Yellow pages information acquisition method, device and electronic equipment

Abstract

The embodiment of the present application provides a method, device and electronic device for obtaining yellow page information. The method includes: querying a telephone number to be queried through a search engine to obtain multiple web pages containing the telephone number to be queried; extracting yellow page information to be selected from multiple web pages through a pre-trained recognition model; for any yellow page information to be selected, performing weighted calculation according to the confidence weight of the source website where at least one web page corresponding to it is located to obtain a weighted result; determining the yellow page information to be selected with the largest weighted result as the yellow page information of the telephone number to be queried. The embodiment of the present application achieves the purpose of determining yellow page information with high accuracy and credibility from a large amount of messy search data, so that users can obtain yellow page information with high accuracy and credibility that matches their queried telephone number through a one-step quick query of the search engine, thereby improving the user's query experience.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and more specifically, to a method, device and electronic device for obtaining yellow page information. Background Art

[0002] With the development of Internet technology, all kinds of information can be obtained on the Internet. When people want to obtain the yellow pages information of a phone number, they can also search for it on the Internet.

[0003] In the related art, the yellow pages information of a telephone number is generally searched through a search engine, and the search engine returns a series of web pages related to the searched telephone number, and then the user views and selects the yellow pages information he needs from the large amount of data.

[0004] However, the inventor of the present application has found that the yellow pages are generally huge in quantity and disorganized, and their accuracy cannot be guaranteed, making it difficult for users to make choices. Summary of the invention

[0005] The present application provides a yellow page information acquisition method, device and electronic device for acquiring relatively accurate yellow page information from a large amount of messy search data.

[0006] According to a first aspect, an embodiment of the present application provides a method for obtaining yellow page information, the method comprising:

[0007] Searching the telephone number to be queried through a search engine to obtain multiple web pages containing the telephone number to be queried;

[0008] Through the pre-trained recognition model, the yellow pages information to be selected is extracted from multiple web pages;

[0009] For any yellow page information to be selected, weighted calculation is performed according to the confidence weight of the source website where at least one webpage corresponding to it is located, to obtain a weighted result;

[0010] The yellow page information with the largest weighted result is determined as the yellow page information of the telephone number to be queried.

[0011] In a possible implementation, the pre-trained recognition model includes any of the following:

[0012] Pre-trained named entity recognition models;

[0013] A set of regular expressions trained based on labeled data.

[0014] In a possible implementation, before performing weighted calculation for any yellow page information to be selected according to the confidence weight of the source website where at least one webpage corresponding to the yellow page information is located, the method further includes:

[0015] Determine the confidence weight of each source website.

[0016] In a possible implementation, determining the confidence weight of each source website includes:

[0017] Searching multiple sample phone numbers of known yellow page information through a search engine to obtain multiple web pages to be judged including each sample phone number;

[0018] Through the pre-trained named entity recognition model, the yellow page information to be judged is extracted from each web page to be judged;

[0019] Calculate the similarity between any yellow page information to be judged and the corresponding known yellow page information;

[0020] According to the calculated similarity, the confidence weight of the source website of the web page to be determined corresponding to any yellow page information to be determined is determined.

[0021] In a possible implementation, similarity calculation is performed between any yellow page information to be determined and corresponding known yellow page information, including:

[0022] Perform word segmentation processing on the yellow page information to be judged and the corresponding known yellow page information respectively, and obtain feature information of the yellow page information to be judged and feature information of the known yellow page information;

[0023] The similarity between the feature information of the yellow pages information to be judged and the feature information of the known yellow pages information is calculated.

[0024] In a possible implementation, the feature information includes:

[0025] Personal or business name, phone number, address.

[0026] In a possible implementation, the method further includes:

[0027] Filter the obtained yellow pages information.

