CN111651976B - Name broadcasting method and device - Google Patents

Name broadcasting method and device Download PDF

Info

Publication number
CN111651976B
CN111651976B CN202010644225.6A CN202010644225A CN111651976B CN 111651976 B CN111651976 B CN 111651976B CN 202010644225 A CN202010644225 A CN 202010644225A CN 111651976 B CN111651976 B CN 111651976B
Authority
CN
China
Prior art keywords
regional
client
name
regional group
information
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
Application number
CN202010644225.6A
Other languages
Chinese (zh)
Other versions
CN111651976A (en
Inventor
朱军
张宇
吴平凡
杨儒良
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN202010644225.6A priority Critical patent/CN111651976B/en
Publication of CN111651976A publication Critical patent/CN111651976A/en
Application granted granted Critical
Publication of CN111651976B publication Critical patent/CN111651976B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F40/237—Lexical tools
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G10L13/02—Methods for producing synthetic speech; Speech synthesisers
    • 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
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Computing Systems (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Machine Translation (AREA)

Abstract

The application provides a method and a device for name broadcasting, wherein the method comprises the following steps: acquiring regional group face information and client face information; establishing a regional group distribution database according to regional group face information; matching the regional group distribution database with a preset polyphone library, and determining a parameter corresponding table; determining a customer name and customer face characteristics according to the customer face information; comparing the customer name with a preset polyphone library, and if the polyphone exists in the customer name, matching the customer face characteristics with a regional population distribution database to determine regional population information to which the customer belongs; according to regional group information of a client, matching pronunciation corresponding to the polyphones in the client name through a parameter corresponding table, replacing the polyphones with homophones by using a direct-tone method, and determining a client name broadcasting text; and converting the client name broadcasting text into voice to broadcast the client name. The method and the device realize accurate broadcasting when the polyphones exist in the name, and improve customer experience.

