Non-standard format house property certificate identification method, apparatus and device, and storage medium

Abstract

The invention discloses a non-standard format house property certificate identification method, device and equipment and a storage medium, and the method comprises the steps: obtaining a house property certificate material uploaded in an examination and approval service system, carrying out the traversal of all house property certificate files under the house property certificate material through an OCR algorithm, and extracting the house property certificate number of each house property certificate file; if the type of the house property certificate file is an immobile property certificate, acquiring a house detailed address corresponding to the house property certificate file by adopting an OCR algorithm, and identifying target attribute information of the house property certificate file; if the type of the house property certificate file is other types except a house location certificate, a house right certificate and an immobile property certificate, determining a house detailed address corresponding to the house property certificate file according to a similarity algorithm, and identifying target attribute information of the house property certificate file; and carrying out statistics on all the obtained house detailed addresses, and determining a target house detailed address corresponding to the house property certificate material according to a statistical result. According to the technical scheme of the embodiment of the invention, the identification accuracy of the house property certificate material can be improved, and the processing efficiency of the house property certificate material approval service is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, equipment and storage medium for identifying a non-standard format real estate certificate. Background Art

[0002] At present, when banks review real estate certificate materials, they have introduced Robotic Process Automation (RPA) technology. This technology, combined with the Optical Character Recognition (OCR) algorithm, realizes the intelligent review and entry of users' real estate materials. The staff only needs to enter a small amount of information and scan and upload the paper materials to the approval system. The back-end digital employee RPA will automatically review and enter. This method greatly improves the work efficiency of the staff, and also greatly shortens the review cycle of real estate materials, providing users with better services.

[0003] However, in practice, it is found that the real estate materials uploaded to the approval system may include non-real estate certificate image files, and old real estate certificates are contaminated by oil and other pollution and interfered by stamps. Therefore, the existing OCR algorithm has a relatively low recognition accuracy for image information related to real estate certificates. An effective technical means is urgently needed to optimize the recognition results of the OCR algorithm. Summary of the invention

[0004] The present invention provides a method, device, equipment and storage medium for identifying real estate certificates in non-standard formats, and provides a method for intelligently identifying and extracting real estate certificate information from a large number of real estate certificates and non-standard real estate certificate image files. Compared with the prior art method of relying on a single OCR algorithm to determine the recognition result, the recognition accuracy of real estate certificate materials can be improved, thereby releasing more human resources and improving the processing efficiency of real estate certificate material approval business.

[0005] According to one aspect of the present invention, a method for identifying a non-standard format real estate certificate is provided, the method comprising:

[0006] Obtain the real estate certificate materials pre-uploaded in the approval business system, use the OCR algorithm to traverse all real estate certificate files under the real estate certificate materials, and extract the real estate certificate number in each real estate certificate file;

[0007] If the type of the real estate certificate document is a real estate certificate, an OCR algorithm is used to obtain the detailed address of the house corresponding to the real estate certificate document, and identify the target attribute information corresponding to the real estate certificate document;

[0008] If the type corresponding to the real estate certificate document is other than a real estate certificate, a house ownership certificate, or a real estate ownership certificate, then determining the detailed address of the house corresponding to the real estate certificate document according to a preset similarity algorithm, and identifying the target attribute information corresponding to the real estate certificate document;

[0009] Count all the house addresses obtained, and determine the target house address corresponding to the real estate certificate material based on the statistical results.

[0010] Optionally, extract the property certificate number from each property certificate document, including:

[0011] Extract the real estate certificate number from each real estate certificate file according to the different strings corresponding to the preset different real estate certificate types;

[0012] The character string includes the type of real estate certificate and a preset separator.

[0013] Optionally, determining the detailed address of the house corresponding to the real estate certificate document according to a preset similarity algorithm includes:

[0014] Obtain the first house detailed address identified by the OCR algorithm on the real estate certificate document, and obtain the second house detailed address currently recorded in the real estate certificate attribute table;

[0015] Determining a first similarity between the first house address and a preset address keyword, and determining a second similarity between the second house address and the preset address keyword;

[0016] If the first similarity is greater than the second similarity, the first house address is used as the current house address in the property certificate attribute table.

[0017] Optionally, identifying the target attribute information corresponding to the real estate certificate document includes:

[0018] Identify the land nature, floor area, building area, land use expiration date, seller's ID number and seller's name corresponding to the real estate certificate document.

[0019] Optionally, identifying the land use expiration date corresponding to the real estate certificate document includes:

[0020] Obtaining the original land use expiration date identified by the OCR algorithm on the real estate certificate document, and replacing the keyword in the original land use expiration date;

[0021] A regular match is performed on the replaced termination date, and the target land use termination date corresponding to the real estate certificate document is determined based on the regular match result.

