CN113822049B - Address auditing method, device, equipment and storage medium based on artificial intelligence - Google Patents
Address auditing method, device, equipment and storage medium based on artificial intelligence Download PDFInfo
- Publication number
- CN113822049B CN113822049B CN202111149201.4A CN202111149201A CN113822049B CN 113822049 B CN113822049 B CN 113822049B CN 202111149201 A CN202111149201 A CN 202111149201A CN 113822049 B CN113822049 B CN 113822049B
- Authority
- CN
- China
- Prior art keywords
- standard
- address
- pinyin
- address information
- element set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/226—Validation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3335—Syntactic pre-processing, e.g. stopword elimination, stemming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention relates to an artificial intelligence technology, and discloses an address auditing method based on artificial intelligence, which comprises the following steps: performing voice recognition on the voice address information to obtain text address information to be matched, and obtaining standard address information; performing word segmentation and pinyin conversion on the text address information to be matched and the standard address information to obtain a pinyin element set to be verified and a standard pinyin element set, matching each standard pinyin element with each pinyin element to be verified, and calculating an address matching score according to a matching result; when the address matching score is greater than or equal to a preset threshold value, the voice address information passes the auditing; and when the address matching score is smaller than a preset threshold, the voice address information does not pass the audit. In addition, the invention also relates to a block chain technology, and address information can be stored in nodes of the block chain. The invention further provides an address auditing device based on the artificial intelligence, electronic equipment and a storage medium. The invention can improve the address auditing efficiency.
Description
Technical Field
The present invention relates to the field of artificial intelligence technologies, and in particular, to an address auditing method, device, electronic device, and computer readable storage medium based on artificial intelligence.
Background
Along with the rapid development of financial loan business, a bank client initiates a loan application to a bank more and more frequently, and after the bank client initiates the loan application, the bank can execute a facing sign on the bank client through a facing sign personnel so as to confirm whether the data submitted by the bank client during the loan application is correct. When the face-label personnel executes the face-label, firstly, whether address information filled in by a bank client in the loan application is correct or not needs to be confirmed. Address information is generally longer, and the structure is complicated, and when the face tag personnel check, occupation time is longer, and along with the increase of the customer who applies for loan, the check pressure of face tag personnel increases, and this kind of manual check mode consumes a large amount of manpowers and inefficiency.
With the development of artificial intelligence, AI surface examination is now performed, the voice input by the client is primarily recognized as an address text by using a voice recognition module, and then the address text is matched with address information pre-filled by the client by using a text matching algorithm, but a word in an address answered by the client may be erroneously recognized as an wrongly written word with the same tone and the same tone by using the voice recognition module during AI surface examination, so that the matching result of the address is inaccurate, and the efficiency of AI surface examination is affected.
Disclosure of Invention
The invention provides an address auditing method and device based on artificial intelligence and a computer readable storage medium, and mainly aims to solve the problems that an artificial verification mode consumes a great deal of manpower and is low in efficiency, and the conventional AI surface auditing effect is not ideal.
In order to achieve the above object, the present invention provides an address auditing method based on artificial intelligence, comprising:
receiving voice address information input by a user, performing voice recognition on the voice address information to obtain text address information to be matched, and acquiring standard address information input by the user in advance from a preset database;
word segmentation is respectively carried out on the text address information to be matched and the standard address information to obtain an address element set to be verified and a standard address element set;
respectively performing pinyin conversion on the address element set to be verified and the standard address element set to obtain a pinyin element set to be verified and a standard pinyin element set, performing one-to-one matching on each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified to obtain a matching result, and calculating an address matching score between the text address information to be matched and the standard address information according to the matching result;
Comparing the address matching score with a preset threshold value, and judging whether the address matching score is smaller than the preset threshold value or not;
when the address matching score is greater than or equal to the preset threshold value, judging that the voice address information input by the user passes the audit;
and when the address matching score is smaller than the preset threshold value, judging that the voice address information input by the user does not pass the audit.
Optionally, the performing pinyin conversion on the address element set to be verified and the standard address element set to obtain the pinyin element set to be verified and the standard pinyin element set includes:
identifying the characters to be converted in the address element set to be verified and the standard address element set;
searching pinyin corresponding to the text to be converted in a pre-constructed text pinyin conversion comparison table;
and according to the positions of the characters to be converted in the address element set to be verified and the standard address element set, the pinyin corresponding to the characters to be converted is arranged to obtain the pinyin element set to be verified and the standard pinyin element set.
Optionally, the step of performing one-to-one matching between each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified to obtain a matching result includes:
Calculating the edit distance between each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified by using a pre-constructed edit distance calculation formula to obtain an edit distance set;
selecting the minimum editing distance corresponding to each standard pinyin element in the standard pinyin element set from the editing distance set;
and calculating the element matching score of each standard pinyin element in the standard pinyin element set by using a pre-constructed element matching score formula and the minimum editing distance, and obtaining the matching result according to the element matching score.
Optionally, the obtaining the matching result according to the element matching score includes:
judging whether the element matching score is smaller than a preset matching threshold value or not;
and if the element matching score is smaller than the matching threshold value, setting the element matching score to be zero.
