points of interest such as the city's government building, shopping mall, zoo, etc.

[0049] Because the geographic location corresponding to a geographic information phrase is non-unique and uncertain, it's impossible to directly determine whether a geographic information phrase is sensitive or non-sensitive. However, geographic information phrases are elements that make up geographic information vocabulary, and sensitive vocabulary often includes specific elements, such as "army" and "government building." Therefore, it's possible to roughly infer the probability that a geographic information vocabulary containing a particular geographic information phrase is a sensitive term. That is, label information can be established for each geographic information phrase to indicate the probability that the geographic information vocabulary containing that geographic information phrase is a sensitive term or a non-sensitive term. For example, the probability of a geographic information phrase containing the geographic information phrase "army" being a sensitive term is high, so the probability represented by the label information corresponding to the geographic information phrase "army" is also high, for example, 0.7. Conversely, the probability of a geographic information phrase containing the geographic information phrase "noodle shop" being a sensitive term is high, so the probability represented by the label information corresponding to the geographic information phrase "noodle shop" is also low, for example, 0.1. It should be understood that the numerical values ​​here are merely illustrative and are not intended to limit this disclosure.

[0050] In some embodiments, the geographic information phrase database may include a positive phrase database and a negative phrase database. The probability indicated by the tag information corresponding to the geographic information phrases in the positive phrase database is greater than the probability indicated by the tag information corresponding to the geographic information phrases in the negative phrase database. In other words, if the target geographic information vocabulary includes a geographic information vocabulary in the positive phrase database, then the target geographic information vocabulary has a higher probability of being a sensitive vocabulary; if the target geographic information vocabulary includes a geographic information vocabulary in the negative phrase database, then the target geographic information vocabulary has a lower probability of being a sensitive vocabulary.

[0051] The geographic information phrase database may also be updated at a certain frequency, for example, by deleting existing geographic information phrases in the geographic information phrase database, adding new geographic information phrases to the geographic information phrase database, and / or changing the label information of geographic information phrases.

[0052] In some embodiments, the geographic information phrase database also includes version information for indicating the current version of the geographic information phrase database. Different versions of the geographic information phrase database may have different contents. By adding version information, it is easier to manage the updated geographic information phrase database.

[0053] In some embodiments, the geographic information phrase database also includes a file flag indicating the validity of the geographic information phrase database. During use, the file flag in the geographic information phrase database can be read and matched against a preset valid file flag. If a match is successful, the geographic information phrase database is considered valid, and sensitivity determination of the target geographic information vocabulary can be performed based on the geographic information phrase database.

[0054] In some embodiments, the geographic information phrase database may further include weights for the geographic information phrase database. Different geographic information phrase databases (e.g., positive phrase databases and negative phrase databases) may use different weights. By setting weights for the geographic information phrase databases, the degree of influence of the label information of the geographic information phrases in the geographic information phrase database on the sensitivity determination results can be adjusted.

[0055] In some embodiments, the geographic information phrase database may also include weights for each geographic information phrase. By assigning weights to geographic information phrases (referred to as phrase weights), the degree to which the label information corresponding to the geographic information phrase influences the sensitivity determination result can be adjusted. For example, the geographic information vocabulary that includes the geographic information phrase "army" is much more likely to be a sensitive vocabulary than the geographic information vocabulary that includes the geographic information phrase "noodle shop." Therefore, the weight corresponding to the geographic information phrase "army" may be greater than the weight corresponding to the geographic information phrase "noodle shop."

[0056] In some embodiments, each geographic information phrase in the geographic information phrase database, tag information corresponding to the geographic information phrase, weights of the geographic information phrase database, and weights corresponding to the geographic information phrases may all be encrypted.

[0057] Some embodiments of the geographic information phrase database such as Figure 3 As shown, it includes header information and table data, wherein the header information includes file flags, file version information and weights of geographic information phrase database, and the table data is used to record geographic information phrases, label information of geographic information phrases and weights of geographic information phrases. The weights of geographic information phrase database, geographic information phrases, label information of geographic information phrases and weights of geographic information phrases can all be encrypted data. In the example where the geographic information phrase database includes a positive phrase database and a negative phrase database, both the positive phrase database and the negative phrase database can be encrypted. Figure 3 The data structure shown.