[0022] Optionally, all the house addresses obtained are counted, and according to the statistical results, the target house address corresponding to the real estate certificate material is determined, including:

[0023] The acquired house addresses are stored in a set of addresses, and the number of occurrences of each house address in the set of addresses is counted;

[0024] Determine whether the number of house addresses with the highest number of occurrences is one;

[0025] If yes, the house address with the highest number of occurrences is used as the target house address corresponding to the real estate certificate material;

[0026] If not, then determining the similarity between each of the house addresses with the highest number of occurrences and the preset address keyword according to a preset similarity algorithm;

[0027] According to the similarity, the detailed address of the target house corresponding to the real estate certificate material is determined.

[0028] Optionally, determining the detailed address of the target house corresponding to the real estate certificate material according to the similarity includes:

[0029] Determine whether the number of house addresses with the highest similarity is one;

[0030] If so, the house address with the highest similarity is used as the target house address corresponding to the real estate certificate material;

[0031] If not, the first house address with the highest similarity is obtained, and the first house address with the highest similarity is used as the target house address corresponding to the real estate certificate material.

[0032] According to another aspect of the present invention, a non-standard format real estate certificate recognition device is provided, the device comprising:

[0033] The file traversal module is used to obtain the real estate certificate materials pre-uploaded in the approval business system, use the OCR algorithm to traverse all the real estate certificate files under the real estate certificate materials, and extract the real estate certificate number in each real estate certificate file;

[0034] An attribute recognition module is used to use an OCR algorithm to obtain the detailed address of the house corresponding to the real estate certificate document if the type corresponding to the real estate certificate document is a real estate certificate, and to identify the target attribute information corresponding to the real estate certificate document;

[0035] The attribute recognition module is further configured to determine the detailed address of the house corresponding to the real estate certificate document according to a preset similarity algorithm and identify the target attribute information corresponding to the real estate certificate document if the type corresponding to the real estate certificate document is other than a real estate certificate, a house ownership certificate, or a real estate ownership certificate;

[0036] The house address determination module is used to collect statistics of all the house addresses obtained, and determine the target house address corresponding to the real estate certificate material based on the statistical results.

[0037] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0038] at least one processor; and

[0039] a memory communicatively connected to the at least one processor; wherein,

[0040] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the non-standard format real estate certificate identification method described in any embodiment of the present invention.

[0041] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the non-standard format real estate certificate identification method described in any embodiment of the present invention when executed.

[0042] The technical solution provided by the embodiment of the present invention obtains the real estate certificate materials pre-uploaded in the approval business system, adopts the OCR algorithm to traverse all the real estate certificate files under the real estate certificate materials, extracts the real estate certificate number in each real estate certificate file, and if the type corresponding to the real estate certificate file is a real estate title certificate, adopts the OCR algorithm to obtain the house address corresponding to the real estate certificate file, and identifies the target attribute information corresponding to the real estate certificate file; if the type corresponding to the real estate certificate file is other types except the real estate certificate, the house title certificate, and the real estate title certificate, the house address corresponding to the real estate certificate file is determined according to the preset similarity algorithm, and the target attribute information corresponding to the real estate certificate file is identified, and all the house addresses obtained are counted, and a technical means for determining the target house address corresponding to the real estate certificate material according to the statistical results is provided, and a method for intelligently identifying and extracting real estate certificate information from a large number of real estate certificates and non-standard real estate certificate image files is provided, and compared with the method of the prior art that relies on a single OCR algorithm to determine the recognition result, the recognition accuracy of the real estate certificate material can be improved, thereby releasing more human resources and improving the processing efficiency of the entire real estate certificate material approval business.

[0043] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 is a flow chart of a method for identifying a non-standard format real estate certificate provided according to an embodiment of the present invention;

[0046] Figure 2 is a flow chart of another method for identifying a non-standard format real estate certificate provided according to an embodiment of the present invention;

[0047] Figure 3 is a flow chart of another method for identifying a non-standard format real estate certificate provided according to an embodiment of the present invention;

[0048] Figure 4 It is a structural schematic diagram of a non-standard format real estate certificate recognition device provided according to an embodiment of the present invention;

[0049] Figure 5 It is a structural schematic diagram of an electronic device for implementing the non-standard format real estate certificate recognition method of an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0051] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0052] Figure 1This is a flowchart of a non-standard format real estate certificate recognition method provided by an embodiment of the present invention. This embodiment is applicable to the situation where a bank recognizes and enters non-standard format real estate certificate information. The method can be executed by a non-standard format real estate certificate recognition device. The non-standard format real estate certificate recognition device can be implemented in the form of hardware and / or software. The non-standard format real estate certificate recognition device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0053] Step 110: obtain the real estate certificate materials pre-uploaded in the approval business system, use the OCR algorithm to traverse all the real estate certificate files under the real estate certificate materials, and extract the real estate certificate number in each real estate certificate file.