[0028] According to a second aspect, an embodiment of the present application provides a yellow page information acquisition device, the device comprising:

[0029] In the query module, the user searches for the phone number to be queried through the search engine and obtains multiple web pages containing the phone number to be queried;

[0030] An extraction module, used for extracting yellow page information to be selected from multiple web pages obtained by the query module through a pre-trained recognition model;

[0031] A weighted calculation module, for performing weighted calculation on any yellow page information to be selected extracted by the extraction module according to the confidence weight of the source website where at least one webpage corresponding thereto is located, to obtain a weighted result;

[0032] The determination module is used to determine the yellow page information to be selected with the largest weighted result obtained by the weighted calculation module as the yellow page information of the telephone number to be queried.

[0033] In a possible implementation, the pre-trained recognition model includes any of the following:

[0034] Pre-trained named entity recognition models;

[0035] A set of regular expressions trained based on labeled data.

[0036] In one possible implementation, the device also includes: a confidence weight determination module, which is used to determine the confidence weights of each source website before performing weighted calculation on any candidate yellow pages information extracted by the extraction module based on the confidence weights of the source website where at least one corresponding web page is located.

[0037] In a possible implementation, the confidence weight determination module includes:

[0038] A search unit, used to search multiple sample phone numbers of known yellow page information through a search engine to obtain multiple web pages to be judged including each sample phone number;

[0039] An extraction unit, used to extract yellow page information to be judged from each web page to be judged obtained by the search unit through a pre-trained named entity recognition model;

[0040] A similarity calculation unit, used for calculating the similarity between any yellow page information to be determined extracted by the extraction unit and the corresponding known yellow page information;

[0041] The confidence weight determination unit is used to determine the confidence weight of the source website where the web page to be determined corresponding to any yellow page information to be determined is located according to the similarity calculated and determined by the similarity calculation unit.

[0042] In a possible implementation, the similarity calculation unit includes:

[0043] The word segmentation processing subunit is used to perform word segmentation processing on the yellow page information to be judged and the corresponding known yellow page information respectively, and obtain the characteristic information of the yellow page information to be judged and the characteristic information of the known yellow page information;

[0044] The similarity calculation subunit is used to calculate the similarity between the feature information of the yellow pages information to be judged and the feature information of the known yellow pages information.

[0045] In a possible implementation, the feature information includes:

[0046] Personal or business name, phone number, address.

[0047] In a possible implementation, the device further includes:

[0048] The filtering module is used to filter the acquired yellow pages information.

[0049] According to a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising:

[0050] processor, memory, and bus;

[0051] A bus, used to connect the processor and memory;

[0052] A memory, used for storing operation instructions;

[0053] The processor is used to execute the yellow page information acquisition method shown in the first aspect or any implementation thereof by calling an operation instruction.

[0054] According to a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which is used to store computer instructions. When the computer instructions are executed on a computer, the computer can execute the yellow page information acquisition method shown in the first aspect above or any of its implementations.

[0055] The beneficial effects of the technical solution provided by the embodiment of the present application are:

[0056] Compared with the prior art, in the embodiment of the present application, a search engine is used to query a telephone number to be queried, and multiple web pages containing the telephone number to be queried are obtained; then, a pre-trained recognition model is used to extract yellow page information to be selected from the multiple web pages; then, for any yellow page information to be selected, a weighted calculation is performed on the confidence weight of the source website where at least one web page corresponding to it is located, and a weighted result is obtained; finally, the yellow page information to be selected with the largest weighted result is determined as the yellow page information of the telephone number to be queried, that is, the embodiment of the present application uses the confidence weight of the source website of the yellow page information as the judgment standard for judging the credibility and accuracy of the yellow page information, and uses the yellow page information with the highest weighted confidence result of the source website as the yellow page information of the telephone number to be queried, thereby achieving the purpose of determining yellow page information with high accuracy and credibility from a large amount of messy search data, so that users can obtain yellow page information with high accuracy and credibility that matches their queried telephone number through a one-step quick query of the search engine, thereby improving the user's query experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

[0058] Figure 1 A flowchart of a method for obtaining yellow page information provided by an embodiment of the present application;

[0059] Figure 2 A flowchart of a method for determining the confidence weight of each source website provided by an embodiment of the present application;

[0060] Figure 3 A schematic diagram of the structure of a yellow pages information acquisition device provided in another embodiment of the present application;

[0061] Figure 4 A schematic diagram of the structure of a confidence weight determination module provided in yet another embodiment of the present application;

[0062] Figure 5 A schematic structural diagram of an electronic device provided in yet another embodiment of the present application. DETAILED DESCRIPTION

[0063] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0064] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0065] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0066] The yellow page information acquisition method, device, electronic device and computer-readable storage medium provided in this application are intended to solve the above-mentioned technical problems in the prior art.