[0058] In step S14, the target geographic information vocabulary may be segmented to obtain multiple segmented words. The multiple segmented words may include geographic information phrases or non-geographic information phrases, including but not limited to names, time, numbers, etc. For example, if the target geographic information vocabulary is "Zhang San Noodle House", segmenting the target geographic information vocabulary may obtain two segmented words, "Zhang San" and "Noodle House", where "Zhang San" is a name and "Noodle House" is a geographic information phrase.

[0059] Each of the multiple segmented words can be matched with a geographic information phrase in a geographic information phrase database. In the case where the geographic information phrase database includes a positive phrase database and a negative phrase database, each segmented word can be matched with a geographic information phrase in the positive phrase database first. If a segmented word fails to successfully match a geographic information phrase in the positive phrase database, the segmented word can then be matched with a geographic information phrase in the negative phrase database. Alternatively, each segmented word can be matched with a geographic information phrase in the negative phrase database first. If a segmented word fails to successfully match a geographic information phrase in the negative phrase database, the segmented word can then be matched with a geographic information phrase in the positive phrase database. Alternatively, each segmented word can be matched with both a geographic information phrase in the positive phrase database and a geographic information phrase in the negative phrase database in parallel.

[0060] In some embodiments, each geographic information word and its label information in the geographic information phrase database is pre-encrypted. The geographic information phrase in the geographic information phrase database can be decrypted first, and each of the multiple segmented words can be matched with the decrypted geographic information phrase in the geographic information phrase database. Furthermore, the label information of the geographic information phrases in the geographic information phrase database that successfully match the multiple segmented words can be decrypted, and the sensitivity of the target geographic information word can be determined based on the decrypted label information of each successfully matched geographic information phrase.

[0061] For example, each geographic information phrase in the geographic information phrase database can be decrypted and then matched against multiple word segments in the target geographic information vocabulary. Assuming that geographic information phrase a in the geographic information phrase database successfully matches a word segment in the target geographic information vocabulary, the tag information of geographic information phrase a can be decrypted, and the sensitivity of the target geographic information vocabulary can be determined based on the decrypted tag information of geographic information phrase a.

[0062] It is understood that the above is only one possible implementation method. In other implementation methods, multiple word segments in the target geographic information vocabulary can be encrypted according to the encryption method of geographic information phrases, and the encrypted multiple word segments are matched with geographic information phrases in the geographic information phrase database to screen out successfully matched geographic information phrases. The label information of the successfully matched geographic information phrases is then decrypted, and the sensitivity of the target geographic information vocabulary is determined based on the decrypted label information. This method can reduce the leakage of geographic information phrases and improve data security.

[0063] Through the above matching process, the geographic information phrases in the geographic information phrase database that successfully match each segmentation can be determined. Based on these determined geographic information phrases, the sensitivity of the target geographic information vocabulary can be determined. For example, the target geographic information vocabulary is segmented into four segments: A, B, C, and D. Among them, A and B successfully match geographic information phrase a in the positive phrase database, C does not successfully match any geographic information phrase in the geographic information phrase database, and D successfully matches geographic information phrase d in the negative phrase database. In this case, the sensitivity of the target geographic information vocabulary can be determined based on the label information of geographic information phrase a and the label information of geographic information phrase d.

[0064] In some embodiments, when matching a segmented word with a geographic information phrase, if the segmented word is the same as a geographic information phrase, it can be determined that the segmented word matches the geographic information phrase successfully. If the segmented word is different from the geographic information phrase, it can be determined that the segmented word matches the geographic information phrase unsuccessfully.