[0054] In this embodiment, optionally, the digital employee RPA can be used to log in to the retail credit centralized approval business system to obtain the real estate certificate materials in non-standard format pre-uploaded by the bank staff on the system. The real estate certificate materials may include images of the real estate certificate, screenshots of online query results of the real estate certificate, and related image files of non-real estate certificate information.

[0055] In this step, specifically, after obtaining the real estate certificate materials, the OCR algorithm can be used to traverse all the real estate certificate files under the real estate certificate materials in the order in which the real estate certificate files are uploaded, and extract the real estate certificate number and real estate certificate file type in each real estate certificate file according to the preset identifier.

[0056] Step 120: If the type of the real estate certificate document is a real estate ownership certificate, an OCR algorithm is used to obtain the detailed address of the house corresponding to the real estate certificate document, and identify the target attribute information corresponding to the real estate certificate document.

[0057] In this embodiment, specifically, if the type corresponding to the real estate certificate document is a real estate certificate, a house ownership certificate or a real estate ownership certificate, the extracted real estate certificate number can be used as the final real estate certificate number of the real estate certificate document.

[0058] If the type of the real estate certificate is a real estate certificate, an OCR algorithm can be used to obtain the house address corresponding to the real estate certificate, and the target attribute information corresponding to the real estate certificate can be identified according to a preset attribute extraction algorithm. The target attribute information can be the property attribute information corresponding to the real estate certificate.

[0059] Step 130: If the type corresponding to the real estate certificate document is other than a real estate certificate, a house ownership certificate, or a real estate ownership certificate, the detailed address of the house corresponding to the real estate certificate document is determined according to a preset similarity algorithm, and the target attribute information corresponding to the real estate certificate document is identified.

[0060] In this embodiment, optionally, if the type corresponding to the real estate certificate document is other types, the house address corresponding to the real estate certificate document can be determined based on the house address identified by the OCR algorithm and a preset similarity algorithm (such as a cosine similarity algorithm or an Euclidean distance algorithm, etc.), and the target attribute information corresponding to the real estate certificate document can be identified based on a preset attribute extraction algorithm.

[0061] Step 140: Count all the acquired house addresses, and determine the target house address corresponding to the real estate certificate material based on the statistical results.

[0062] In this step, optionally, all house addresses obtained in steps 120-130 may be obtained, and then the final house address (ie, the target house address) corresponding to the real estate certificate material may be determined according to the number of occurrences of each house address.

[0063] In this embodiment, after obtaining the real estate certificate number, target attribute information and target house address corresponding to the real estate certificate document through the above steps, the digital employee RPA can be used to automatically enter the above information into the approval business system.

[0064] The technical solution provided by the embodiment of the present invention obtains the real estate certificate materials pre-uploaded in the approval business system, adopts the OCR algorithm to traverse all the real estate certificate files under the real estate certificate materials, extracts the real estate certificate number in each real estate certificate file, and if the type corresponding to the real estate certificate file is a real estate title certificate, adopts the OCR algorithm to obtain the house address corresponding to the real estate certificate file, and identifies the target attribute information corresponding to the real estate certificate file; if the type corresponding to the real estate certificate file is other types except the real estate certificate, the house title certificate, and the real estate title certificate, the house address corresponding to the real estate certificate file is determined according to the preset similarity algorithm, and the target attribute information corresponding to the real estate certificate file is identified, and all the house addresses obtained are counted, and a technical means for determining the target house address corresponding to the real estate certificate material according to the statistical results is provided, and a method for intelligently identifying and extracting real estate certificate information from a large number of real estate certificates and non-standard real estate certificate image files is provided, and compared with the method of the prior art that relies on a single OCR algorithm to determine the recognition result, the recognition accuracy of the real estate certificate material can be improved, thereby releasing more human resources and improving the processing efficiency of the entire real estate certificate material approval business.

[0065] Figure 2 A flowchart of another non-standard format real estate certificate recognition method provided by an embodiment of the present invention, such as Figure 2 As shown, the method includes:

[0066] Step 210: Obtain the real estate certificate materials pre-uploaded in the approval business system, and use the OCR algorithm to traverse all real estate certificate files under the real estate certificate materials.