If the element matching score is greater than or equal to the matching threshold, keeping the element matching score unchanged;
and collecting the standard pinyin elements with non-zero element matching scores to obtain a matching result.
Optionally, the calculating the address matching score between the text address information to be matched and the standard address information according to the matching result includes:
Judging character attributes of each standard pinyin element in the matching result;
extracting a first standard pinyin element subset with character attributes of Chinese characters from the matching result, calculating the character length proportion of each standard pinyin element in the first standard pinyin element subset to all standard pinyin elements in the first standard pinyin element subset, and calculating the weight factor of each standard pinyin element in the first standard pinyin element subset according to the character length proportion;
extracting a second standard pinyin element subset with character attributes of non-Chinese characters from the matching result, and calculating a weight factor of each standard pinyin element in the second standard pinyin element subset by utilizing a pre-constructed element normalization function and the character position of each standard pinyin element in the second standard pinyin element subset in the standard address element set;
and calculating the matching score between the text address information to be matched and the standard address information according to the element matching score and the weight factor.
Optionally, the calculating the matching score between the text address information to be matched and the standard address information according to the element matching score and the weight factor includes:
Calculating the matching score of the first standard pinyin subset by utilizing the element matching score and the weight factor of each standard pinyin element in the first standard pinyin subset;
calculating the matching score of the second standard pinyin subset by utilizing the element matching score and the weight factor of each standard pinyin element in the second standard pinyin subset;
and obtaining the matching score between the text address information to be matched and the standard address information according to the matching score of the first standard pinyin subset and the matching score of the second standard pinyin subset.
Optionally, the word segmentation is performed on the text address information to be matched and the standard address information to obtain an address element set to be verified and a standard address element set, which includes:
performing redundancy elimination operation on the text address information to be matched and the standard address information, and performing format conversion on the text address information to be matched and the standard address information after the redundancy elimination operation;
and respectively word-dividing the text address information to be matched and the standard address information after format conversion by using a pre-constructed resultant word-dividing algorithm to obtain an address element set to be verified and a standard address element set.
In order to solve the above problems, the present invention further provides an address auditing device based on artificial intelligence, the device comprising:
the voice address recognition module is used for receiving voice address information input by a user, carrying out voice recognition on the voice address information to obtain text address information to be matched, and acquiring standard address information input in advance by the user from a preset database;
the text address word segmentation module is used for respectively segmenting the text address information to be matched and the standard address information to obtain an address element set to be checked and a standard address element set;
the text address matching module is used for respectively performing pinyin conversion on the address element set to be verified and the standard address element set to obtain the pinyin element set to be verified and the standard pinyin element set, performing one-to-one matching on each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified to obtain a matching result, and calculating the address matching score between the text address information to be matched and the standard address information according to the matching result;
the matching result output module is used for comparing the address matching score with a preset threshold value and judging whether the address matching score is smaller than the preset threshold value or not; when the address matching score is greater than or equal to the preset threshold value, judging that the voice address information input by the user passes the audit; and when the address matching score is smaller than the preset threshold value, judging that the voice address information input by the user does not pass the audit.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
a memory storing at least one instruction; a kind of electronic device with high-pressure air-conditioning system
And the processor executes the instructions stored in the memory to realize the address auditing method based on artificial intelligence.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having stored therein at least one computer program that is executed by a processor in an electronic device to implement the above-mentioned artificial intelligence-based address auditing method.
According to the embodiment of the invention, the address information to be matched is obtained by carrying out text conversion on the voice address information input by the user, the address information to be matched is subjected to word segmentation and pinyin conversion processing, the to-be-verified pinyin element set obtained after word segmentation and pinyin conversion and the standard pinyin element set are subjected to one-to-one matching, the address matching score between the two is obtained, and whether the voice address information input by the user passes the verification is judged according to the address matching score. According to the address auditing method, the device, the electronic equipment and the computer readable storage medium based on the artificial intelligence, when address comparison is carried out, the address is split into pinyin levels, so that the address matching is more accurate.
Drawings
FIG. 1 is a flow chart of an address auditing method based on artificial intelligence according to an embodiment of the present application;
FIG. 2 is a functional block diagram of an address auditing apparatus based on artificial intelligence according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device implementing the address auditing method based on artificial intelligence according to an embodiment of the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The embodiment of the application provides an address auditing method based on artificial intelligence. The execution subject of the address auditing method based on artificial intelligence includes, but is not limited to, at least one of a server, a terminal and the like capable of being configured to execute the method provided by the embodiment of the application. In other words, the address auditing method based on artificial intelligence may be performed by software or hardware installed on a terminal device or a server device, where the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of an address auditing method based on artificial intelligence according to an embodiment of the invention is shown. In this embodiment, the address auditing method based on artificial intelligence includes:
s1, receiving voice address information input by a user, performing voice recognition on the voice address information to obtain text address information to be matched, and acquiring standard address information input by the user in advance from a preset database;
in the embodiment of the invention, the standard address information can be address information input by a user in a text form when the user submits the loan application, and the voice address information can be address information input in a voice form when the user confirms the loan information in the process of executing the face sign on the loan application. The preset database is a database for storing the reserved personal data when the user submits the loan application. In the embodiment of the invention, the personal information of the user is verified by extracting the standard address information in the personal data and matching the acquired voice address information.