Description

Name broadcasting method and device
Technical Field
The application relates to the technical field of computer information processing, in particular to a name broadcasting method and device.
Background
This section is intended to provide a background or context to the embodiments of the application that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
In the scene of customer face recognition and customer name broadcasting, the prior art is to read out the name by using a single reading method when multi-tone surname is found; for example, surname "singly" and the radical error is reading "dan", and the existing methods are basically reading "good". Thus, although the basic problem of multi-tone word reading errors does not exist, the defect that a single word is read as a cicada in some groups and a pattern is read as a Tan in some places cannot be solved.
Because the surnames or first names of Chinese people have various reading methods, and because the Chinese people have important ' different sources ' when reading the surnames of the Chinese people, the principle of two surnames ' is suitable, and different groups have different pronunciations on the same word. If the customer name is simply read from the main sound of the surname without considering the region and group information, the error reading is very easy, and the poor customer experience is caused.
Therefore, how to provide a new solution to the above technical problem is a technical problem to be solved in the art.
Disclosure of Invention
The embodiment of the application provides a name broadcasting method, which realizes accurate broadcasting when polyphones exist in names, and comprises the following steps:
acquiring regional group face information and client face information;
establishing a regional group distribution database according to regional group face information;
matching the regional group distribution database with a preset polyphone library, and determining a parameter corresponding table;
determining a customer name and customer face characteristics according to the customer face information;
comparing the customer name with a preset polyphone library, and if the polyphone exists in the customer name, matching the customer face characteristics with a regional population distribution database to determine regional population information to which the customer belongs;
according to regional group information of a client, matching pronunciation corresponding to the polyphones in the client name through a parameter corresponding table, replacing the polyphones with homophones by using a direct-tone method, and determining a client name broadcasting text;
and converting the client name broadcasting text into voice to broadcast the client name.
The embodiment of the application also provides a name broadcasting device, which comprises:
the information acquisition module is used for acquiring regional group face information and client face information;
the regional group distribution database building module is used for building a regional group distribution database according to regional group face information;
the parameter corresponding table determining module is used for matching the regional group distribution database with a preset polyphone library to determine a parameter corresponding table;
the client name and client face feature determining module is used for determining the client name and the client face feature according to the client face information;
the regional group information determining module is used for comparing the name of the client with a preset polyphone library, and if the polyphone exists in the name of the client, matching the face characteristics of the client with a regional group distribution database to determine the regional group information of the client;
the client name broadcasting text determining module is used for matching the pronunciation corresponding to the polyphone in the client name through the parameter corresponding table according to the regional group information of the client, and replacing the polyphone with the homophone by using a direct sound method to determine the client name broadcasting text;
and the name broadcasting module is used for converting the client name broadcasting text into voice and broadcasting the client name.
The embodiment of the application also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the last name broadcasting method is realized when the processor executes the computer program.
The embodiment of the application also provides a computer readable storage medium which stores a computer program for executing the above-mentioned surname broadcasting method.
According to the name broadcasting method and device provided by the embodiment of the application, the regional group face information is acquired, the regional group distribution database is established, then the regional group distribution database is matched with the preset polyphone database, the parameter corresponding table is determined, the establishment of the connection between the polyphone reading method and the group face information is realized, then the client face information is identified, the client name and the client face characteristics are determined, the client name is compared with the preset polyphone database, if the polyphone exists in the client name, the client face characteristics are matched with the regional group distribution database, the regional group information of the client is determined, then the pronunciation corresponding to the polyphone in the client name is matched through the parameter corresponding table according to the regional group information of the client, the polyphone is replaced with the homophone by the direct phone method, and the broadcasting text of the client name is determined; and finally, converting the client name broadcasting text into voice to broadcast the client name. According to the embodiment of the application, the regional group face information is introduced to establish the parameter corresponding table, and the reading method of surnames and the face characteristics of the group are associated, so that accurate broadcasting when polyphones exist in the name is realized, and user experience and satisfaction are improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a schematic diagram of a name broadcasting method according to an embodiment of the present application.
Fig. 2 is a representative face image feature of a yellow river basin obtained by a name broadcasting method according to an embodiment of the present application.
Fig. 3 is a representative face image feature of a Yangtze river basin obtained by a name broadcasting method according to an embodiment of the present application.
Fig. 4 is a representative face image feature of a Zhujiang river basin obtained by a name broadcasting method according to an embodiment of the present application.
Fig. 5 is a typical face image feature of a cloud precious area obtained by a name broadcasting method according to an embodiment of the present application.
Fig. 6 is a typical facial image feature of Xinjiang area obtained by a name broadcasting method according to an embodiment of the present application.
Fig. 7 is a schematic diagram of a computer device for running a name broadcasting method implemented in the present application.