[0067] In this embodiment, after obtaining the real estate certificate materials, the attribute table of the real estate certificate materials (including real estate certificate number, land nature, house address, floor area, building area, seller's ID number, seller's name, land use termination date) can be set to empty first, and then the OCR algorithm can be used to traverse all real estate certificate files under the real estate certificate materials.

[0068] Step 220: extract the real estate certificate number from each real estate certificate file according to different preset character strings corresponding to different real estate certificate types; the character string includes the real estate certificate type and a preset separator.

[0069] In a specific embodiment, the real estate certificate number in each real estate certificate file may be extracted according to the following real estate certificate number extraction algorithm:

[0070] Extract the property certificate number of the real estate certificate based on the string starting with "number + real estate certificate" and ending with "number"; extract the property certificate number of the property certificate based on the string starting with "house ownership certificate" and ending with "number"; extract the property certificate number of the real estate certificate based on the string starting with the provincial abbreviation and ending with "number".

[0071] In this step, after obtaining the real estate certificate number in each real estate certificate document, if the real estate certificate number contains "land certificate", the corresponding real estate certificate document type is a real estate certificate; if the real estate certificate number contains "right certificate", the corresponding real estate certificate document type is a house right certificate; if the real estate certificate number contains "movable right", the corresponding real estate certificate document type is a real estate right certificate.

[0072] In this embodiment, if the type corresponding to the real estate certificate document is a real estate certificate, a house ownership certificate or a real estate ownership certificate, the real estate certificate number of the above-mentioned extraction number can be assigned to the real estate certificate number in the attribute table.

[0073] Step 230: If the type of the real estate certificate document is a real estate ownership certificate, an OCR algorithm is used to obtain the detailed address of the house corresponding to the real estate certificate document.

[0074] Step 240: If the type corresponding to the real estate certificate document is other than a real estate certificate, a house ownership certificate, or a real estate ownership certificate, obtain the first house address identified by the OCR algorithm for the real estate certificate document, and obtain the second house address currently recorded in the real estate certificate attribute table.

[0075] In this embodiment, if there is no real estate certificate number on the real estate certificate document or the real estate certificate number is not recognized, it can be considered that the type corresponding to the real estate certificate document is other than the real estate certificate, the house ownership certificate, and the real estate ownership certificate. In this case, the first house address recognized by the OCR algorithm for the real estate certificate document can be obtained, and the second house address currently recorded in the real estate certificate attribute table can be obtained.

[0076] Step 250: Determine a first similarity between the first house address and a preset address keyword, and determine a second similarity between the second house address and a preset address keyword.

[0077] In this embodiment, a preset house address similarity algorithm may be used to compare the similarity between the house address and preset keywords. Specifically, the preset keywords may include: province, city, district, county, town, township, village, street, office, number, building, building, #, unit, attached, garden, flower garden, etc. If the house address to be compared contains one of the keywords, the corresponding similarity value is increased by one, and repeated keywords are calculated as one keyword.

[0078] Step 260: If the first similarity is greater than the second similarity, the first house address is used as the current house address in the property certificate attribute table.

[0079] Step 270: Identify the target attribute information corresponding to the real estate certificate document.

[0080] In one implementation of this embodiment, identifying the target attribute information corresponding to the real estate certificate document includes: identifying the land nature, floor area, building area, land use termination date, seller's ID number and seller's name corresponding to the real estate certificate document.

[0081] In a specific embodiment, a preset land nature extraction algorithm can be used to extract the land nature corresponding to the real estate certificate document. If the real estate certificate number recognized by the OCR algorithm contains "allocation" or "transfer", the corresponding land nature is "allocation"; if it contains "out" or "transfer", the corresponding land nature is "transfer", otherwise it is empty.

[0082] In a specific embodiment, a preset house area extraction algorithm may be used to extract the floor area and building area corresponding to the real estate certificate document, including the following steps:

[0083] Step 21, obtain the area recognized by the OCR algorithm, and use the decimal in the area as the house area. If the house area extraction fails, obtain the characters before the "dot" in the area recognized by the OCR algorithm as the integer part of the house area. For example, if the area recognized by the OCR algorithm is: 10,203,000.435, then use 10,203,000 as the integer part of the house area.