[0065] In other embodiments, the segmented words and geographic information phrases can be matched in two dimensions, namely, pronunciation and glyph, to obtain the pronunciation similarity and glyph similarity between the segmented words and the geographic information phrases, determine the total similarity between the segmented words and the geographic information phrases based on the pronunciation similarity and glyph similarity, and determine whether the segmented words and the geographic information phrases match based on the total similarity. For example, when the total similarity is greater than a preset similarity threshold, it can be determined that the segmented words and the geographic information phrases are successfully matched; otherwise, it is determined that the segmented words and the geographic information phrases fail to match. In this way, it is possible to reduce inaccurate matching caused by spelling errors or similar pronunciations. For example, when a user uploads the geographic information vocabulary "XX Troops" through the interface with the open map service, the "troops" in it is input as "department"; or, when the vehicle-mounted voice output module outputs "Luoyang", it is mistakenly recognized as "Luoyang".

[0066] In some embodiments, each of the multiple segmentations can be matched with a geographic information phrase in a positive phrase database to determine the first label information of each first geographic information phrase in the positive phrase database that successfully matches the multiple segmentations, each of the multiple segmentations can be matched with a geographic information phrase in a negative phrase database to determine the second label information of each second geographic information phrase in the negative phrase database that successfully matches the multiple segmentations, and based on the first label information of each first geographic information phrase and the second label information of each second geographic information phrase, the sensitivity of the target geographic information vocabulary can be determined.

[0067] Continuing with the previous example, the first geographic information phrase in the positive phrase database that successfully matches the multiple word segmentations includes geographic information phrase a, and the second geographic information phrase in the negative phrase database that successfully matches the multiple word segmentations includes geographic information phrase d. Therefore, the sensitivity of the target geographic information vocabulary can be determined based on the label information of geographic information phrase a and the label information of geographic information phrase d.

[0068] Furthermore, the first weight corresponding to the positive phrase database and the second weight corresponding to the negative phrase database can be determined, the first label information of each first geographic information phrase is weighted based on the first weight, and the second label information of each second geographic information phrase is weighted based on the second weight, and the sensitivity of the target geographic information vocabulary is determined based on the weighted first label information of each first geographic information phrase and the weighted second label information of each second geographic information phrase.

[0069] Continuing with the previous example, the tag information of geographic information phrase a can be weighted based on the first weight, and the tag information of geographic information phrase d can be weighted based on the second weight. Then, based on the weighted tag information of geographic information phrase a and the weighted tag information of geographic information phrase d, it is determined whether the target geographic information word is a sensitive word.

[0070] Furthermore, before determining the sensitivity of the target geographic information vocabulary based on the first label information of each first geographic information phrase and the second label information of each second geographic information phrase, the weight of each first geographic information phrase and the weight of each second geographic information phrase can also be determined, and the first label information of the corresponding first geographic information phrase can be weighted based on the weight of each first geographic information phrase, and the second label information of the corresponding second geographic information phrase can be weighted based on the weight of each second geographic information phrase.

[0071] In some embodiments, the weight of a geographic information phrase is related to the sensitivity level of the geographic information phrase. The sensitivity level of the geographic information phrase can be determined first, and then the weight of the geographic information phrase can be determined based on the sensitivity level of the geographic information phrase. The higher the sensitivity level of the geographic information phrase, the greater the probability that the geographic information vocabulary containing the geographic information phrase is a sensitive vocabulary. Different sensitivity levels can correspond to different weights.

[0072] It can be understood that in actual applications, the number of geographic information phrases that successfully match multiple word segments in the target geographic information vocabulary may not be limited to the cases listed in the above examples. However, no matter how many geographic information phrases are successfully matched, the sensitivity of the target geographic information vocabulary can be determined in a manner similar to that in the above embodiments.

[0073] A specific embodiment of the present application and its application scenario are illustrated below with reference to the accompanying drawings.

[0074] This application can be used in the field of intelligent connected vehicles and autonomous driving to perform sensitivity judgment on geographic information vocabulary collected by on-board sensors and provide judgment results. This application mainly consists of three parts: knowledge base, judgment reference materials, and semantic judgment.