Fig. 8 is a schematic diagram of a name broadcasting device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present application and their descriptions herein are for the purpose of explaining the present application, but are not to be construed as limiting the application.
According to the technical scheme, the data are acquired, stored, used and processed according with relevant regulations of laws and regulations. For example, acquiring user related information (such as user face information and the like) refers to acquiring under the condition of user authorization.
Fig. 1 is a schematic diagram of a name broadcasting method according to an embodiment of the present application, and as shown in fig. 1, the embodiment of the present application provides a name broadcasting method, which realizes accurate broadcasting when a polyphone exists in a name, and the method includes:
step 101: acquiring regional group face information and client face information;
step 102: establishing a regional group distribution database according to regional group face information;
step 103: matching the regional group distribution database with a preset polyphone library, and determining a parameter corresponding table;
step 104: determining a customer name and customer face characteristics according to the customer face information;
step 105: comparing the customer name with a preset polyphone library, and if the polyphone exists in the customer name, matching the customer face characteristics with a regional population distribution database to determine regional population information to which the customer belongs;
step 106: according to regional group information of a client, matching pronunciation corresponding to the polyphones in the client name through a parameter corresponding table, replacing the polyphones with homophones by using a direct-tone method, and determining a client name broadcasting text;
step 107: and converting the client name broadcasting text into voice to broadcast the client name.
According to the name broadcasting method provided by the embodiment of the application, the regional group face information is acquired, the regional group distribution database is built, then the regional group face information is matched with the preset polyphone database, the parameter corresponding table is determined, the establishment of the connection between the polyphone reading method and the group face information is realized, then the client face information is identified, the client name and the client face characteristics are determined, the client name is compared with the preset polyphone database, if the polyphone exists in the client name, the client face characteristics are matched with the regional group distribution database, the regional group information of the client is determined, then the pronunciation corresponding to the polyphone in the client name is matched through the parameter corresponding table according to the regional group information of the client, the polyphone is replaced with the homophone by the direct-tone method, and the client name broadcasting text is determined; and finally, converting the client name broadcasting text into voice to broadcast the client name. According to the embodiment of the application, the regional group face information is introduced to establish the parameter corresponding table, and the reading method of surnames and the face characteristics of the group are associated, so that accurate broadcasting when polyphones exist in the name is realized, and user experience and satisfaction are improved.
In the existing names in China, the situation of one-word multi-reading is more common, for example:
the Chinese character name "solution" can be read as: h, ji ě, S, xi, xiere, gai, ji ě, xiere, S, four-tone surname in Chinese surname dictionary (p 1363-1364), different sources, preferably four surnames, wherein H, i, surname in New thousands of surnames, shanxi Jiangxian; ji ě sound surnames are found in the names , the Chinese dictionary, the Lisu, the Zhuang nationality surnames, ningxia, shandong, guangxi, yunnan and other places; s atri surname is found in the New Charpy Zhuyin Qianjiasurname, ningxia, shanxi Jiangcounty; xi's surname is shown in "dialectical book of the family names of the ancient and the like, and the main names, jinzhuang, mongolia, miao, water, naxi, buyi and other national surnames are widely distributed, and the seven provinces of Henan, shandong, shanxi, anhui and the like are more, and 8 Xi's complex names are also provided. See also "Chinese surname calligraphy dictionary" (p 1015): "surname dictionary: ' solution, 1, H, see Wang Shumin, new Chanzhen Qianjin Jianjiao. 2. Ji ě, S-a, xi, and Xi' ". gai and ji re are not used by last names.
From the above description, the "solved" family names with main sounds "are derived from Chinese, manchurian, mongolian, etc. nations, distributed Heilongjiang, liaoning, hebei, henan, shandong and Shaanxi. The second-tone surname of "solution" is named as "sister" and originates from the nationality of the Lisu, zhuang etc., and is distributed in Ningxia, guangxi and Yunnan. If the traditional polyphone reading method is used, all the reading is 'thank you', the reading method is wrong in surnames of certain groups.
Likewise, "single" suffers from similar problems:
singly (CHAN), read as: chan, D ā n, sh ā n, sh-an (Sh-n), T ā n, T-an seven-tone four single surnames and six surnames. Wherein: chon is a single-tone (character) surname, and is available in Hubei Honghu lake area; or the surname is singly Ch n y U, shandong's city, yidu, shanxi's city, hunan Yiyang, shanghai and Fujian spring state, all see "China's name explanatory dictionary" or "surname source seeking". The D ā n sound surnames are different sources, mainly comprising: (1) after being prepared from Ji surname and Zhou Daishan Xiang, see Yuan He surname. (2) North Wei Zhou A Shan Shi, shan Shi, and Ke Shan Shi, etc. Jian Wen are changed to Shan Shi, see Yuan He Mi Zhong Yuan Zhong Jia. (3) Jin Dai the fuzhen Shan Shi Han chemical is changed into Shan Shi, see "Jin Shi" for five kinds of supplement, hebei Fuping, bao deer, shanxi Jiangcounty, hunan Zhijiang, jiangxi Yugan, guizhou Ziyun and the like.
Similar polyphones are also numerous. The name of the customer is simply read from the main sound of the surname without considering the region and group information, so that the misreading is very easy, and the problem of poor customer experience is caused.
In order to solve the problem of the pronunciation error of the polyphone, the embodiment of the method provides a name broadcasting method, which may include:
acquiring regional group face information and client face information;
establishing a regional group distribution database according to regional group face information;
matching the regional group distribution database with a preset polyphone library, and determining a parameter corresponding table;
determining a customer name and customer face characteristics according to the customer face information;
comparing the customer name with a preset polyphone library, and if the polyphone exists in the customer name, matching the customer face characteristics with a regional population distribution database to determine regional population information to which the customer belongs;
according to regional group information of a client, matching pronunciation corresponding to the polyphones in the client name through a parameter corresponding table, replacing the polyphones with homophones by using a direct-tone method, and determining a client name broadcasting text;