[0067] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0068] An embodiment of the present application provides a method for obtaining yellow page information, such as Figure 1 As shown, the method includes steps S101-S104:

[0069] Step S101: query the telephone number to be queried through a search engine to obtain multiple web pages containing the telephone number to be queried.

[0070] For the embodiment of the present application, when a user wants to obtain the yellow pages information of a phone number, the phone number can be queried through a search engine, for example, through the AA search engine. The spider crawler of the AA search engine will automatically crawl these web pages in advance under the premise of following the robots protocol, and put the data of the web pages on a distributed storage platform, such as HBase; when the AA search engine receives a query request input by the user including the phone number to be queried, it will query the distributed storage platform according to the query request to obtain multiple web pages containing the phone number to be queried.

[0071] Step S102: extracting yellow page information to be selected from multiple web pages through a pre-trained recognition model.

[0072] For the embodiment of the present application, when it is necessary to extract the yellow pages information to be selected from multiple web pages, that is, when multiple web pages need to be parsed, the system will pull the corresponding data from HBase and extract the telephone numbers and corresponding yellow pages information according to the trained named entity recognition model or the regular expression set automatically generated based on the labeled data.

[0073] For the embodiment of the present application, the pre-trained recognition model is a model output after training a named entity recognition algorithm (conditional random field, hidden Markov model, etc.) or a regular expression set and other models on a high-performance server based on the annotated data of the existing yellow pages data (i.e., a specific telephone number, the web pages searched based on it, and the yellow pages information included therein).

[0074] For the embodiment of the present application, the purpose of extracting yellow page information from multiple web pages based on the input telephone number can be achieved through the above-mentioned pre-trained recognition model.

[0075] Step S103: For any yellow page information to be selected, weighted calculation is performed according to the confidence weight of the source website where at least one corresponding web page is located to obtain a weighted result.

[0076] For the embodiment of the present application, there is at least one webpage corresponding to any yellow page information to be selected. The source website where each webpage in the at least one webpage is located has a corresponding confidence weight. According to the confidence weights of these source websites, a weighted calculation is performed on the yellow page information to be selected to obtain a weighted result for the yellow page information to be selected.

[0077] Step S104: Determine the yellow page information with the largest weighted result as the yellow page information of the telephone number to be queried.

[0078] For the embodiment of the present application, the larger the weighted result, the higher the confidence, so the candidate yellow page information with the largest weighted result is the yellow page information with the highest credibility that can be determined according to the embodiment of the present application. Through this step, the user can be provided with the yellow page information with the highest accuracy and credibility.

[0079] Compared with the prior art, in the embodiment of the present application, a search engine is used to query a telephone number to be queried, and multiple web pages containing the telephone number to be queried are obtained; then, the yellow page information to be selected is extracted from the multiple web pages through a pre-trained recognition model; then, for any yellow page information to be selected, a weighted calculation is performed according to the confidence weight of the source website where at least one web page corresponding to it is located, to obtain a weighted result; finally, the yellow page information to be selected with the largest weighted result is determined as the yellow page information of the telephone number to be queried, that is, the embodiment of the present application uses the confidence weight of the source website of the yellow page information as the judgment standard for judging the credibility and accuracy of the yellow page information, and uses the yellow page information with the highest weighted result of the confidence of the source website as the yellow page information of the telephone number to be queried, thereby achieving the purpose of determining the yellow page information with high accuracy and credibility from a large amount of messy search data, so that the user can obtain the yellow page information with high accuracy and credibility that matches the telephone number to be queried through a one-step quick query of the search engine, thereby improving the user's query experience.

[0080] In another possible implementation of the embodiment of the present application, the pre-trained recognition model includes any of the following:

[0081] Pre-trained named entity recognition models;

[0082] A set of regular expressions trained based on labeled data.