[0075] The overall system architecture is as follows Figure 4 As shown, it includes the following parts: a compliance strong positive word library, a compliance strong positive word library comparison table, a compliance strong positive semantic judgment module, a compliance strong negative word library, a compliance strong negative word library comparison table, a compliance strong negative semantic judgment module, a compliance weak positive word library, a compliance weak positive word library comparison table, a compliance weak positive semantic judgment module, a compliance weak negative word library, a compliance weak negative word library comparison table and a compliance weak negative semantic judgment module.

[0076] The knowledge base includes a positive vocabulary database (also known as a compliant strong positive vocabulary database), a negative vocabulary database (also known as a compliant strong negative vocabulary database), a positive phrase database (also known as a compliant weak positive vocabulary database) and a negative phrase database (also known as a compliant weak negative vocabulary database). These knowledge bases can be continuously accumulated and updated based on the practical experience of the expert team.

[0077] The geographic information vocabulary in the compliant strong positive word library is publicly available, non-sensitive geographic information vocabulary related to the field of intelligent connected vehicles and autonomous driving (i.e., the non-sensitive vocabulary in the aforementioned embodiment);

[0078] The geographic information words in the compliant strong negative word library are non-public, highly sensitive geographic information words related to the fields of intelligent connected vehicles and autonomous driving (i.e., the sensitive words in the aforementioned embodiment);

[0079] The geographic information phrases in the compliant weak positive word library are publicly available and related to the fields of intelligent connected vehicles and autonomous driving, but may cause objections when combined with weakly sensitive phrases. Therefore, the label information in the compliant weak positive word library is used to indicate the probability that the geographic information vocabulary containing the geographic information phrase is a non-sensitive word.

[0080] The geographic information phrases in the compliant weak negative vocabulary are weakly sensitive geographic information phrases related to the fields of intelligent connected vehicles and autonomous driving. Therefore, the label information in the compliant weak positive vocabulary is used to indicate the probability that the geographic information vocabulary including the geographic information phrases is a sensitive vocabulary.

[0081] The reference materials for judgment include a comparison table and judgment principles. The comparison table includes a compliant strong positive word library comparison table (including several non-sensitive words), a compliant strong negative word library comparison table (including several sensitive words), a compliant weak positive word library comparison table (including several geographic information phrases and their label information, the label information is used to indicate the probability that the geographic information vocabulary including the geographic information phrases is a non-sensitive word), and a compliant weak negative word library comparison table (including several geographic information phrases and their label information, the label information is used to indicate the probability that the geographic information vocabulary including the geographic information phrases is a sensitive word).

[0082] All words in the compliant strong positive word library can be encrypted using commercial secret data protection technology to generate irreversible digital unique identifiers, which can be stored in a private format file. This is the compliant strong positive word library comparison table. Similarly, all words in the compliant strong negative word library can be encrypted using commercial secret data protection technology to generate irreversible digital unique identifiers, which can be stored in a private format file. This is the compliant strong negative word library comparison table.

[0083] Based on the practical experience of the expert team, the compliant weak positive word library can be continuously accumulated and updated, and based on the compliant weak positive word library, the sensitivity level of the geographic information phrase can be determined according to the degree of objection that may arise when combined with the geographic information phrase, and different weights can be assigned to geographic information phrases of different sensitivity levels. For example, multiple N sensitivity levels can be divided and formed, each corresponding to N weights. Each time the compliant weak positive word library is updated, the weight of the geographic information phrase can be adjusted in coordination with the compliant weak negative word library. The weight of the geographic information phrase, label information, and the weight of the compliant weak positive word library are encrypted and stored in a private format file, namely the compliant weak positive word library comparison table. The specific steps are as follows: Figure 5 shown.

[0084] The processing methods for the compliant weak negative word library and the compliant weak negative word library comparison table are similar and will not be repeated here.

[0085] The various weights involved in the above embodiments can be determined based on the technical judgment rules formed by the continuous accumulation and updating of the actual experience of the expert team, relying on the compliant weak positive word library scoring table and the compliant weak negative word library scoring table. At the same time, the scoring and judgment process of the semantic judgment module will rely on the scoring judgment principle.