and converting the client name broadcasting text into voice to broadcast the client name.
When the name broadcasting device provided by the embodiment of the present application is implemented, in one embodiment, the aforementioned regional group face information includes: the method comprises the steps of a designated ethnic distribution and face image, an undetermined ethnic distribution and face image, a drainage basin ethnic distribution and face image, an average face model and face characteristics of each province;
according to the regional group face information, a regional group distribution database is established, comprising:
dividing regional group classification, extracting regional group face information to the regional group classification, identifying the regional group face information divided into the same regional group classification through a deep learning framework, and determining typical face image characteristics of each regional group classification;
and establishing a regional group distribution database according to the typical face image characteristics of each regional group classification.
The ethnic group refers to a specific named or unnamed ethnic group, such as named han, zhuang, korea, etc. Or unidentified ethnicities such as Ai Nuren, creutzfeld, etc. Or foreign groups such as korea, japan, vietnam, etc.
In an embodiment, the region group face information includes: the method comprises the steps of a designated ethnic distribution and face image, an undetermined ethnic distribution and face image, a drainage basin ethnic distribution and face image, an average face model and face characteristics of each province;
the establishing a regional group distribution database according to the regional group face information includes: dividing regional group classification, extracting regional group face information to the regional group classification, identifying the regional group face information divided into the same regional group classification through a deep learning framework, and determining typical face image characteristics of each regional group classification; and establishing a regional group distribution database according to the typical face image characteristics of each regional group classification.
For example, in one example of the embodiment of the present application, the regional group of china is divided into: yellow river basin, yangtze river basin, zhujiang river basin, cloud precious area, xinjiang area and other 5 types; wherein, fig. 2 is a representative face image feature of a yellow river basin obtained by a name broadcasting method according to an embodiment of the present application, fig. 3 is a representative face image feature of a Yangtze river basin obtained by a name broadcasting method according to an embodiment of the present application, fig. 4 is a representative face image feature of a zhujiang river basin obtained by a name broadcasting method according to an embodiment of the present application, fig. 5 is a representative face image feature of a cloud precious area obtained by a name broadcasting method according to an embodiment of the present application, and fig. 6 is a representative face image feature of a Xinjiang region obtained by a name broadcasting method according to an embodiment of the present application; as shown in fig. 2-6, the typical face image features of the present application are obtained by extracting regional group face information to the regional group classification, and identifying and classifying the regional group face information classified into the same regional group classification by the deep learning framework;
when the last name broadcasting device provided by the embodiment of the application is implemented, in one embodiment, the preset polyphonic word library includes: all polyphone surnames; wherein each pronunciation record of each polyphone surname has regional group attribution information and homonyms;
matching the regional group distribution database with a preset polyphone library to determine a parameter corresponding table, wherein the method comprises the following steps:
and matching the typical face image characteristics of each region group classification in the region group distribution database with the region group attribution information of the polyphonic surnames, establishing a mapping relation between the typical face image characteristics and the polyphonic surnames, and determining a parameter corresponding table.
In the embodiment, a preset polyphone library is used for acquiring all existing polyphone surnames through a Chinese polyphone surname identification dictionary, a Chinese surname big dictionary, a New-book surname, a surname dictionary and a network search, wherein each pronunciation of each polyphone surname is recorded with regional group attribution information and homonyms; the following is recorded in the polyphonic word stock:
solution, yellow river basin, sound metabolism;
solution, zhujiang river basin, xingjie.
The foregoing matching the regional group distribution database with a preset polyphone library to determine a parameter mapping table includes: matching the typical face image characteristics of each region group classification in the region group distribution database with the region group attribution information of the polyphonic surnames, establishing a mapping relation between the typical face image characteristics and the polyphonic surnames, and determining a parameter corresponding table; in one example of this embodiment, the established parameter correspondence table may be:
the method comprises the steps of solving, yellow river basin, regional parameter 01, typical face image characteristics of the yellow river basin and sound metabolism.
Solving, zhujiang river basin, regional parameters 03, typical human face image characteristics of Zhujiang river basin, and the same sister.
When the name broadcasting device provided by the embodiment of the application is implemented, in one embodiment, the determining the client name and the client face feature according to the client face information may include: and according to the obtained client face information, obtaining the client face characteristics through a face recognition technology, and matching from a preset name database by utilizing the client face characteristics to obtain the client name. The application scenario of the embodiment may be that when a bank handles a service, when the camera recognizes the face information of the client, the client name and the face feature of the client are obtained; another application scenario may be used as an attendance system; the preset name database may be attendance data.
In an embodiment of the present application, when implementing the first name broadcasting device, the comparing the client name with a preset polyphone library, if there are polyphones in the client name, matching the client face feature with a regional population distribution database, and determining the regional population information to which the client belongs includes:
comparing the customer name with a preset polyphone library, if the polyphone exists in the customer name, matching the customer face characteristics with typical face image characteristics in a regional population distribution database, and determining the regional population confidence level of the customer in various regional population classifications;
and screening the regional group confidence in the multiple regional group classifications, classifying the regional group to which the maximum value of the regional group confidence belongs, and determining the regional group to which the client belongs as regional group information.
In the embodiment, firstly, the names of the clients need to be searched word by word, the client names are compared with a preset polyphone library, if the polyphones do not exist in the client names, the client names are directly output as unique client name broadcasting text, and the client names are converted into voice through subsequent text to be broadcasted; if the name of the client has polyphones, matching the face features of the client with typical face image features in a regional population distribution database, and determining the regional population confidence level of the client in various regional population classifications;
for example, the customer name is: and solving a certain problem, and matching the face features of the client with typical face image features in a regional population distribution database, wherein the confidence of the yellow river basin is 53%, and the confidence of the Zhujiang basin is 63%.
After obtaining the regional group confidence degrees of the user in the multiple regional group classifications, screening the regional group confidence degrees in the multiple regional group classifications, and determining the regional group classification to which the maximum value of the regional group confidence degrees belongs as the regional group information to which the user belongs; the confidence of the river basin and the confidence of the Zhujiang basin are screened, so that the confidence of the river basin can be obtained to be the largest, and therefore the Zhujiang basin with the confidence of the river basin is needed to be used as regional group information of a client. The customer "solves something" should read as "clean something".
In an embodiment of the present application, the foregoing method matches, according to regional group information to which a client belongs, pronunciations corresponding to polyphones in a client name through a parameter correspondence table, replaces the polyphones with homophones by a direct-tone method, and determines a client name broadcasting text, where the method includes:
according to regional group information of a client, matching target pronunciation of regional group attribution information corresponding to polyphones in a client name through a mapping relation of a parameter corresponding table, finding homophones of target pronunciation corresponding to the polyphones, replacing the polyphones with homophones with only one pronunciation by using a direct-tone method, and determining a client name broadcasting text.
The straight-sound method refers to an important pronunciation method of Chinese characters before pinyin appears. Find a homophone word to annotate the original word with a sound, write "A, B". For example, "cup" and "ancient" are known to be homophones, and are read according to the reading method of the "ancient" word. In the embodiment, according to the regional group information to which the client belongs, the target pronunciation of the regional group attribution information corresponding to the polyphones in the client name can be matched through the mapping relation of the parameter correspondence table, the homophones of the target pronunciation corresponding to the polyphones are found, the polyphones are replaced by homophones with only one pronunciation by using the direct sound method, and the broadcasting text of the client name is determined.
In general, the multi-tone word has multiple pronunciations, and the straight-tone method is to replace each pronunciation of the multi-tone word with a non-multi-tone word with the same pronunciation, namely, a homotone word with only one pronunciation, and establish a corresponding relation with the face information of the client by using the regional group attribution information of the homotone word so as to realize the correct pronunciation of the multi-tone word.
When the last name broadcasting device provided by the embodiment of the application is implemented, in one embodiment, the foregoing method for converting the client name broadcasting text into voice and broadcasting the client name may include: through the text-to-speech converter, the client name broadcasting text is converted into voice, and the client name is broadcasted through sound equipment such as sound equipment.
The name broadcasting method provided by the embodiment of the application is applied to an attendance checking system: the method can comprise the following steps:
1. and acquiring regional group face information and establishing a regional group distribution database.
2. And matching the regional group distribution database with a preset polyphone library, and determining a parameter corresponding table. The preset polyphone library comprises the polyphone retrieval of all the names of the attendance checking persons obtained from the attendance checking database in batches in advance, and comprises the polyphones of all the names of the attendance checking persons.
3. The attendance checking person enters an attendance checking area to obtain client face information, and the client name and the client face characteristics are obtained through interaction with an attendance checking database;
4. comparing the customer name with a preset polyphone library, and if the polyphone exists in the customer name, matching the customer face characteristics with a regional population distribution database to determine regional population information to which the customer belongs; according to regional group information of a client, matching pronunciations corresponding to polyphones in a client name through a parameter corresponding table, replacing the polyphones with homophones by a direct-tone method, and determining a client name broadcasting text
5. And converting the client name broadcasting text into voice, broadcasting the client name, and finishing attendance checking and card punching.
In the embodiment of the present application, the parameter correspondence table may be coded in the form of table 1:
TABLE 1
In the embodiment of the application, in order to improve the efficiency of comparing the customer name with a preset polyphone library, a program for supporting automatic retrieval of polyphones of a batch of texts is provided, the retrieval efficiency can be improved under the condition of large attendance number, retrieval omission is less, and the program pseudo code and Chinese interpretation of automatic retrieval of polyphones of the batch of texts are shown in the table 2:
TABLE 2
The meaning of the pseudo code of table 2 in one application scenario is shown in table 3:
TABLE 3 Table 3
In order to accurately locate the name field of the attendance in the attendance data in the program, the data range of the parameter comparison table application needs to be defined, as shown in table 4:
TABLE 4 Table 4
Fig. 7 is a schematic diagram of a computer device for running a first name broadcasting method implemented in the present application, and as shown in fig. 7, an embodiment of the present application further provides a computer device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor, where the processor implements the first name broadcasting method when executing the computer program.