[0083] The so-called named entity (NE) is a person's name, organization name, place name, and all other entities identified by names.

[0084] Optionally, the named entity model of the embodiment of the present application can be trained using manually annotated corpus based on statistical methods, which does not require extensive linguistic knowledge when annotating the corpus and can be completed in a relatively short time. Methods based on statistical machine learning mainly include: Hidden Markov Model (HMM), Maximum Entropy (ME), Support Vector Machine (SVM), Conditional Random Fields (CRF), etc.

[0085] A regular expression (RE) is a string matching pattern that can be used to check whether a string contains a certain substring, replace the matching substring, or extract a substring that meets a certain condition from a string.

[0086] Optionally, the named entity recognition model or regular expression set can be extensively trained based on a large number of known phone numbers, web pages containing phone numbers, and known yellow pages information, and the model can be output to obtain a pre-trained named entity recognition model and a regular expression set trained based on labeled data.

[0087] Compared with the prior art, the embodiment of the present application extracts telephone numbers and corresponding yellow pages information through a pre-trained named entity recognition model and a set of regular expressions trained based on labeled data, thereby improving the accuracy of parsing.

[0088] In another possible implementation of the embodiment of the present application, before step S103, for any yellow page information to be selected, weighted calculation is performed according to the confidence weight of the source website where at least one web page corresponding to the yellow page information is located, the method further includes:

[0089] Determine the confidence weight of each source website.

[0090] Optionally, the confidence of the source website can be calculated by the model (described in detail below), or the confidence of the source website can be preset according to its type. For example, the confidence of a government website can be preset to be higher, or the confidence of the official website of an enterprise or other institution can be preset to be higher, while the confidence of a general website can be preset to be lower.

[0091] Compared with the prior art, the embodiment of the present application determines the confidence weight of each source website so that when judging the credibility of yellow page information, the confidence weight can be directly used for weighted calculation, providing a simple and reliable method for judging the credibility of yellow page information.

[0092] Another possible implementation of the embodiment of the present application is as follows: Figure 2 As shown, the method for determining the confidence weight of each source website includes steps S201-S204:

[0093] Step S201: Search multiple sample phone numbers of known yellow page information through a search engine to obtain multiple web pages to be determined including each sample phone number.

[0094] Step S202: extracting yellow page information to be judged from each web page to be judged respectively through the pre-trained named entity recognition model.

[0095] Optionally, other pre-trained models may be used to extract yellow page information to be determined from each web page to be determined. The process of pre-training the named entity recognition model is similar to the description in step S102 above, and will not be repeated here.

[0096] Step S203: Calculate the similarity between any yellow page information to be determined and the corresponding known yellow page information.

[0097] Optionally, the similarity between any yellow page information to be determined and the corresponding known yellow page information may be calculated based on any method such as Hamming distance, Euclidean distance, cosine distance, etc. The embodiment of the present application does not limit the similarity calculation method.

[0098] Optionally, the similarity can be a value between 0 and 1. For example, when two information are completely dissimilar, the similarity is 0; when two information are completely identical, the similarity is 1.

[0099] Step S204: Determine the confidence weight of the source website of the web page to be determined corresponding to any yellow page information to be determined based on the calculated similarity.

[0100] Optionally, based on the calculated similarity, the confidence weight of the source website of the web page to be judged corresponding to any yellow pages information to be judged is determined by the corresponding relationship between similarity and confidence weight, for example, a similarity of 0.4 corresponds to a confidence weight of 0.4.

[0101] Optionally, based on the calculated similarity, the confidence weight of the source website of the web page to be judged corresponding to any yellow pages information to be judged is determined, which can be determined by the corresponding relationship between the similarity range and the confidence weight. For example, the similarity (0.9-1] corresponds to the confidence weight 1, and the similarity (0.8-0.9] corresponds to the confidence weight 0.9.

[0102] Compared with the prior art, the confidence weight of the website is obtained by calculating the similarity between the yellow page information to be judged and the known yellow page information, which provides a reliable and convenient way for calculating the confidence weight of the website.

[0103] Another possible implementation method of the embodiment of the present application is that the above step S203, performing similarity calculation between any yellow pages information to be judged and the corresponding known yellow pages information, includes: performing word segmentation processing on the yellow pages information to be judged and the corresponding known yellow pages information respectively, obtaining feature information of the yellow pages information to be judged and feature information of the known yellow pages information; performing similarity calculation between the feature information of the yellow pages information to be judged and the feature information of the known yellow pages information.

[0104] Optionally, the word segmentation processing for the yellow page information to be judged and the corresponding known yellow page information can be based on dictionary-based string matching (for example, proximity matching algorithm, two-way maximum matching method, etc.), or can be based on statistics-based word segmentation (for example, hidden Markov model). The embodiment of the present application does not limit the method of word segmentation processing.

[0105] Optionally, feature information of the yellow page information to be determined and the corresponding known yellow page information can be obtained after word segmentation processing.

[0106] Optionally, the characteristic information of the yellow pages information may include: personal or corporate name, telephone number, and address.

[0107] Optionally, the characteristic information of the yellow page information may also include: industry nature, website, fax, zip code, etc. The embodiment of the present application does not limit the characteristic information of the yellow page information.

[0108] Based on the acquired characteristic information, any similarity calculation method described in step S203 can be used to calculate the similarity between the characteristic information of the yellow pages information to be judged and the characteristic information of the known yellow pages information, thereby obtaining the similarity between the yellow pages information to be judged and the known yellow pages information.

[0109] In another possible implementation manner of the embodiment of the present application, the method further includes: filtering the acquired yellow page information.

[0110] Optionally, the system will cache the yellow page information on a distributed file system (Hadoop Distributed File System, HDFS). Before going online, the system will filter the online data according to the rules for going online with the yellow page information, filtering out telephone names and their yellow page information that do not meet the standards or are likely to cause controversy.

[0111] Optionally, the obtained yellow page information can be filtered by processing the yellow page information through a string matching method, a latent semantic indexing method, a neural network method, etc.

[0112] Optionally, the obtained yellow page information can be filtered by setting a website blacklist to automatically filter the yellow page information in the web pages from the website blacklist, for example, adding illegal websites to the website blacklist.

[0113] For the embodiment of the present application, the yellow page information can be pushed to the yellow page library through the data push interface. The offline yellow page library will be stored in a NoSql database such as MongoDB, and finally updated to the online database in the form of incremental updates. The online database is stored in the form of levelDB, which can support the storage of billions of number information and billions of telephone query requests every day.

[0114] Compared with the prior art, the embodiments of the present application can provide more accurate and reliable yellow page information by performing filtering processing before going online, thereby filtering out telephone names and their yellow page information that do not meet the standards or are likely to cause controversy.

[0115] Figure 3 A schematic diagram of a yellow page information acquisition device 300 provided in another embodiment of the present application is shown in FIG. Figure 3 As shown, the device may include: a query module 301 , an extraction module 302 , a weighted calculation module 303 and a determination module 304 .

[0116] The query module 301 is used to query the telephone number to be queried through a search engine to obtain multiple web pages containing the telephone number to be queried.

[0117] The extraction module 302 is used to extract the yellow page information to be selected from the multiple web pages obtained by the query module 301 through the pre-trained recognition model.

[0118] The weighted calculation module 303 is used to perform weighted calculation on any yellow page information to be selected extracted by the extraction module 302 according to the confidence weight of the source website where at least one corresponding web page is located, to obtain a weighted result.

[0119] The determination module 304 is used to determine the yellow page information to be selected with the largest weighted result obtained by the weighted calculation module 303 as the yellow page information of the telephone number to be queried.

[0120] Optionally, the pre-trained recognition model includes any of the following: a pre-trained named entity recognition model; a set of regular expressions trained based on labeled data.

[0121] Optionally, the device also includes: a confidence weight determination module 400, which is used to determine the confidence weights of various source websites before weighted calculation is performed on any candidate yellow page information extracted by the extraction module 302 according to the confidence weights of the source website where at least one corresponding web page is located.

[0122] Alternatively, if Figure 4As shown, the confidence weight determination module 400 may include: a searching unit 401 , an extracting unit 402 , a similarity calculating unit 403 , and a confidence weight determination unit 404 .

[0123] The search unit 401 is used to search multiple sample phone numbers of known yellow page information through a search engine to obtain multiple web pages to be determined including each sample phone number.

[0124] The extraction unit 402 is used to extract the yellow page information to be determined from each web page to be determined obtained by the search unit 401 by using a pre-trained named entity recognition model.

[0125] The similarity calculation unit 403 is used to calculate the similarity between any yellow page information to be determined extracted by the extraction unit 402 and the corresponding known yellow page information.

[0126] The confidence weight determination unit 404 is used to determine the confidence weight of the source website where the web page to be determined corresponding to any yellow page information to be determined is located according to the similarity calculated and determined by the similarity calculation unit 404.

[0127] Optionally, the similarity calculation unit 403 may include: a word segmentation processing subunit and a similarity calculation subunit.

[0128] The word segmentation processing subunit is used to perform word segmentation processing on the yellow page information to be judged and the corresponding known yellow page information respectively, and obtain the characteristic information of the yellow page information to be judged and the characteristic information of the known yellow page information.

[0129] The similarity calculation subunit is used to calculate the similarity between the feature information of the yellow pages information to be judged and the feature information of the known yellow pages information.

[0130] Optionally, the characteristic information includes: personal or corporate name, telephone number, and address.

[0131] Optionally, the yellow page information acquisition device further includes:

[0132] The filtering module is used to filter the obtained yellow page information.

[0133] The yellow page information acquisition device provided in an embodiment of the present application can execute a yellow page information acquisition method provided in an embodiment of the present application. The implementation principle is similar and will not be repeated here.

[0134] Compared with the prior art, in the embodiment of the present application, a search engine is used to query a telephone number to be queried, and multiple web pages containing the telephone number to be queried are obtained; then, the yellow page information to be selected is extracted from the multiple web pages through a pre-trained recognition model; then, for any yellow page information to be selected, a weighted calculation is performed according to the confidence weight of the source website where at least one web page corresponding to it is located, to obtain a weighted result; finally, the yellow page information to be selected with the largest weighted result is determined as the yellow page information of the telephone number to be queried, that is, the embodiment of the present application uses the confidence weight of the source website of the yellow page information as the judgment standard for judging the credibility and accuracy of the yellow page information, and uses the yellow page information with the highest weighted result of the confidence of the source website as the yellow page information of the telephone number to be queried, thereby achieving the purpose of determining the yellow page information with high accuracy and credibility from a large amount of messy search data, so that the user can obtain the yellow page information with high accuracy and credibility that matches the telephone number to be queried through a one-step quick query of the search engine, thereby improving the user's query experience.

[0135] Another embodiment of the present application provides an electronic device, such as Figure 5 As shown, Figure 5 The electronic device 500 shown includes: a processor 501 and a memory 503. The processor 501 and the memory 503 are connected, such as through a bus 502. Optionally, the electronic device 500 may also include a transceiver 504. It should be noted that in actual applications, the transceiver 504 is not limited to one, and the structure of the electronic device 500 does not constitute a limitation on the embodiments of the present application.

[0136] The processor 501 may be a central processing unit (CPU), a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 501 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0137] The bus 502 may include a path to transfer information between the above components. The bus 502 may be a PCI bus or an EISA bus. The bus 502 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0138] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an erasable programmable read-only memory (EEPROM), a CD-ROM (Compact Disc-ROM) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0139] The memory 503 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the application code stored in the memory 503 to implement Figure 3 The illustrated embodiment provides the actions of the device for obtaining yellow page information.

[0140] The electronic device provided in an embodiment of the present application can execute a method for obtaining yellow page information provided in an embodiment of the present application. The implementation principle is similar and will not be repeated here.

[0141] Compared with the prior art, the embodiment of the present application uses the confidence weight of the source website of the yellow page information as the judgment standard for judging the credibility and accuracy of the yellow page information, and uses the yellow page information with the highest confidence weighted result of the source website as the yellow page information of the telephone number to be queried, thereby achieving the purpose of determining the yellow page information with high accuracy and credibility from a large amount of messy search data, so that the user can obtain the yellow page information with high accuracy and credibility that matches the queried telephone number through a one-step quick query of the search engine, thereby improving the user's query experience.

[0142] Another embodiment of the present application provides a computer-readable storage medium, which is used to store computer instructions. When the computer instructions are executed on a computer, the computer can execute the yellow page information acquisition method provided by one embodiment of the present application.

[0143] An embodiment of the present application provides a computer-readable storage medium applicable to the yellow page information acquisition method provided in one embodiment of the present application above. The implementation principle is similar and will not be repeated here.

[0144] Compared with the prior art, the embodiment of the present application uses the confidence weight of the source website of the yellow page information as the judgment standard for judging the credibility and accuracy of the yellow page information, and uses the yellow page information with the highest confidence weighted result of the source website as the yellow page information of the telephone number to be queried, thereby achieving the purpose of determining the yellow page information with high accuracy and credibility from a large amount of messy search data, so that the user can obtain the yellow page information with high accuracy and credibility that matches the queried telephone number through a one-step quick query of the search engine, thereby improving the user's query experience.

[0145] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0146] The above is only a partial implementation method 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 present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for obtaining yellow page information, characterized in that: include: Searching the telephone number to be queried through a search engine to obtain multiple web pages containing the telephone number to be queried; Extracting yellow page information to be selected from the plurality of web pages by using a pre-trained recognition model; Determining the confidence weight of the source website of at least one web page corresponding to the yellow pages information to be selected; For any yellow page information to be selected, weighted calculation is performed according to the confidence weight of the source website where at least one webpage corresponding to it is located, to obtain a weighted result; Determine the yellow page information with the largest weighted result as the yellow page information of the telephone number to be queried; Wherein, the step of determining the confidence weight of the source website of at least one web page corresponding to the yellow pages information to be selected includes: searching multiple sample telephone numbers of known yellow pages information through a search engine to obtain multiple web pages to be judged including each sample telephone number; extracting the yellow pages information to be judged from each web page to be judged through a pre-trained named entity recognition model; performing similarity calculation between any yellow pages information to be judged and the corresponding known yellow pages information; according to the calculated similarity, determining the confidence weight of the source website of the web page to be judged corresponding to any yellow pages information to be judged through the corresponding relationship between the similarity and the confidence weight, or determining the confidence weight of the source website of the web page to be judged corresponding to any yellow pages information to be judged through the corresponding relationship between the similarity range and the confidence weight; After determining the yellow page information with the largest weighted result as the yellow page information of the telephone number to be queried, the method further includes filtering the yellow page information in the web pages from the website blacklist by setting a website blacklist.

2. The method for obtaining yellow page information according to claim 1, characterized in that: The pre-trained recognition model includes any of the following: Pre-trained named entity recognition models; A set of regular expressions trained based on labeled data.

3. The method for obtaining yellow page information according to claim 1, characterized in that: Before performing weighted calculation for any yellow page information to be selected according to the confidence weight of the source website where at least one webpage corresponding thereto is located, the method further includes: Determine the confidence weight of each source website.

4. The method for obtaining yellow page information according to claim 3, characterized in that: Determining the confidence weight of each source website includes: Searching multiple sample phone numbers of known yellow page information through a search engine to obtain multiple web pages to be judged including each sample phone number; Through the pre-trained named entity recognition model, the yellow page information to be judged is extracted from each web page to be judged; Calculate the similarity between any yellow page information to be judged and the corresponding known yellow page information; According to the calculated similarity, the confidence weight of the source website of the web page to be determined corresponding to any yellow page information to be determined is determined.

5. The method for obtaining yellow page information according to claim 4, characterized in that: The similarity calculation between any yellow page information to be determined and corresponding known yellow page information includes: Performing word segmentation processing on the yellow page information to be determined and the corresponding known yellow page information respectively, and obtaining feature information of the yellow page information to be determined and feature information of the known yellow page information; A similarity calculation is performed between the feature information of the yellow pages information to be determined and the feature information of the known yellow pages information.

6. The method for obtaining yellow page information according to claim 5, characterized in that: The characteristic information includes: Personal or business name, phone number, address.

7. The method for obtaining yellow page information according to any one of claims 1 to 6, characterized in that: The method further includes: Filter the obtained yellow pages information.

8. A yellow page information acquisition device, characterized in that: include: A query module, used to query the telephone number to be queried through a search engine to obtain multiple web pages containing the telephone number to be queried; An extraction module, used for extracting yellow page information to be selected from the plurality of web pages obtained by the query module through a pre-trained recognition model; A confidence weight determination module, used to determine the confidence weight of the source website of at least one web page corresponding to the yellow page information to be selected; A weighted calculation module, used for performing weighted calculation on any yellow page information to be selected extracted by the extraction module according to the confidence weight of the source website where at least one webpage corresponding thereto is located, to obtain a weighted result; A determination module, used for determining the yellow page information to be selected with the largest weighted result obtained by the weighted calculation module as the yellow page information of the telephone number to be queried; The confidence weight determination module is specifically used for: searching multiple sample telephone numbers of known yellow page information through a search engine to obtain multiple web pages to be judged including each sample telephone number; extracting yellow page information to be judged from each web page to be judged through a pre-trained named entity recognition model; performing similarity calculation between any yellow page information to be judged and the corresponding known yellow page information; according to the calculated similarity, determining the confidence weight of the source website of the web page to be judged corresponding to any yellow page information to be judged through the corresponding relationship between the similarity and the confidence weight, or determining the confidence weight of the source website of the web page to be judged corresponding to any yellow page information to be judged through the corresponding relationship between the similarity range and the confidence weight; Wherein, the yellow page information acquisition device is further used for filtering the yellow page information in the web pages from the website blacklist by setting a website blacklist.

9. The yellow page information acquisition device according to claim 8, characterized in that: The pre-trained recognition model includes any of the following: Pre-trained named entity recognition models; A set of regular expressions trained based on labeled data.

10. The yellow page information acquisition device according to claim 8, characterized in that: The device also includes a confidence weight determination module for determining the confidence weights of various source websites before weighted calculation is performed on any yellow page information to be selected extracted by the extraction module according to the confidence weights of the source website where at least one corresponding web page is located.

11. The yellow page information acquisition device according to claim 10, characterized in that: The confidence weight determination module comprises: A search unit, used to search multiple sample phone numbers of known yellow page information through a search engine to obtain multiple web pages to be judged including each sample phone number; An extraction unit, used to extract yellow page information to be determined from each web page to be determined obtained by the search unit through a pre-trained named entity recognition model; A similarity calculation unit, used for calculating the similarity between any yellow page information to be determined extracted by the extraction unit and corresponding known yellow page information; The confidence weight determination unit is used to determine the confidence weight of the source website where the web page to be determined corresponding to any yellow page information to be determined is located according to the similarity calculated and determined by the similarity calculation unit.

12. The yellow page information acquisition device according to claim 11, characterized in that: The similarity calculation unit comprises: A word segmentation processing subunit is used to perform word segmentation processing on the yellow page information to be determined and the corresponding known yellow page information respectively, and obtain feature information of the yellow page information to be determined and feature information of the known yellow page information; The similarity calculation subunit is used to calculate the similarity between the feature information of the yellow page information to be determined and the feature information of the known yellow page information.

13. The yellow page information acquisition device according to claim 12, characterized in that: The characteristic information includes: Personal or business name, phone number, address.

14. The yellow page information acquisition device according to any one of claims 8 to 13, characterized in that: The device also includes: The filtering module is used to filter the obtained yellow page information.

15. An electronic device, characterized in that: The electronic device includes: processor, memory, and bus; The bus is used to connect the processor and the memory; The memory is used to store operation instructions; The processor is used to execute the yellow page information acquisition method described in any one of claims 1 to 7 by calling the operation instruction.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store computer instructions. When the computer instructions are executed on a computer, the computer can execute the yellow page information acquisition method described in any one of claims 1 to 7.

Images