In detail, in the embodiment of the present invention, an automatic speech recognition technology (Automatic Speech Recognition, abbreviated as ASR) may be used to convert the speech address information into the text address information to be matched, where the automatic speech recognition technology is an existing mature technology and is not described herein.
S2, word segmentation is carried out on the text address information to be matched and the standard address information respectively, and an address element set to be verified and a standard address element set are obtained;
in the embodiment of the invention, the address element set to be verified refers to an address element set obtained after the address information to be matched is subjected to word segmentation. Similarly, the standard address element set refers to an address element set obtained after the standard address information is subjected to word segmentation.
For example: address information of "Shenzhen city Dragon Hua Ou Dragon lake community viewing-wave street Yunshan Yao district 6 a3 unit 1001 room" is obtained after word segmentation: "Guangdong province, shenzhen City, longhua district, dragon lake, community, guanlan, street, yunshan Yao, district, 6, tong, a3, unit, 1001, chamber".
In the embodiment of the present invention, the word segmentation is performed on the text address information to be matched and the standard address information to obtain an address element set to be verified and a standard address element set, which includes:
performing redundancy elimination operation on the text address information to be matched and the standard address information, and performing format conversion on the text address information to be matched and the standard address information after the redundancy elimination operation;
And respectively word-dividing the text address information to be matched and the standard address information after format conversion by using a pre-constructed resultant word-dividing algorithm to obtain an address element set to be verified and a standard address element set.
In detail, the redundancy elimination operation refers to elimination of redundant characters in the text address information to be matched and the standard address information, for example: and removing redundant characters such as periods, commas, brackets, personification, sighing, mood words and the like in the address information.
In the embodiment of the invention. The format conversion means that the case and case formats of English letters in the address element set to be verified and the standard address element set are unified, and English letters in the address element set to be verified and the standard address element set can be converted into lowercase English letters.
In the embodiment of the present invention, the barker word segmentation algorithm is in the prior art, and will not be described herein.
S3, respectively performing pinyin conversion on the address element set to be verified and the standard address element set to obtain a pinyin element set to be verified and a standard pinyin element set, performing one-to-one matching on each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified to obtain a matching result, and calculating address matching scores between the text address information to be matched and the standard address information according to the matching result;
In the embodiment of the invention, the to-be-verified pinyin element set refers to converting a text set in the to-be-verified address element set into a pinyin set. The standard pinyin element set refers to converting a text set in the standard address element set into a pinyin set. For example: the address element set is 'Guangdong province, shenzhen city, longhua district, longhu, community, wave, street, yunshan Yao, district, 6, span, a3, unit, 1001 and room', and the pinyin element set obtained after conversion is 'guangdongsheng, shenzhenshi, longhuaqu, longhu, shequ, guanlan, jiedao, yunshanyao, xiaoqu, 6, dong, a3, danyuan, 1001 and shi'.
In the embodiment of the present invention, the performing pinyin conversion on the address element set to be verified and the standard address element set to obtain the pinyin element set to be verified and the standard pinyin element set includes:
identifying the characters to be converted in the address element set to be verified and the standard address element set;
searching pinyin corresponding to the text to be converted in a pre-constructed text pinyin conversion comparison table;
and according to the positions of the characters to be converted in the address element set to be verified and the standard address element set, the pinyin corresponding to the characters to be converted is arranged to obtain the pinyin element set to be verified and the standard pinyin element set.
In the embodiment of the invention, the text pinyin conversion comparison table refers to a comparison table in which all text and corresponding pinyin are recorded, and the corresponding pinyin can be indexed through the text pinyin conversion comparison table. For example: the pinyin corresponding to the Guangdong province is the pinyin of the guangdong phrase.
In the embodiment of the present invention, the step of performing one-to-one matching between each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified to obtain a matching result includes:
calculating the edit distance between each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified by using a pre-constructed edit distance calculation formula to obtain an edit distance set;
selecting the minimum editing distance corresponding to each standard pinyin element in the standard pinyin element set from the editing distance set;
and calculating the element matching score of each standard pinyin element in the standard pinyin element set by using a pre-constructed element matching score formula and the minimum editing distance, and obtaining the matching result according to the element matching score.
In the embodiment of the present invention, the edit distance calculation formula is:
wherein a refers to an a standard pinyin element in the standard pinyin element set, and b refers to a b standard pinyin element in the pinyin element set to be verified. i refers to the ith letter in the standard pinyin element, and j refers to the jth letter in the pinyin element to be verified. m refers to the character length of the standard pinyin element, and n refers to the character length of the pinyin element to be verified. lev (Lev) a,b (i, j) means the minimum number of steps required to pass for changing the a-th standard pinyin element to the b-th pinyin element to be verified, namely the minimum editing distance. For example: the number of steps required for the guang change to gua is 2.a, a i Refers to the first i character string sequences in the a standard pinyin element, and b is as follows j And the first j character string sequences in the b-th element to be verified are referred to.