[0086] like Figure 6 As shown in Figure 1, semantic judgment mainly includes the following steps: 1) judging compliance with strong positive terms; 2) judging compliance with strong negative terms; 3) judging compliance with weak positive terms; 4) judging compliance with weak negative terms; and 5) outputting the judgment result. This judgment result can determine whether the input geographic information vocabulary can be made public or transmitted.

[0087] ① Compliance strong word library judgment

[0088] The target geographic information vocabulary is encrypted using commercial secret data protection technology to generate an irreversible digital unique identifier. The compliant strong positive word library comparison table is checked to see if this digital unique identifier is included. If so, the target geographic information vocabulary is determined to be a non-sensitive vocabulary, and the judgment result is returned, ending the judgment process. If not, the process proceeds to step 2 to continue the judgment.

[0089] ② Compliance strong negative vocabulary determination

[0090] The target geographic information vocabulary is encrypted using commercial secret data protection technology to generate an irreversible digital unique identifier. The compliant strong negative vocabulary comparison table is checked to see if this digital unique identifier is included. If so, the target geographic information vocabulary is determined to be a sensitive vocabulary and the judgment result is returned, ending the judgment process. If not, the process proceeds to step 3 to continue the judgment.

[0091] ③ Compliant weak positive word library judgment

[0092] Traverse the compliant weak positive word library scoring table, perform regular matching on the input target geographic information vocabulary and each decrypted geographic information phrase in the compliant weak positive word library scoring table, obtain the weight and probability (i.e. label information) of each geographic information phrase, and cumulatively calculate the probability corresponding to each geographic information phrase that successfully matches in the compliant weak positive word library scoring table to obtain the cumulative total score; the dynamic scoring formula is as follows:

[0093]

[0094] Among them, y positive represents the cumulative total score of each geographic information phrase that successfully matched in the compliance weak positive word database score table, α1, α2, … ,α N Represents the weight of each of the N geographic information phrases in the compliant weak positive word library scoring table, which is determined based on the sensitivity level of the corresponding geographic information phrases, x1, x2, … ,x N Represents the probability of each of the N geographic information phrases in the compliant weak positive word library scoring table.

[0095] ④ Compliant weak negative vocabulary determination

[0096] Traverse the compliant weak negative vocabulary scoring table, perform regular matching on the input target geographic information vocabulary and each decrypted geographic information phrase in the compliant weak negative vocabulary scoring table, obtain the dimension weight and probability (i.e. label information) of each geographic information phrase, and cumulatively calculate the probability corresponding to each geographic information phrase that successfully matched in the compliant weak negative vocabulary scoring table to obtain the cumulative total score; the dynamic scoring formula is as follows:

[0097]

[0098] Among them, ynegative It represents the cumulative total score of each geographic information phrase that successfully matched in the compliant weak negative vocabulary score table, β1, β2, … ,β M Represents the weight of each of the M geographic information phrases in the compliant weak negative vocabulary score table, which is determined based on the sensitivity level of the corresponding geographic information phrases, y1, y2, … ,y M Represents the probability corresponding to each of the M geographic information phrases in the compliant weak negative vocabulary scoring table.

[0099] ⑤Output judgment result

[0100] For a target geographic information word input, its sensitivity is determined based on the cumulative total score of the compliant weak positive word library score and the compliant weak negative word library score. The specific formula is as follows:

[0101]

[0102] Among them, γ positive and γ negative They represent the weight of the compliant weak positive word library and the weight of the compliant weak negative word library, S total Indicates the probability that the target geographic information word is a sensitive word.

[0103] The weights of the compliant weak positive word library and the compliant weak negative word library are used to ensure the consistency of the value domain of the accumulated total score when the knowledge base is dynamically updated. They come from the compliant weak positive word library scoring table file and the compliant weak negative word library scoring table file respectively, and are dynamically updated synchronously with the two word libraries.