[0084] Step 22: Replace the traditional Chinese numerals in the integer part recognition content with simplified Chinese. For example, the integer part recognition content is: 10,020,000,300, and the content after replacement is: 10,200,300;

[0085] Step 23: Split the Chinese text according to decimal units, and replace the simplified Chinese numerals except decimal units with numbers. For example, for the content "one thousand and twenty thousand three thousand", the replaced content is "1 thousand 02 ten thousand 3 thousand";

[0086] Step 24: Enclose the converted numbers in parentheses, then add a closing parenthesis between two consecutive decimal units, and add an opening parenthesis after it. If the last two characters after replacement are "()", then remove the last "()". For example, for the content "1 thousand 02 ten thousand 3 thousand", the replaced content is "(1 thousand 02 ten) ten thousand (3 thousand)";

[0087] Step 25: Remove the 0s in the replaced characters. For example, for the content "1 thousand 02 ten thousand 3 thousand", the replaced content is "1 thousand 2 ten thousand 3 thousand";

[0088] Step 26: Determine whether there are still numbers after each decimal unit. If so, replace the decimal units with (*decimal unit+), and if not, replace the decimal units with (*decimal unit). For example, for the content "(1 thousand 2 ten) ten thousand (3 thousand)", the replaced content is "(1*1000 + 2*10)*10000+(3*1000)";

[0089] Step 27: Calculate the integer part of the套内面积 (inner area) according to the operation rules. For example, for the content "(1*1000 + 2*10)*10000+(3*1000)", the calculated content is "10203000";

[0090] Step 28: Change the complex writing of the part after the decimal point to simplified writing. For example, for the content "肆叁伍", the replaced content is "四三五";

[0091] Step 29: Change the simplified decimal part to numbers. For example, for the content "四三五", the replaced content is "435";

[0092] Step 30: Concatenate the converted integer part and decimal part, separated by a decimal point. For example, for the content "10203000" and "435", the concatenated content is "10203000.435".

[0093] In a specific embodiment, a preset land use termination date extraction algorithm can be used to extract the land use termination date corresponding to the property ownership certificate file, including: obtaining the original land use termination date recognized by the OCR algorithm for the property ownership certificate file, and replacing the keywords in the original land use termination date; performing regular matching on the replaced termination date, and determining the target land use termination date corresponding to the property ownership certificate file according to the regular matching result.

[0094] For example, in the original land use termination date recognized by the OCR algorithm, the characters "目" and "且" can be replaced with "month", and the character "曰" can be replaced with "day". Then, the content after replacement can be extracted as the final land use termination date (i.e., the target land use termination date) by using regular matching method.

[0095] In a specific embodiment, a preset algorithm for extracting the seller's identification number can be adopted to extract the seller's identification number corresponding to the real estate certificate file, including: obtaining the seller's identification number recognized by the OCR algorithm, and using regular matching method to extract all 15-digit or 18-digit ID card numbers (the last digit can be X or x).

[0096] Step 280: Count all the detailed addresses of the houses obtained, and determine the target detailed address of the real estate certificate material according to the statistical result.

[0097] In an implementation manner of this embodiment, counting all the detailed addresses of the houses obtained, and determining the target detailed address of the real estate certificate material according to the statistical result, includes: storing all the obtained detailed addresses of the houses in a detailed address set, and counting the occurrence times corresponding to each detailed address in the detailed address set; judging whether the number of the detailed addresses with the highest occurrence times is one; if so, using the detailed address with the highest occurrence times as the target detailed address corresponding to the real estate certificate material; if not, determining the similarity between each of the detailed addresses with the highest occurrence times and a preset address keyword according to a preset similarity algorithm, and determining the target detailed address of the real estate certificate material according to the similarity.

[0098] In a specific embodiment, determining the target detailed address of the real estate certificate material according to the similarity includes: judging whether the number of the detailed addresses with the highest similarity is one; if so, using the detailed address with the highest similarity as the target detailed address corresponding to the real estate certificate material; if not, obtaining the first detailed address with the highest similarity, and using the first detailed address with the highest similarity as the target detailed address corresponding to the real estate certificate material.

[0099] The technical solution provided by the embodiment of the present invention obtains the real estate certificate materials pre-uploaded in the approval business system, uses the OCR algorithm to traverse all the real estate certificate files under the real estate certificate materials, extracts the real estate certificate number in each real estate certificate file according to different character strings corresponding to different preset real estate certificate types, and if the type corresponding to the real estate certificate file is a real estate certificate, uses the OCR algorithm to obtain the house address, if the type corresponding to the real estate certificate file is other types except the real estate certificate, the house certificate, and the real estate certificate, obtains the first house address identified by the OCR algorithm for the real estate certificate file, obtains the second house address currently recorded in the real estate certificate attribute table, determines the first similarity between the first house address and the preset address keyword, determines the second similarity between the second house address and the preset address keyword, if the first similarity is greater than the second similarity, uses the first house address as the current house address in the real estate certificate attribute table, identifies the target attribute information corresponding to the real estate certificate file, counts all the acquired house addresses, and determines the target house address corresponding to the real estate certificate material according to the statistical results. The technical means can improve the recognition accuracy of the real estate certificate material and improve the processing efficiency of the real estate certificate material approval business.