In detail, the element matching score formula is:
wherein match score (a, b) refers to the element matching score, m refers to the character length of the standard pinyin element, n refers to the character length of the pinyin element to be verified, lev a,b (i, j) refers to the minimum edit distance, and threshold refers to a preset matching threshold.
In the embodiment of the present invention, the obtaining the matching result according to the element matching score includes:
Judging whether the element matching score is smaller than a preset matching threshold value or not;
and if the element matching score is smaller than the matching threshold value, setting the element matching score to be zero.
If the element matching score is greater than or equal to the matching threshold, keeping the element matching score unchanged;
and collecting the standard pinyin elements with non-zero element matching scores to obtain a matching result.
In detail, the matching threshold may be set to 0.67 through a plurality of trials.
In the embodiment of the present invention, the calculating the address matching score between the text address information to be matched and the standard address information according to the matching result includes:
judging character attributes of each standard pinyin element in the matching result;
extracting a first standard pinyin element subset with character attributes of Chinese characters from the matching result, calculating the character length proportion of each standard pinyin element in the first standard pinyin element subset to all standard pinyin elements in the first standard pinyin element subset, and calculating the weight factor of each standard pinyin element in the first standard pinyin element subset according to the character length proportion;
Extracting a second standard pinyin element subset with character attributes of non-Chinese characters from the matching result, and calculating a weight factor of each standard pinyin element in the second standard pinyin element subset by utilizing a pre-constructed element normalization function and the character position of each standard pinyin element in the second standard pinyin element subset in the standard address element set;
and calculating the matching score between the text address information to be matched and the standard address information according to the element matching score and the weight factor.
In the embodiment of the invention, the character attribute can be divided into a Chinese character and a non-Chinese character. The weight factor of each standard pinyin element in the first subset of standard pinyin elements may be calculated by:
wherein k denotes the firstThe number of standard pinyin elements in a standard pinyin element set, u referring to the u-th standard pinyin element in the first standard pinyin element set.And the weight of the u standard pinyin element is indicated. />Refers to the character length, len, of the u-th standard pinyin element non_num (child address elements) refers to the total character length of the first subset of standard pinyin elements.
In the embodiment of the invention, the element normalization function is as follows:
Wherein, the liquid crystal display device comprises a liquid crystal display device,the weight of the v standard pinyin element in the standard pinyin element set is indicated, v indicates the v standard pinyin element in the standard pinyin element set, and h indicates the number of the standard pinyin elements in the standard pinyin element set. />And the last character of the v standard pinyin element is the serial number in the standard pinyin element set.
For example, the standard pinyin element sets are "guangdongsheng, shenzhenshi, longhuaqu, longhu, shequ, guanlan, jiedao, 366, hao, yunshanyao, xiaoqu, 6, dong, a3, dannyuan, 1001 and shi", and the last character serial numbers of "366", "6", "a3" and "1001" are "20", "27", "30" and "36", and the weights are 0.0586, 0.1559, 0.2371 and 0.5484, respectively.
In the embodiment of the present invention, the calculating the matching score between the text address information to be matched and the standard address information according to the element matching score and the weight factor includes:
calculating the matching score of the first standard pinyin subset by utilizing the element matching score and the weight factor of each standard pinyin element in the first standard pinyin subset;
calculating the matching score of the second standard pinyin subset by utilizing the element matching score and the weight factor of each standard pinyin element in the second standard pinyin subset;
And obtaining the matching score between the text address information to be matched and the standard address information according to the matching score of the first standard pinyin subset and the matching score of the second standard pinyin subset.
In the embodiment of the present invention, the matching score of the first standard pinyin element subset may be calculated by the following formula:
wherein, the liquid crystal display device comprises a liquid crystal display device,referring to the matching scores of the first subset of standard pinyin elements,and the matching score of the u standard pinyin element is indicated.
In the embodiment of the present invention, the matching score of the second standard pinyin element subset may be calculated by the following formula:
wherein, the liquid crystal display device comprises a liquid crystal display device,refers to the matching score of the second subset of standard pinyin,refers to the matching score of the v standard pinyin element in the standard pinyin element set. h refers to the number of standard pinyin elements of the standard pinyin element set.
In the embodiment of the present invention, the obtaining the matching score between the text address information to be matched and the standard address information according to the matching score of the first standard pinyin subset and the matching score of the second standard pinyin subset includes:
calculating a weight factor of the first standard pinyin subset according to the character length proportion of the first standard pinyin subset to the standard pinyin element set and a pre-constructed first normalization function;
Calculating a weight factor of the second standard pinyin subset according to the character length proportion of the second standard pinyin subset to the standard pinyin element set and a pre-constructed second normalization function;
weighting the matching scores of the first standard pinyin subsets by using the weight factors of the first standard pinyin subsets, and weighting the matching scores of the second standard pinyin subsets by using the weight factors of the second standard pinyin subsets;
and integrating the matching score of the first standard pinyin subset and the matching score of the second standard pinyin subset after the weighting processing to obtain the matching score between the text address information to be matched and the standard address information.