The embodiment of the application also provides a computer readable storage medium which stores a computer program for implementing the surname broadcasting method.
The embodiment of the application also provides a name broadcasting device, which is described in the following embodiment. Because the principle of the device for solving the problem is similar to that of a name broadcasting method, the implementation of the device can refer to the implementation of the name broadcasting method, and the repetition is omitted.
Fig. 8 is a schematic diagram of a name broadcasting device according to an embodiment of the present application, and as shown in fig. 8, an embodiment of the present application further provides a name broadcasting device, which may include:
an information obtaining module 801, configured to obtain regional group face information and client face information;
a region group distribution database establishing module 802, configured to establish a region group distribution database according to the region group face information;
the parameter mapping table determining module 803 is configured to match the regional group distribution database with a preset polyphone database, and determine a parameter mapping table;
a client name and client face feature determining module 804, configured to determine a client name and a client face feature according to client face information;
the regional group information determining module 805 is configured to compare the client name with a preset polyphone library, and if there are polyphones in the client name, match the face feature of the client with the regional group distribution database, and determine the regional group information to which the client belongs;
the client name broadcasting text determining module 806 is configured to match, according to the regional group information to which the client belongs, the pronunciation corresponding to the polyphones in the client name through the parameter correspondence table, and replace the polyphones with homophones by using a direct-tone method, so as to determine the client name broadcasting text;
and the name broadcasting module 807 is configured to convert the client name broadcasting text into voice and broadcast the client name.
When the name broadcasting device provided by the embodiment of the present application is implemented, in one embodiment, the aforementioned regional group face information includes: the method comprises the steps of a designated ethnic distribution and face image, an undetermined ethnic distribution and face image, a drainage basin ethnic distribution and face image, an average face model and face characteristics of each province;
the regional group distribution database building module is specifically configured to:
dividing regional group classification, extracting regional group face information to the regional group classification, identifying the regional group face information divided into the same regional group classification through a deep learning framework, and determining typical face image characteristics of each regional group classification;
and establishing a regional group distribution database according to the typical face image characteristics of each regional group classification.
When the last name broadcasting device provided by the embodiment of the application is implemented, in one embodiment, the preset polyphonic word library includes: all polyphone surnames; wherein each pronunciation record of each polyphone surname has regional group attribution information and homonyms;
the parameter corresponding table determining module is specifically configured to:
and matching the typical face image characteristics of each region group classification in the region group distribution database with the region group attribution information of the polyphonic surnames, establishing a mapping relation between the typical face image characteristics and the polyphonic surnames, and determining a parameter corresponding table.
When the last name broadcasting device provided by the embodiment of the application is implemented, in one embodiment, the aforementioned client-affiliated region group information determining module is specifically configured to:
comparing the customer name with a preset polyphone library, if the polyphone exists in the customer name, matching the customer face characteristics with typical face image characteristics in a regional population distribution database, and determining the regional population confidence level of the customer in various regional population classifications;
and screening the regional group confidence in the multiple regional group classifications, classifying the regional group to which the maximum value of the regional group confidence belongs, and determining the regional group to which the client belongs as regional group information.
When the name broadcasting device provided by the embodiment of the application is implemented, in one embodiment, the client name broadcasting text determining module is specifically configured to:
according to regional group information of a client, matching target pronunciation of regional group attribution information corresponding to polyphones in a client name through a mapping relation of a parameter corresponding table, finding homophones of target pronunciation corresponding to the polyphones, replacing the polyphones with homophones with only one pronunciation by using a direct-tone method, and determining a client name broadcasting text.
In summary, the method and the device for broadcasting the surname provided by the embodiment of the application establish a regional group distribution database by acquiring regional group face information, then match with a preset polyphone library, determine a parameter corresponding table, realize that a polyphone reading method is connected with the group face information, then identify the client face information, determine the client name and the client face characteristics, compare the client name with the preset polyphone library, match the client face characteristics with the regional group distribution database if the polyphone exists in the client name, determine the regional group information to which the client belongs, then match the pronunciation corresponding to the polyphone in the client name through the parameter corresponding table according to the regional group information to which the client belongs, and utilize a direct sound method to replace the polyphone with the homophone to determine the text of the client name for broadcasting; and finally, converting the client name broadcasting text into voice to broadcast the client name. According to the embodiment of the application, the regional group face information is introduced to establish the parameter corresponding table, and the reading method of surnames and the face characteristics of the group are associated, so that accurate broadcasting when polyphones exist in the name is realized, and user experience and satisfaction are improved.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the application, and is not meant to limit the scope of the application, but to limit the application to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the application are intended to be included within the scope of the application.

Claims (12)

1. A name broadcasting method is characterized by comprising the following steps:
acquiring regional group face information and client face information;
establishing a regional group distribution database according to regional group face information;
matching the regional group distribution database with a preset polyphone library, and determining a parameter corresponding table;
determining a customer name and customer face characteristics according to the customer face information;
comparing the customer name with a preset polyphone library, and if the polyphone exists in the customer name, matching the customer face characteristics with a regional population distribution database to determine regional population information to which the customer belongs;
according to regional group information of a client, matching pronunciation corresponding to the polyphones in the client name through a parameter corresponding table, replacing the polyphones with homophones by using a direct-tone method, and determining a client name broadcasting text;
and converting the client name broadcasting text into voice to broadcast the client name.
2. The method of claim 1, wherein the regional population face information comprises: the method comprises the steps of a designated ethnic distribution and face image, an undetermined ethnic distribution and face image, a drainage basin ethnic distribution and face image, an average face model and face characteristics of each province;
according to the regional group face information, a regional group distribution database is established, comprising:
dividing regional group classification, extracting regional group face information to the regional group classification, identifying the regional group face information divided into the same regional group classification through a deep learning framework, and determining typical face image characteristics of each regional group classification;
and establishing a regional group distribution database according to the typical face image characteristics of each regional group classification.
3. The method of claim 2, wherein the pre-set polyphonic word stock comprises: all polyphone surnames; wherein each pronunciation record of each polyphone surname has regional group attribution information and homonyms;
matching the regional group distribution database with a preset polyphone library to determine a parameter corresponding table, wherein the method comprises the following steps:
and matching the typical face image characteristics of each region group classification in the region group distribution database with the region group attribution information of the polyphonic surnames, establishing a mapping relation between the typical face image characteristics and the polyphonic surnames, and determining a parameter corresponding table.
4. The method of claim 3, wherein comparing the customer name with a pre-set polyphone library, and if there are polyphones in the customer name, matching the customer face characteristics with a regional population distribution database, determining regional population information to which the customer belongs, comprises:
comparing the customer name with a preset polyphone library, if the polyphone exists in the customer name, matching the customer face characteristics with typical face image characteristics in a regional population distribution database, and determining the regional population confidence level of the customer in various regional population classifications;
and screening the regional group confidence in the multiple regional group classifications, classifying the regional group to which the maximum value of the regional group confidence belongs, and determining the regional group to which the client belongs as regional group information.
5. The method of claim 4, wherein the step of determining the broadcasting text of the customer name by matching the pronunciation corresponding to the polyphones in the customer name according to the regional group information to which the customer belongs through the parameter correspondence table and replacing the polyphones with homophones by a direct-tone method comprises the steps of:
according to regional group information of a client, matching target pronunciation of regional group attribution information corresponding to polyphones in a client name through a mapping relation of a parameter corresponding table, finding homophones of target pronunciation corresponding to the polyphones, replacing the polyphones with homophones with only one pronunciation by using a direct-tone method, and determining a client name broadcasting text.
6. A name broadcasting device, comprising:
the information acquisition module is used for acquiring regional group face information and client face information;
the regional group distribution database building module is used for building a regional group distribution database according to regional group face information;
the parameter corresponding table determining module is used for matching the regional group distribution database with a preset polyphone library to determine a parameter corresponding table;
the client name and client face feature determining module is used for determining the client name and the client face feature according to the client face information;
the regional group information determining module is used for comparing the name of the client with a preset polyphone library, and if the polyphone exists in the name of the client, matching the face characteristics of the client with a regional group distribution database to determine the regional group information of the client;
the client name broadcasting text determining module is used for matching the pronunciation corresponding to the polyphone in the client name through the parameter corresponding table according to the regional group information of the client, and replacing the polyphone with the homophone by using a direct sound method to determine the client name broadcasting text;
and the name broadcasting module is used for converting the client name broadcasting text into voice and broadcasting the client name.
7. The apparatus of claim 6, wherein the regional population face information comprises: the method comprises the steps of a designated ethnic distribution and face image, an undetermined ethnic distribution and face image, a drainage basin ethnic distribution and face image, an average face model and face characteristics of each province;
the regional group distribution database building module is specifically configured to:
dividing regional group classification, extracting regional group face information to the regional group classification, identifying the regional group face information divided into the same regional group classification through a deep learning framework, and determining typical face image characteristics of each regional group classification;
and establishing a regional group distribution database according to the typical face image characteristics of each regional group classification.
8. The apparatus of claim 7, wherein the pre-set polyphonic word stock comprises: all polyphone surnames; wherein each pronunciation record of each polyphone surname has regional group attribution information and homonyms;
the parameter corresponding table determining module is specifically configured to:
and matching the typical face image characteristics of each region group classification in the region group distribution database with the region group attribution information of the polyphonic surnames, establishing a mapping relation between the typical face image characteristics and the polyphonic surnames, and determining a parameter corresponding table.
9. The apparatus of claim 8, wherein the client local group information determining module is specifically configured to:
comparing the customer name with a preset polyphone library, if the polyphone exists in the customer name, matching the customer face characteristics with typical face image characteristics in a regional population distribution database, and determining the regional population confidence level of the customer in various regional population classifications;
and screening the regional group confidence in the multiple regional group classifications, classifying the regional group to which the maximum value of the regional group confidence belongs, and determining the regional group to which the client belongs as regional group information.
10. The apparatus of claim 9, wherein the client name broadcast text determination module is specifically configured to:
according to regional group information of a client, matching target pronunciation of regional group attribution information corresponding to polyphones in a client name through a mapping relation of a parameter corresponding table, finding homophones of target pronunciation corresponding to the polyphones, replacing the polyphones with homophones with only one pronunciation by using a direct-tone method, and determining a client name broadcasting text.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 5 when executing the computer program.
12. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program for executing the method of any one of claims 1 to 5.
CN202010644225.6A 2020-07-07 2020-07-07 Name broadcasting method and device Active CN111651976B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010644225.6A CN111651976B (en) 2020-07-07 2020-07-07 Name broadcasting method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010644225.6A CN111651976B (en) 2020-07-07 2020-07-07 Name broadcasting method and device