[0100] Figure 3 A flowchart of another non-standard format real estate certificate recognition method provided by an embodiment of the present invention, such as Figure 3 As shown, the method includes:

[0101] Step 1: Set the property certificate attribute table C (including property certificate number, land nature, house address, floor area, building area, seller's ID number, seller's name, land use termination date) to be empty;

[0102] Step 2: RPA simulates manual login to the retail credit centralized approval business system to download all the information affecting the real estate certificate;

[0103] Step 3: Traverse all the image data in all the real estate certificate folders in turn;

[0104] Step 4: Call OCR to identify each file in each real estate certificate document folder;

[0105] Step 5: Extract the certificate number in each real estate certificate document using the real estate certificate number extraction algorithm;

[0106] Step 6: If the property certificate type is a real estate certificate or a house ownership certificate, assign the property certificate number of the extracted number to the property certificate number in the attribute table, and then return to step 4;

[0107] Step 7: If the property certificate type is real estate certificate, assign the property certificate number of the extraction number to the property certificate number in the attribute table, and then execute step 8;

[0108] Step 8: If the house address in the attribute table is empty, assign the house address identified by the OCR algorithm to the house address in the attribute table, otherwise no processing is performed;

[0109] Step 9: If the type of the real estate certificate is other than the real estate certificate, the house ownership certificate, and the real estate ownership certificate, then obtain the similarity N between the house address recognized by the OCR algorithm and the preset address keyword, and obtain the similarity M between the house address currently recorded in the real estate certificate attribute table and the preset address keyword;

[0110] Step 10: Determine whether N is greater than M. If so, execute step 11; if not, return to execute step 4;

[0111] Step 11: Assign the house address identified by the OCR algorithm to the house address in the attribute table;

[0112] Step 12: Store all the acquired house addresses in the address set L;

[0113] Step 13: If the land property in the attribute table C is empty, the OCR algorithm recognition result is processed using a preset land property extraction algorithm;

[0114] Step 14: If the area of ​​the unit in the attribute table C is empty, the preset house area extraction algorithm is used to process the OCR algorithm recognition result;

[0115] Step 15: If the building area in the attribute table C is empty, the preset house area extraction algorithm is used to process the OCR algorithm recognition result;

[0116] Step 16: If the land use expiration date in the attribute table C is empty, the OCR algorithm recognition result is processed using the preset land use expiration date extraction algorithm;

[0117] Step 17: Using a preset seller ID number extraction algorithm, process the seller ID number identified by OCR to obtain the ID number Number;

[0118] Step 18: Determine whether the seller's ID number in attribute table C is empty, or whether Number contains the seller's ID number in attribute table C. If so, execute step 19; if not, execute step 22;

[0119] Step 19: Assign the seller's ID number in attribute table C to Number;

[0120] Step 20: Determine whether the seller's name in attribute table C is empty, or whether the seller's name identified by the OCR algorithm includes the seller's name in attribute table C. If so, execute step 21; if not, execute step 22;

[0121] Step 21: assign the seller's name in attribute table C to the seller's name identified by the OCR algorithm;

[0122] Step 22: Determine whether the traversal of all real estate certificate documents is completed. If so, execute step 23. If not, return to execute step 4.

[0123] Step 23: Count the number of occurrences of each house address in the address set L;

[0124] Step 24: Determine whether the number of house addresses with the highest number of occurrences is one, if so, execute step 25, if not, execute step 26;

[0125] Step 25: Assign the house address in the attribute table C to the house address in the address set L;

[0126] Step 26: Using a preset house address similarity algorithm, obtain the similarity between each house address with the highest number of occurrences and the preset address keyword;

[0127] Step 27: Determine whether the number of house addresses with the highest similarity is one, if so, execute step 28, if not, execute step 29;

[0128] Step 28: assign the house address in attribute table C to the house address with the highest similarity;

[0129] Step 29: Assign the house address in attribute table C to the first house address with the highest similarity.

[0130] The technical solution provided by the embodiment of the present invention can improve the recognition accuracy of real estate certificate materials and improve the processing efficiency of real estate certificate material approval business through the above-mentioned technical means.

[0131] Figure 4 The present invention provides a structural diagram of a non-standard format real estate certificate recognition device, which is applied to electronic devices such as Figure 4 As shown, the device includes: a file traversal module 410, an attribute identification module 420 and a house address determination module 430.

[0132] The file traversal module 410 is used to obtain the real estate certificate materials pre-uploaded in the approval business system, use the OCR algorithm to traverse all the real estate certificate files under the real estate certificate materials, and extract the real estate certificate number in each real estate certificate file;

[0133] The attribute recognition module 420 is used to use an OCR algorithm to obtain the detailed address of the house corresponding to the real estate certificate document and recognize the target attribute information corresponding to the real estate certificate document if the type corresponding to the real estate certificate document is a real estate certificate;

[0134] The attribute identification module 420 is further configured to determine the detailed address of the house corresponding to the real estate certificate document according to a preset similarity algorithm and identify the target attribute information corresponding to the real estate certificate document if the type corresponding to the real estate certificate document is other than a real estate certificate, a house ownership certificate, and a real estate ownership certificate;

[0135] The house address determination module 430 is used to collect statistics of all the acquired house addresses and determine the target house address corresponding to the real estate certificate material according to the statistical results.

[0136] The technical solution provided by the embodiment of the present invention obtains the real estate certificate materials pre-uploaded in the approval business system, adopts the OCR algorithm to traverse all the real estate certificate files under the real estate certificate materials, extracts the real estate certificate number in each real estate certificate file, and if the type corresponding to the real estate certificate file is a real estate title certificate, adopts the OCR algorithm to obtain the house address corresponding to the real estate certificate file, and identifies the target attribute information corresponding to the real estate certificate file; if the type corresponding to the real estate certificate file is other types except the real estate certificate, the house title certificate, and the real estate title certificate, the house address corresponding to the real estate certificate file is determined according to the preset similarity algorithm, and the target attribute information corresponding to the real estate certificate file is identified, and all the house addresses obtained are counted, and a technical means for determining the target house address corresponding to the real estate certificate material according to the statistical results is provided, and a method for intelligently identifying and extracting real estate certificate information from a large number of real estate certificates and non-standard real estate certificate image files is provided, and compared with the method of the prior art that relies on a single OCR algorithm to determine the recognition result, the recognition accuracy of the real estate certificate material can be improved, thereby releasing more human resources and improving the processing efficiency of the entire real estate certificate material approval business.

[0137] Based on the above embodiment, the file traversal module 410 includes:

[0138] The real estate certificate number extraction unit is used to extract the real estate certificate number in each real estate certificate file according to different character strings corresponding to different preset real estate certificate types; wherein the character string includes the real estate certificate type and a preset separator.

[0139] The attribute identification module 420 includes:

[0140] Other real estate certificate file processing units, used for obtaining the first house address identified by the OCR algorithm for the real estate certificate file and obtaining the second house address currently recorded in the real estate certificate attribute table if the type corresponding to the real estate certificate file is other than the real estate certificate, the house ownership certificate, and the real estate ownership certificate; determining a first similarity between the first house address and a preset address keyword, and determining a second similarity between the second house address and the preset address keyword; if the first similarity is greater than the second similarity, using the first house address as the current house address in the real estate certificate attribute table;

[0141] A real estate attribute identification unit, used to identify the land nature, floor area, building area, land use expiration date, seller's ID number and seller's name corresponding to the real estate certificate document;

[0142] A termination date replacement unit, used to obtain the original land use termination date identified by the OCR algorithm on the real estate certificate document, and replace the keyword in the original land use termination date;

[0143] The regular matching unit is used to perform regular matching on the replaced termination date, and determine the target land use termination date corresponding to the real estate certificate document according to the regular matching result.

[0144] The house address determination module 430 includes:

[0145] A frequency counting unit, used for storing all acquired house addresses in a detailed address set, and counting the number of occurrences corresponding to each house address in the detailed address set;

[0146] The house address determination unit is used to determine whether the number of the house address with the highest number of occurrences is one; if so, the house address with the highest number of occurrences is used as the target house address corresponding to the real estate certificate material; if not, the similarity between each of the house addresses with the highest number of occurrences and a preset address keyword is determined according to a preset similarity algorithm; and the target house address corresponding to the real estate certificate material is determined according to the similarity;

[0147] The similarity processing unit is used to determine whether the number of house addresses with the highest similarity is one; if so, the house address with the highest similarity is used as the target house address corresponding to the real estate certificate material; if not, the first house address with the highest similarity is obtained, and the first house address with the highest similarity is used as the target house address corresponding to the real estate certificate material.

[0148] The above device can execute the methods provided by all the above embodiments of the present invention, and has the corresponding functional modules and beneficial effects of executing the above methods. For technical details not fully described in the embodiments of the present invention, please refer to the methods provided by all the above embodiments of the present invention.

[0149] Figure 5A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0150] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0151] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0152] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for identifying a non-standard format real estate certificate.

[0153] In some embodiments, the non-standard format real estate certificate identification method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the non-standard format real estate certificate identification method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the non-standard format real estate certificate identification method in any other appropriate manner (for example, by means of firmware).

[0154] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0155] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0156] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0157] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0158] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0159] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0160] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0161] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying a non-standard format real estate certificate, characterized in that: The method comprises: Obtain the real estate certificate materials pre-uploaded in the approval business system, use the optical character recognition (OCR) algorithm to traverse all real estate certificate files under the real estate certificate materials, and extract the real estate certificate number in each real estate certificate file; If the type of the real estate certificate document is a real estate certificate, an OCR algorithm is used to obtain the detailed address of the house corresponding to the real estate certificate document, and identify the target attribute information corresponding to the real estate certificate document; If the type corresponding to the real estate certificate document is other than a real estate certificate, a house ownership certificate, or a real estate ownership certificate, then determining the detailed address of the house corresponding to the real estate certificate document according to a preset similarity algorithm, and identifying the target attribute information corresponding to the real estate certificate document; Count all the house addresses obtained, and determine the target house address corresponding to the real estate certificate material based on the statistical results.

2. The method according to claim 1, characterized in that Extract the real estate certificate number from each real estate certificate document, including: Extract the real estate certificate number from each real estate certificate file according to the different strings corresponding to the preset different real estate certificate types; The character string includes the type of real estate certificate and a preset separator.

3. The method according to claim 1, characterized in that Determining the detailed address of the house corresponding to the real estate certificate document according to a preset similarity algorithm includes: Obtain the first house detailed address identified by the OCR algorithm on the real estate certificate document, and obtain the second house detailed address currently recorded in the real estate certificate attribute table; Determining a first similarity between the first house address and a preset address keyword, and determining a second similarity between the second house address and the preset address keyword; If the first similarity is greater than the second similarity, the first house address is used as the current house address in the property certificate attribute table.

4. The method according to claim 1, characterized in that: Identify the target attribute information corresponding to the real estate certificate document, including: Identify the land nature, floor area, building area, land use expiration date, seller's ID number and seller's name corresponding to the real estate certificate document.

5. The method according to claim 4, characterized in that Identify the land use expiration date corresponding to the real estate certificate document, including: Obtaining the original land use expiration date identified by the OCR algorithm on the real estate certificate document, and replacing the keyword in the original land use expiration date; A regular match is performed on the replaced termination date, and the target land use termination date corresponding to the real estate certificate document is determined based on the regular match result.

6. The method according to claim 1, characterized in that Count all the house addresses obtained, and determine the target house address corresponding to the real estate certificate material based on the statistical results, including: The acquired house addresses are stored in a set of addresses, and the number of occurrences of each house address in the set of addresses is counted; Determine whether the number of house addresses with the highest number of occurrences is one; If so, the house address with the highest number of occurrences is used as the target house address corresponding to the real estate certificate material; If not, then determining the similarity between each of the house addresses with the highest number of occurrences and the preset address keyword according to a preset similarity algorithm; According to the similarity, the detailed address of the target house corresponding to the real estate certificate material is determined.

7. The method according to claim 6, characterized in that According to the similarity, determining the detailed address of the target house corresponding to the real estate certificate material includes: Determine whether the number of house addresses with the highest similarity is one; If so, the house address with the highest similarity is used as the target house address corresponding to the real estate certificate material; If not, the first house address with the highest similarity is obtained, and the first house address with the highest similarity is used as the target house address corresponding to the real estate certificate material.

8. A non-standard format real estate certificate recognition device, characterized in that: The device comprises: The file traversal module is used to obtain the real estate certificate materials pre-uploaded in the approval business system, use the optical character recognition (OCR) algorithm to traverse all the real estate certificate files under the real estate certificate materials, and extract the real estate certificate number in each real estate certificate file; An attribute recognition module is used to use an OCR algorithm to obtain the detailed address of the house corresponding to the real estate certificate document if the type corresponding to the real estate certificate document is a real estate certificate, and to identify the target attribute information corresponding to the real estate certificate document; The attribute recognition module is further configured to determine the detailed address of the house corresponding to the real estate certificate document according to a preset similarity algorithm and identify the target attribute information corresponding to the real estate certificate document if the type corresponding to the real estate certificate document is other than a real estate certificate, a house ownership certificate, or a real estate ownership certificate; The house address determination module is used to collect statistics of all the house addresses obtained, and determine the target house address corresponding to the real estate certificate material based on the statistical results.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the non-standard format real estate certificate identification method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the non-standard format real estate certificate identification method described in any one of claims 1-7 when executed.

Images