In detail, the first normalization function is as follows:
wherein, softmax non_num (sum weight) refers to the weight factor of the first standard pinyin subset non_num (child address elements) means that the first subset of standard pinyin is a proportion of the character length of the subset of standard pinyin.
sum_weight non_num (child address elements) can be calculated by the following formula:
wherein, len non_num (child address elements) refers to the character length of the first subset of standard pinyin and n refers to the character length of the standard pinyin element.
For example, when the standard pinyin elements are guangdongsheng, shenzhenshi, longhuaqu, longhu, shequ, guanlan, jiedao, 366, hao, yunshanyao, xiaoqu, 6, dong, a3, dannyuan, 1001 and shi, the character length of the first standard pinyin element is 27, the character length of the standard pinyin element is 37, and the proportion of the first standard pinyin subset to the character length of the standard pinyin subset is 0.7297. After the first normalization function is calculated, the weight factor of the first standard pinyin subset is reduced to 0.6864.
Further, the second normalization function is as follows:
wherein, softmax num (sum weight) means the second normalization function, sum weight num (child address elements) means that the second subset of standard pinyin is a proportion of the character length of the subset of standard pinyin.
sum_weight num (child address elements) can be calculated by the following formula:
wherein, len num (child address elements) refers to the character length of the second subset of standard pinyin and n refers to the character length of the standard pinyin element.
For example: when the standard pinyin elements are guangdongsheng, shenzhenshi, longhuaqu, longhu, shequ, guanlan, jiedao, 366, hao, yunshanyao, xiaoqu, 6, dong, a3, danyuan, 1001 and shi, the character length of the second standard pinyin element is 10, the character length of the standard pinyin element is 37, and the proportion of the second standard pinyin subset to the character length of the standard pinyin subset is 0.2702. After the second normalization function is calculated, the weight factor of the second standard pinyin subset is increased to 0.3136.
Since the character length of the pinyin elements of a Chinese character is generally greater than the character length of the pinyin elements of a non-Chinese character in the standard pinyin element set, the weighting factors of the first and second standard pinyin subsets are appropriately adjusted by the first and second normalization functions.
S4, comparing the address matching score with a preset threshold value, and judging whether the address matching score is smaller than the preset threshold value.
When the address matching score is greater than or equal to the preset threshold, S5 is executed, and the voice address information input by the user is judged to pass the auditing;
in the embodiment of the invention, the preset threshold value can be set by utilizing multiple groups of similarity degree of the text address information to be matched and the standard address information and the corresponding address matching score and multiple times of experiments. And when the address matching score is larger than the preset threshold value, judging that the voice address information passes the auditing.
And when the address matching score is smaller than a preset threshold, executing S6, and judging that the voice address information input by the user does not pass the audit.
In the embodiment of the invention, when the address matching score is smaller than the preset threshold value, the voice address information input by the user is judged to not pass the audit.
According to the embodiment of the invention, the address information to be matched is obtained by carrying out text conversion on the voice address information input by the user, the address information to be matched is subjected to word segmentation and pinyin conversion processing, the to-be-verified pinyin element set obtained after word segmentation and pinyin conversion and the standard pinyin element set are subjected to one-to-one matching, the address matching score between the two is obtained, and whether the voice address information input by the user passes the verification is judged according to the address matching score. According to the address auditing method based on artificial intelligence, when address comparison is carried out, the address is split into pinyin levels, so that the address matching is more accurate.
FIG. 2 is a functional block diagram of an address auditing apparatus based on artificial intelligence according to an embodiment of the present invention.
The address auditing apparatus 100 based on artificial intelligence according to the present invention may be installed in an electronic device. Depending on the implementation, the address auditing device 100 based on artificial intelligence may include a voice address recognition module 101, a text address word segmentation module 102, a text address matching module 103, and a matching result output module 104. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the voice address recognition module 101 is configured to receive voice address information entered by a user, perform voice recognition on the voice address information to obtain text address information to be matched, and obtain standard address information entered by the user in advance from a preset database;
the text address word segmentation module 102 is configured to segment the text address information to be matched and the standard address information respectively to obtain an address element set to be verified and a standard address element set;
the text address matching module 103 is configured to perform pinyin conversion on the address element set to be verified and the standard address element set to obtain a pinyin element set to be verified and a standard pinyin element set, perform one-to-one matching with each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified to obtain a matching result, and calculate an address matching score between the text address information to be matched and the standard address information according to the matching result;
the matching result output module 104 is configured to compare the address matching score with a preset threshold, and determine whether the address matching score is smaller than the preset threshold; when the address matching score is greater than or equal to the preset threshold value, judging that the voice address information input by the user passes the audit; and when the address matching score is smaller than the preset threshold value, judging that the voice address information input by the user does not pass the audit.
In detail, each module in the address auditing device 100 based on artificial intelligence in the embodiment of the present invention adopts the same technical means as the address auditing method based on artificial intelligence described in fig. 1, and can produce the same technical effects, which are not described herein.