Publications (2)

Publication Number Publication Date
CN111651976A CN111651976A (en) 2020-09-11
CN111651976B true CN111651976B (en) 2023-08-25

Family

ID=72352556

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010644225.6A Active CN111651976B (en) 2020-07-07 2020-07-07 Name broadcasting method and device

Country Status (1)

Country Link
CN (1) CN111651976B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007071904A (en) * 2005-09-02 2007-03-22 Yamaha Corp Speaking learning support system by region
CN103455167A (en) * 2013-08-18 2013-12-18 苏州量跃信息科技有限公司 Method, client and system for adjusting input method editor (IME) corpus based on geographical region information
CN103680493A (en) * 2013-12-19 2014-03-26 百度在线网络技术（北京）有限公司 Voice data recognition method and device for distinguishing regional accents
JP2018200452A (en) * 2017-05-30 2018-12-20 アルパイン株式会社 Voice recognition device and voice recognition method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007071904A (en) * 2005-09-02 2007-03-22 Yamaha Corp Speaking learning support system by region
CN103455167A (en) * 2013-08-18 2013-12-18 苏州量跃信息科技有限公司 Method, client and system for adjusting input method editor (IME) corpus based on geographical region information
CN103680493A (en) * 2013-12-19 2014-03-26 百度在线网络技术（北京）有限公司 Voice data recognition method and device for distinguishing regional accents
JP2018200452A (en) * 2017-05-30 2018-12-20 アルパイン株式会社 Voice recognition device and voice recognition method

Also Published As

Publication number Publication date
CN111651976A (en) 2020-09-11

Similar Documents

Publication Publication Date Title
CN109918680B (en) Entity identification method and device and computer equipment
CN107291783B (en) Semantic matching method and intelligent equipment
CN106776544B (en) Character relation recognition method and device and word segmentation method
CN106057206B (en) Sound-groove model training method, method for recognizing sound-groove and device
CN108388674B (en) Method and device for pushing information
CN105678625B (en) A kind of method and apparatus of determining subscriber identity information
CN106980652B (en) Intelligent question and answer method and system
CN109299471B (en) Text matching method, device and terminal
CN107943786B (en) Chinese named entity recognition method and system
CN105678129B (en) A kind of method and apparatus of determining subscriber identity information
CN109408821A (en) A kind of corpus generation method, calculates equipment and storage medium at device
CN107862058B (en) Method and apparatus for generating information
CN112035599A (en) Query method and device based on vertical search, computer equipment and storage medium
CN111241853B (en) Session translation method, device, storage medium and terminal equipment
CN109344396A (en) Text recognition method, device and computer equipment
CN109872714A (en) A kind of method, electronic equipment and storage medium improving accuracy of speech recognition
CN114387061A (en) Product pushing method and device, electronic equipment and readable storage medium
CN113782026A (en) Information processing method, device, medium and equipment
CN113903361A (en) Speech quality detection method, device, equipment and storage medium based on artificial intelligence
CN112948429B (en) Data reporting method, device and equipment
CN113761137B (en) Method and device for extracting address information
CN111651976B (en) Name broadcasting method and device
CN113192534A (en) Address search method and device, electronic equipment and storage medium
CN114528851B (en) Reply sentence determination method, reply sentence determination device, electronic equipment and storage medium
CN115691503A (en) Voice recognition 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