[0104] Based on the cumulative total score S total The built-in judgment principle can give a unique judgment result, which is used to indicate whether the target geographic information vocabulary can be disclosed or transmitted. For example, when S total When it is greater than a certain threshold, the target geographic information vocabulary can be determined to be a sensitive vocabulary and cannot be disclosed or transmitted; when S total When the value is less than or equal to the above threshold, the target geographic information vocabulary can be determined to be a non-sensitive vocabulary and can be disclosed or transmitted.

[0105] This application builds a multi-dimensional knowledge base based on the long-term practical experience of the expert team. This knowledge base not only covers a wide range of industry knowledge and experience, but is also continuously updated by the expert team to ensure that it keeps pace with industry developments and can respond to the ever-changing needs of hazard identification.

[0106] Based on this multi-dimensional knowledge base, this application further develops decision references and semantic decision logic. These references and semantic decision logic incorporate industry expertise and experience to comprehensively evaluate input vocabulary from multiple perspectives. By scoring the sensitivity of a word across multiple dimensions, we can more accurately determine the potential harm of a word.

[0107] To improve the accuracy of this assessment, we've designed a rigorous and scientific semantic judgment module. This module doesn't simply perform word matching; instead, it assigns different weights and probabilities to different geographic information phrases to assess whether they pose a threat. This multi-step, comprehensive scoring mechanism takes into account the sensitivity level of each word, resulting in more accurate and reliable judgments.

[0108] like Figure 7 As shown, the present application also provides a device for determining the sensitivity of geographic information vocabulary, the device comprising:

[0109] The first acquisition module 101 is used to acquire target geographic information vocabulary;

[0110] Determination module 102, configured to determine whether the target geographic information vocabulary matches a pre-established geographic information vocabulary database, wherein the geographic information vocabulary database includes a plurality of geographic information vocabulary, each geographic information vocabulary corresponding to a point of interest, the point of interest representing a unique and deterministic geographic location, and the plurality of geographic information vocabulary including sensitive vocabulary and non-sensitive vocabulary;

[0111] A second acquisition module 103 is configured to acquire a pre-established geographic information phrase database if the target geographic information vocabulary does not match the geographic information vocabulary database, wherein the geographic information phrase database includes a plurality of geographic information phrases and their label information. Multiple geographic information phrases can constitute a geographic information vocabulary, and the label information of a geographic information phrase is used to indicate the probability that the geographic information vocabulary including the geographic information phrase is a sensitive word or a non-sensitive word.

[0112] The matching module 104 is used to segment the target geographic information vocabulary to obtain multiple segmentations, match each of the multiple segmentations with a geographic information phrase in the geographic information phrase database, and determine the sensitivity of the target geographic information vocabulary based on the label information of each geographic information phrase that successfully matches the segmentation in the geographic information phrase database.

[0113] The functions or modules included in the device provided in this application can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0114] An embodiment of the present application further provides a computer device, which comprises at least a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any of the aforementioned embodiments is implemented.

[0115] Figure 8 1 shows a more specific hardware structure diagram of a computer device provided in an embodiment of the present application. The device may include: a processor 201, a memory 202, an input / output interface 203, a communication interface 204, and a bus 205. The processor 201, the memory 202, the input / output interface 203, and the communication interface 204 are connected to each other within the device via the bus 205.

[0116] The processor 201 can be implemented using a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application. The processor 201 can also include a graphics card, which can be an Nvidia Titan X graphics card or an 1080Ti graphics card.

[0117] The memory 202 can be implemented in the form of a read-only memory (ROM), a random access memory (RAM), a static storage device, a dynamic storage device, etc. The memory 202 can store an operating system and other application programs. When the technical solutions provided in the embodiments of the present application are implemented through software or firmware, the relevant program codes are stored in the memory 202 and are called and executed by the processor 201.

[0118] The input / output interface 203 is used to connect input / output modules to implement information input and output. The input / output modules can be configured as components within the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc., and output devices may include a display, speaker, vibrator, indicator light, etc.

[0119] The communication interface 204 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via a wired method (such as USB, network cable, etc.) or a wireless method (such as mobile network, WIFI, Bluetooth, etc.).