Fig. 3 is a schematic structural diagram of an electronic device for implementing an address auditing method based on artificial intelligence according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program stored in the memory 11 and executable on the processor 10, such as an address auditing program based on artificial intelligence.
The processor 10 may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing unit, CPU), a microprocessor, a digital processing chip, a graphics processor, a combination of various control chips, and so on. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, executes or executes programs or modules stored in the memory 11 (e.g., performs an address auditing program based on artificial intelligence, etc.), and invokes data stored in the memory 11 to perform various functions of the electronic device and process data.
The memory 11 includes at least one type of readable storage medium including flash memory, a removable hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 11 may in other embodiments also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only for storing application software installed in an electronic device and various types of data, such as codes of an address auditing program based on artificial intelligence, but also for temporarily storing data that has been output or is to be output.
The communication bus 12 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
The communication interface 13 is used for communication between the electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
Fig. 3 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The address auditing program based on artificial intelligence stored by the memory 11 in the electronic device 1 is a combination of instructions that, when executed in the processor 10, may implement:
receiving voice address information input by a user, performing voice recognition on the voice address information to obtain text address information to be matched, and acquiring standard address information input by the user in advance from a preset database;
Word segmentation is respectively carried out on the text address information to be matched and the standard address information to obtain an address element set to be verified and a standard address element set;
respectively performing pinyin conversion on the address element set to be verified and the standard address element set to obtain a pinyin element set to be verified and a standard pinyin element set, performing one-to-one matching on each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified to obtain a matching result, and calculating an address matching score between the text address information to be matched and the standard address information according to the matching result;
comparing the address matching score with a preset threshold value, and judging whether the address matching score is smaller than the preset threshold value or not;
when the address matching score is greater than or equal to the preset threshold value, judging that the voice address information input by the user passes the audit;
and when the address matching score is smaller than the preset threshold value, judging that the voice address information input by the user does not pass the audit.
In particular, the specific implementation method of the above instructions by the processor 10 may refer to the description of the relevant steps in the corresponding embodiment of the drawings, which is not repeated herein.
Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
receiving voice address information input by a user, performing voice recognition on the voice address information to obtain text address information to be matched, and acquiring standard address information input by the user in advance from a preset database;
word segmentation is respectively carried out on the text address information to be matched and the standard address information to obtain an address element set to be verified and a standard address element set;
Respectively performing pinyin conversion on the address element set to be verified and the standard address element set to obtain a pinyin element set to be verified and a standard pinyin element set, performing one-to-one matching on each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified to obtain a matching result, and calculating an address matching score between the text address information to be matched and the standard address information according to the matching result;
comparing the address matching score with a preset threshold value, and judging whether the address matching score is smaller than the preset threshold value or not;
when the address matching score is greater than or equal to the preset threshold value, judging that the voice address information input by the user passes the audit;
and when the address matching score is smaller than the preset threshold value, judging that the voice address information input by the user does not pass the audit.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (7)
1. An address auditing method based on artificial intelligence, which is characterized by comprising the following steps:
receiving voice address information input by a user, performing voice recognition on the voice address information to obtain text address information to be matched, and acquiring standard address information input by the user in advance from a preset database;
word segmentation is respectively carried out on the text address information to be matched and the standard address information to obtain an address element set to be verified and a standard address element set;
respectively performing pinyin conversion on the address element set to be verified and the standard address element set to obtain a pinyin element set to be verified and a standard pinyin element set, performing one-to-one matching on each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified to obtain a matching result, and calculating an address matching score between the text address information to be matched and the standard address information according to the matching result;
Comparing the address matching score with a preset threshold value, and judging whether the address matching score is smaller than the preset threshold value or not;
when the address matching score is greater than or equal to the preset threshold value, judging that the voice address information input by the user passes the audit;
when the address matching score is smaller than the preset threshold value, judging that the voice address information input by the user does not pass the audit;
wherein, each standard pinyin element in the standard pinyin element set is utilized to be matched with each pinyin element to be verified in the pinyin element set to be verified one by one, so as to obtain a matching result, which comprises: calculating the edit distance between each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified by using a pre-constructed edit distance calculation formula to obtain an edit distance set; selecting the minimum editing distance corresponding to each standard pinyin element in the standard pinyin element set from the editing distance set; calculating the element matching score of each standard pinyin element in the standard pinyin element set by using a pre-constructed element matching score formula and the minimum editing distance, and obtaining the matching result according to the element matching score;
The calculating the address matching score between the text address information to be matched and the standard address information according to the matching result comprises the following steps: judging character attributes of each standard pinyin element in the matching result; extracting a first standard pinyin element subset with character attributes of Chinese characters from the matching result, calculating the character length proportion of each standard pinyin element in the first standard pinyin element subset to all standard pinyin elements in the first standard pinyin element subset, and calculating the weight factor of each standard pinyin element in the first standard pinyin element subset according to the character length proportion; extracting a second standard pinyin element subset with character attributes of non-Chinese characters from the matching result, and calculating a weight factor of each standard pinyin element in the second standard pinyin element subset by utilizing a pre-constructed element normalization function and the character position of each standard pinyin element in the second standard pinyin element subset in the standard address element set; calculating the matching score between the text address information to be matched and the standard address information according to the element matching score and the weight factor;
The calculating the matching score between the text address information to be matched and the standard address information according to the element matching score and the weight factor comprises the following steps: calculating the matching score of the first standard pinyin subset by utilizing the element matching score and the weight factor of each standard pinyin element in the first standard pinyin subset; calculating the matching score of the second standard pinyin subset by utilizing the element matching score and the weight factor of each standard pinyin element in the second standard pinyin subset; and obtaining the matching score between the text address information to be matched and the standard address information according to the matching score of the first standard pinyin subset and the matching score of the second standard pinyin subset.