[0120] The bus 205 comprises a pathway for transmitting information between the various components of the device (eg, the processor 201 , the memory 202 , the input / output interface 203 , and the communication interface 204 ).

[0121] It should be noted that although the above device only shows the processor 201, the memory 202, the input / output interface 203, the communication interface 204, and the bus 205, in a specific implementation, the device may also include other components necessary for normal operation. In addition, it will be understood by those skilled in the art that the above device may only include the components necessary to implement the embodiments of the present application, and does not necessarily include all the components shown in the figure.

[0122] An embodiment of the present application provides a computer program product, including a computer program, which implements the method described in any embodiment of the present application when executed by a processor.

[0123] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the aforementioned embodiments.

[0124] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computer device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0125] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is merely illustrative, wherein the modules described as separate components may or may not be physically separated, and the functions of each module can be implemented in the same one or more software and / or hardware when implementing the embodiment of this application. It is also possible to select some or all of the modules according to actual needs to achieve the purpose of the embodiment. Those of ordinary skill in the art can understand and implement it without paying any creative work.

[0126] The above is only a specific implementation of the embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the embodiment of the present application. These improvements and modifications should also be regarded as the scope of protection of the embodiment of the present application.

Claims

1. A method for determining the sensitivity of geographic information vocabulary, characterized in that: The method comprises: Obtain target geographic information vocabulary; Determining whether the target geographic information vocabulary matches a pre-established geographic information vocabulary database, wherein the geographic information vocabulary database includes a plurality of geographic information vocabulary, each geographic information vocabulary corresponds to a point of interest, and the point of interest represents a unique and deterministic geographic location, and the plurality of geographic information vocabulary includes sensitive vocabulary and non-sensitive vocabulary; If the target geographic information vocabulary does not match the geographic information vocabulary database, obtaining a pre-established geographic information phrase database, wherein the geographic information phrase database includes a plurality of geographic information phrases and their label information, wherein a plurality of geographic information phrases can constitute a geographic information vocabulary, and the label information of the geographic information phrase is used to indicate the probability that the geographic information vocabulary including the geographic information phrase is a sensitive word or a non-sensitive word; The target geographic information vocabulary is segmented to obtain multiple segmentations, each of the multiple segmentations is matched with a geographic information phrase in the geographic information phrase database, and the sensitivity of the target geographic information vocabulary is determined based on the label information of each geographic information phrase that successfully matches the segmentation in the geographic information phrase database.

2. The method according to claim 1, characterized in that The method further comprises: If the target geographic information vocabulary hits the geographic information vocabulary database, the sensitivity of the target geographic information vocabulary is determined based on the type of geographic information vocabulary hit by the target geographic information vocabulary in the geographic information vocabulary database.

3. The method according to claim 2, characterized in that The geographic information vocabulary database includes a positive vocabulary database and a negative vocabulary database, the positive vocabulary database includes the non-sensitive vocabulary, and the negative vocabulary database includes the sensitive vocabulary; The determining the sensitivity of the target geographic information vocabulary based on the type of geographic information vocabulary hit by the target geographic information vocabulary in the geographic information vocabulary database includes: If the target geographic information vocabulary matches a non-sensitive vocabulary in the positive vocabulary database, determining that the target geographic information vocabulary is a non-sensitive vocabulary; If the target geographic information vocabulary hits a sensitive vocabulary in the negative vocabulary database, it is determined that the target geographic information vocabulary is a sensitive vocabulary.

4. The method according to claim 1, wherein The geographic information phrase database includes a positive phrase database and a negative phrase database, and the probability represented by the label information corresponding to the geographic information phrase in the positive phrase database is greater than the probability represented by the label information corresponding to the geographic information phrase in the negative phrase database; Matching each of the multiple segmented words with a geographic information phrase in the geographic information phrase database, and determining the sensitivity of the target geographic information vocabulary based on label information of each geographic information phrase successfully matched with the segmented word in the geographic information phrase database, includes: Matching each of the multiple segmented words with a geographic information phrase in the positive phrase database, and determining first label information of each first geographic information phrase in the positive phrase database that successfully matches the multiple segmented words; Matching each of the multiple segmented words with a geographic information phrase in the negative phrase database, and determining second label information of each second geographic information phrase in the negative phrase database that successfully matches the multiple segmented words; The sensitivity of the target geographic information vocabulary is determined based on the first tag information of each first geographic information phrase and the second tag information of each second geographic information phrase.

5. The method according to claim 4, characterized in that The determining the sensitivity of the target geographic information vocabulary based on the first tag information of each first geographic information phrase and the second tag information of each second geographic information phrase includes: Determining a first weight corresponding to the positive phrase database and a second weight corresponding to the negative phrase database; weighting the first tag information of each first geographic information phrase based on the first weight, and weighting the second tag information of each second geographic information phrase based on the second weight; The sensitivity of the target geographic information vocabulary is determined based on the weighted first label information of each first geographic information phrase and the weighted second label information of each second geographic information phrase.

6. The method according to claim 4, characterized in that Before determining the sensitivity of the target geographic information vocabulary based on the first tag information of each first geographic information phrase and the second tag information of each second geographic information phrase, the method further includes: Determining a weight for each first geographic information phrase and a weight for each second geographic information phrase; the weight for a geographic information phrase is related to a sensitivity level of the geographic information phrase, wherein a higher sensitivity level of the geographic information phrase indicates a greater probability that the geographic information vocabulary including the geographic information phrase is a sensitive vocabulary; The first tag information of the corresponding first geographic information phrases is weighted based on the weights of the respective first geographic information phrases, and the second tag information of the corresponding second geographic information phrases is weighted based on the weights of the respective second geographic information phrases.

7. The method according to claim 1, characterized in that Each geographic information word in the geographic information word database is encrypted in advance; The determining whether the target geographic information vocabulary hits a pre-established geographic information vocabulary database includes: encrypting the target geographic information vocabulary based on the encryption method of each geographic information vocabulary in the geographic information vocabulary database; Determine whether the encrypted target geographic information vocabulary hits a pre-established geographic information vocabulary database.

8. The method according to claim 1, characterized in that Each geographic information word and its label information in the geographic information phrase database is encrypted in advance; Matching each of the multiple segmented words with a geographic information phrase in the geographic information phrase database, and determining the sensitivity of the target geographic information vocabulary based on label information of each geographic information phrase successfully matched with the segmented word in the geographic information phrase database, includes: Decrypting the geographic information phrases in the geographic information phrase database; matching each of the plurality of segmented words with the decrypted geographic information phrase in the geographic information phrase database; Decrypting the label information of the geographic information phrases in the geographic information phrase database that successfully match the multiple segmented words; The sensitivity of the target geographic information vocabulary is determined based on the decrypted tag information of each successfully matched geographic information phrase.

9. A device for determining the sensitivity of geographic information vocabulary, characterized in that: The device comprises: The first acquisition module is used to acquire target geographic information vocabulary; a determination module, configured to determine whether the target geographic information vocabulary matches a pre-established geographic information vocabulary database, wherein the geographic information vocabulary database includes a plurality of geographic information vocabulary, each geographic information vocabulary corresponding to a point of interest, the point of interest representing a unique and deterministic geographic location, and the plurality of geographic information vocabulary including sensitive vocabulary and non-sensitive vocabulary; a second acquisition module configured to acquire a pre-established geographic information phrase database if the target geographic information vocabulary does not match the geographic information vocabulary database, wherein the geographic information phrase database includes a plurality of geographic information phrases and their label information, wherein a plurality of geographic information phrases can constitute a geographic information vocabulary, and the label information of a geographic information phrase is used to indicate a probability that the geographic information vocabulary including the geographic information phrase is a sensitive word or a non-sensitive word; A matching module is used to segment the target geographic information vocabulary to obtain multiple segmentations, match each of the multiple segmentations with a geographic information phrase in the geographic information phrase database, and determine the sensitivity of the target geographic information vocabulary based on the label information of each geographic information phrase that successfully matches the segmentation in the geographic information phrase database.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

12. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images