2. The method for address auditing based on artificial intelligence according to claim 1, wherein the performing pinyin conversion on the address element set to be verified and the standard address element set to obtain the pinyin element set to be verified and the standard pinyin element set respectively includes:
identifying the characters to be converted in the address element set to be verified and the standard address element set;
searching pinyin corresponding to the text to be converted in a pre-constructed text pinyin conversion comparison table;
And according to the positions of the characters to be converted in the address element set to be verified and the standard address element set, the pinyin corresponding to the characters to be converted is arranged to obtain the pinyin element set to be verified and the standard pinyin element set.
3. The method for auditing addresses based on artificial intelligence according to claim 1, wherein said obtaining the matching result according to the element matching score comprises:
judging whether the element matching score is smaller than a preset matching threshold value or not;
if the element matching score is smaller than the matching threshold, setting the element matching score to be zero;
if the element matching score is greater than or equal to the matching threshold, keeping the element matching score unchanged;
and collecting the standard pinyin elements with non-zero element matching scores to obtain a matching result.
4. The method for auditing addresses based on artificial intelligence according to claim 1, wherein the step of respectively word-segmenting the text address information to be matched and the standard address information to obtain an address element set to be verified and a standard address element set includes:
performing redundancy elimination operation on the text address information to be matched and the standard address information, and performing format conversion on the text address information to be matched and the standard address information after the redundancy elimination operation;
And respectively word-dividing the text address information to be matched and the standard address information after format conversion by using a pre-constructed resultant word-dividing algorithm to obtain an address element set to be verified and a standard address element set.
5. An artificial intelligence based address auditing apparatus for implementing an artificial intelligence based address auditing method according to any of claims 1 to 4, the apparatus comprising:
the voice address recognition module is used for receiving voice address information input by a user, carrying out voice recognition on the voice address information to obtain text address information to be matched, and acquiring standard address information input in advance by the user from a preset database;
the text address word segmentation module is used for respectively segmenting the text address information to be matched and the standard address information to obtain an address element set to be checked and a standard address element set;
the text address matching module is used for respectively performing pinyin conversion on the address element set to be verified and the standard address element set to obtain the pinyin element set to be verified and the standard pinyin element set, performing one-to-one matching on each standard pinyin element in the standard pinyin element set and each pinyin element to be verified in the pinyin element set to be verified to obtain a matching result, and calculating the address matching score between the text address information to be matched and the standard address information according to the matching result;
The matching result output module is used for comparing the address matching score with a preset threshold value and judging whether the address matching score is smaller than the preset threshold value or not; when the address matching score is greater than or equal to the preset threshold value, judging that the voice address information input by the user passes the audit; and when the address matching score is smaller than the preset threshold value, judging that the voice address information input by the user does not pass the audit.
6. An electronic device, the electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the artificial intelligence based address auditing method of any of claims 1 to 4.
7. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the artificial intelligence based address auditing method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111149201.4A CN113822049B (en) | 2021-09-29 | 2021-09-29 | Address auditing method, device, equipment and storage medium based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111149201.4A CN113822049B (en) | 2021-09-29 | 2021-09-29 | Address auditing method, device, equipment and storage medium based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113822049A CN113822049A (en) | 2021-12-21 |
| CN113822049B true CN113822049B (en) | 2023-08-25 |
Family
ID=78915910
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111149201.4A Active CN113822049B (en) | 2021-09-29 | 2021-09-29 | Address auditing method, device, equipment and storage medium based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113822049B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159949A (en) * | 2015-08-12 | 2015-12-16 | 北京京东尚科信息技术有限公司 | Chinese address word segmentation method and system |
| CN108804425A (en) * | 2018-06-13 | 2018-11-13 | 北京玄科技有限公司 | The address information extraction method and device of intelligence machine conference text |
| CN108959244A (en) * | 2018-06-07 | 2018-12-07 | 北京京东尚科信息技术有限公司 | The method and apparatus of address participle |
| CN111159974A (en) * | 2019-12-30 | 2020-05-15 | 北京明略软件系统有限公司 | Address information standardization method and device, storage medium and electronic equipment |
| CN111695355A (en) * | 2020-05-26 | 2020-09-22 | 平安银行股份有限公司 | Address text recognition method, device, medium and electronic equipment |
| WO2021047526A1 (en) * | 2019-09-12 | 2021-03-18 | 深圳前海微众银行股份有限公司 | Address similarity evaluation method, apparatus and device, and medium |
| CN112612863A (en) * | 2020-12-23 | 2021-04-06 | 武汉大学 | Address matching method and system based on Chinese word segmentation device |
| CN112686036A (en) * | 2020-08-18 | 2021-04-20 | 平安国际智慧城市科技股份有限公司 | Risk text recognition method and device, computer equipment and storage medium |
| CN112711950A (en) * | 2020-12-23 | 2021-04-27 | 深圳壹账通智能科技有限公司 | Address information extraction method, device, equipment and storage medium |
| CN112820269A (en) * | 2020-12-31 | 2021-05-18 | 平安科技（深圳）有限公司 | Text-to-speech method, device, electronic equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108108373B (en) * | 2016-11-25 | 2020-09-25 | 阿里巴巴集团控股有限公司 | Name matching method and device |
| CN107220235B (en) * | 2017-05-23 | 2021-01-22 | 北京百度网讯科技有限公司 | Speech recognition error correction method and device based on artificial intelligence and storage medium |
-
2021
- 2021-09-29 CN CN202111149201.4A patent/CN113822049B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159949A (en) * | 2015-08-12 | 2015-12-16 | 北京京东尚科信息技术有限公司 | Chinese address word segmentation method and system |
| CN108959244A (en) * | 2018-06-07 | 2018-12-07 | 北京京东尚科信息技术有限公司 | The method and apparatus of address participle |
| CN108804425A (en) * | 2018-06-13 | 2018-11-13 | 北京玄科技有限公司 | The address information extraction method and device of intelligence machine conference text |
| WO2021047526A1 (en) * | 2019-09-12 | 2021-03-18 | 深圳前海微众银行股份有限公司 | Address similarity evaluation method, apparatus and device, and medium |
| CN111159974A (en) * | 2019-12-30 | 2020-05-15 | 北京明略软件系统有限公司 | Address information standardization method and device, storage medium and electronic equipment |
| CN111695355A (en) * | 2020-05-26 | 2020-09-22 | 平安银行股份有限公司 | Address text recognition method, device, medium and electronic equipment |
| CN112686036A (en) * | 2020-08-18 | 2021-04-20 | 平安国际智慧城市科技股份有限公司 | Risk text recognition method and device, computer equipment and storage medium |
| CN112612863A (en) * | 2020-12-23 | 2021-04-06 | 武汉大学 | Address matching method and system based on Chinese word segmentation device |
| CN112711950A (en) * | 2020-12-23 | 2021-04-27 | 深圳壹账通智能科技有限公司 | Address information extraction method, device, equipment and storage medium |
| CN112820269A (en) * | 2020-12-31 | 2021-05-18 | 平安科技（深圳）有限公司 | Text-to-speech method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113822049A (en) | 2021-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112507936B (en) | Image information auditing method and device, electronic equipment and readable storage medium | |
| CN112541338A (en) | Similar text matching method and device, electronic equipment and computer storage medium | |
| CN113157927B (en) | Text classification method, apparatus, electronic device and readable storage medium | |
| CN112560453A (en) | Voice information verification method and device, electronic equipment and medium | |
| CN113064994A (en) | Conference quality evaluation method, device, equipment and storage medium | |
| CN112988963A (en) | User intention prediction method, device, equipment and medium based on multi-process node | |
| CN113722483A (en) | Topic classification method, device, equipment and storage medium | |
| CN113344125B (en) | Long text matching recognition method and device, electronic equipment and storage medium | |
| CN113627160B (en) | Text error correction method and device, electronic equipment and storage medium | |
| CN114840684A (en) | Map construction method, device and equipment based on medical entity and storage medium | |
| CN113360654B (en) | Text classification method, apparatus, electronic device and readable storage medium | |
| CN112686026B (en) | Keyword extraction method, device, equipment and medium based on information entropy | |
| CN116578696A (en) | Text abstract generation method, device, equipment and storage medium | |
| CN116468025A (en) | Electronic medical record structuring method and device, electronic equipment and storage medium | |
| CN113822049B (en) | Address auditing method, device, equipment and storage medium based on artificial intelligence | |
| CN116450829A (en) | Medical text classification method, device, equipment and medium | |
| CN116681082A (en) | Discrete text semantic segmentation method, device, equipment and storage medium | |
| CN116341646A (en) | Pretraining method and device of Bert model, electronic equipment and storage medium | |
| WO2022141867A1 (en) | Speech recognition method and apparatus, and electronic device and readable storage medium | |
| CN113808616A (en) | Voice compliance detection method, device, equipment and storage medium | |
| CN113806540A (en) | Text labeling method and device, electronic equipment and storage medium | |
| CN115146627B (en) | Entity identification method, entity identification device, electronic equipment and storage medium | |
| CN115221875B (en) | Word weight generation method, device, electronic equipment and storage medium | |
| CN111680513B (en) | Feature information identification method and device and computer readable storage medium | |
| CN115146622B (en) | Data annotation error correction method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |