CN110246493A - Address book contact lookup method, device and storage medium - Google Patents

Address book contact lookup method, device and storage medium Download PDF

Info

Publication number
CN110246493A
CN110246493A CN201910372690.6A CN201910372690A CN110246493A CN 110246493 A CN110246493 A CN 110246493A CN 201910372690 A CN201910372690 A CN 201910372690A CN 110246493 A CN110246493 A CN 110246493A
Authority
CN
China
Prior art keywords
contact person
address list
information
word slot
word
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.)
Pending
Application number
CN201910372690.6A
Other languages
Chinese (zh)
Inventor
陈曼妮
肖蒙
聂聪
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.)
Apollo Zhilian Beijing Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co 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 Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201910372690.6A priority Critical patent/CN110246493A/en
Publication of CN110246493A publication Critical patent/CN110246493A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M1/00Substation equipment, e.g. for use by subscribers
    • H04M1/26Devices for calling a subscriber
    • H04M1/27Devices whereby a plurality of signals may be stored simultaneously
    • H04M1/274Devices whereby a plurality of signals may be stored simultaneously with provision for storing more than one subscriber number at a time, e.g. using toothed disc
    • H04M1/2745Devices whereby a plurality of signals may be stored simultaneously with provision for storing more than one subscriber number at a time, e.g. using toothed disc using static electronic memories, e.g. chips
    • H04M1/27453Directories allowing storage of additional subscriber data, e.g. metadata
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M1/00Substation equipment, e.g. for use by subscribers
    • H04M1/26Devices for calling a subscriber
    • H04M1/27Devices whereby a plurality of signals may be stored simultaneously
    • H04M1/274Devices whereby a plurality of signals may be stored simultaneously with provision for storing more than one subscriber number at a time, e.g. using toothed disc
    • H04M1/2745Devices whereby a plurality of signals may be stored simultaneously with provision for storing more than one subscriber number at a time, e.g. using toothed disc using static electronic memories, e.g. chips
    • H04M1/27467Methods of retrieving data
    • H04M1/2748Methods of retrieving data by matching character strings
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223Execution procedure of a spoken command

Abstract

The embodiment of the present invention proposes a kind of address book contact lookup method, device and computer readable storage medium.Wherein address book contact lookup method includes: to receive voice dial instruction;Contact person's word slot is extracted from voice dial instruction;Obtain the information of address list;The information of the address list and contact person's word slot are matched using appellation normalization creep function;Voice dial instruction corresponding contact person in the address list is determined according to matching result.The embodiment of the present invention is by appellation normalization creep function in combination with common expression way and user's habit, get rid of the limitation of the prime word slot information searching by contact person, corresponding contact person can be correctly locked in address list for the habit appellation of user, user experience is good.

Description

Address book contact lookup method, device and storage medium
Technical field
The present invention relates to information technology field more particularly to a kind of address book contact lookup methods, device and computer Readable storage medium storing program for executing.
Background technique
User can set the pet name or different labels when communication terminal is stored in address book contact to each contact person. When being linked up using communication terminal and contact person, such as when passing through voice dial phone, the phonetic order of user's sending In would generally be comprising to the spoken appellation of contact person.And the spoken appellation to contact person's habit in phonetic order is usually and user The pet name of setting is related to label.
It identifies and the method for searching address book contact information is usually: in the slot for extracting contact person using semantic parsing Behind position, contact person's word slot is directly subjected to lookup matching with the name in user communication record.Such as utilize initial or element With the methods of find approximation, and return to user.
The above method is primarily present following defect:
1. contact person's word slot is directly carried out lookup matching with the name in user communication record, extracts and join for user instruction When being people's word slot, due to the diversity of spoken appellation, it is difficult to correctly lock corresponding relationship people's name using the result that word slot extracts, Contact person is searched in address list for the later period and increases difficulty.
2. the search of address list is not bound with the label that user sets up, the limitation of search is caused.
Summary of the invention
The embodiment of the present invention provides a kind of address book contact lookup method, device and computer readable storage medium, with Solve one or more technical problems in the prior art.
In a first aspect, the embodiment of the invention provides a kind of address book contact lookup methods, comprising:
Receive voice dial instruction;
Contact person's word slot is extracted from voice dial instruction;
Obtain the information of address list;
The information of the address list and contact person's word slot are matched using appellation normalization creep function;
Voice dial instruction corresponding contact person in the address list is determined according to matching result.
In one embodiment, before the instruction of reception voice dial, further includes:
According to the historical data of voice dial and the dictionary information training appellation normalization creep function.
In one embodiment, contact person's word slot is extracted from voice dial instruction, comprising:
The voice dial is instructed and carries out moditied processing, the moditied processing includes deleting in the voice dial instruction Redundancy talk about art;
Contact person's word slot is extracted from the voice dial instruction after the moditied processing.
In one embodiment, contact person's word slot is extracted from the voice dial instruction after the moditied processing, comprising:
Voice dial instruction after the moditied processing is parsed, user's intention and slot position are obtained;
In the case where in the slot position that the user parsed is intended to make a phone call and parses containing contact person's slot position, mention Take contact person's word slot.
In one embodiment, using appellation normalization creep function by the information of the address list and contact person's word slot It is matched, comprising:
Appellation normalized is carried out to contact person's word slot using the appellation normalization creep function;
Contact person's word slot after the information and normalized of the address list is matched.
In one embodiment, appellation normalization is carried out to contact person's word slot using the appellation normalization creep function Processing, comprising:
Obtain the synonym collection of contact person's word slot;
Using the either element in the synonym collection of contact person's word slot as contact person's word slot after normalized, For being matched with the information of the address list.
In one embodiment, the information of address list is obtained, comprising:
The record of the address list is obtained, the record of the address list includes name of contact person, the contact tag, contact person At least one of the pet name, contact person's remarks;
Obtain the address list records corresponding associational word;
Using the record of the address list and the associational word as the information of the address list, it is used for and the contact person Word slot is matched.
In one embodiment, using appellation normalization creep function by the information of the address list and contact person's word slot It is matched, comprising:
For the information setting matching priority of the address list, the matching priority includes: the name of contact person, institute State the contact tag, contact person's pet name, contact person's remarks and the associational word with contact person's word slot into When row matching, corresponding priority match rank;
It is matched using the non-match information of the matching highest priority with contact person's word slot, it is described not match Information is not carry out the information of matching operation in the information of the address list with contact person's word slot;
When not determining matching result, returns and execute the non-match information using the matching highest priority The step of being matched with contact person's word slot.
Second aspect, the embodiment of the invention provides a kind of address book contacts to search device, comprising:
Instruction receiving unit, for receiving voice dial instruction;
Word slot extraction unit, for extracting contact person's word slot from voice dial instruction;
Address list acquiring unit, for obtaining the information of address list;
Matching unit is used for: using appellation normalization creep function by the information of the address list and contact person's word slot into Row matching;
Determination unit is used for: determining that the voice dial instruction is corresponding in the address list according to matching result It is people.
In one embodiment, described device further includes model training unit, and the model training unit is used for:
According to the historical data of voice dial and the dictionary information training appellation normalization creep function.
In one embodiment, institute's predicate slot extraction unit includes:
Subelement is modified, carries out moditied processing for instructing to the voice dial, the moditied processing includes deleting institute State the redundancy words art in voice dial instruction;
Subelement is extracted, for extracting contact person's word slot from the voice dial instruction after the moditied processing.
In one embodiment, the extraction subelement is used for:
Voice dial instruction after the moditied processing is parsed, user's intention and slot position are obtained;
In the case where in the slot position that the user parsed is intended to make a phone call and parses containing contact person's slot position, mention Take contact person's word slot.
In one embodiment, the matching unit includes:
Normalized subelement, is used for: carrying out appellation to contact person's word slot using the appellation normalization creep function Normalized;
Coupling subelement is matched for contact person's word slot after the information and normalized by the address list.
In one embodiment, the normalized subelement is used for:
Obtain the synonym collection of contact person's word slot;
Using the either element in the synonym collection of contact person's word slot as contact person's word slot after normalized, For being matched with the information of the address list.
In one embodiment, the address list acquiring unit is used for:
The record of the address list is obtained, the record of the address list includes name of contact person, the contact tag, contact person At least one of the pet name, contact person's remarks;
Obtain the address list records corresponding associational word;
Using the record of the address list and the associational word as the information of the address list, it is used for and the contact person Word slot is matched.
In one embodiment, the matching unit is used for:
For the information setting matching priority of the address list, the matching priority includes: the name of contact person, institute State the contact tag, contact person's pet name, contact person's remarks and the associational word with contact person's word slot into When row matching, corresponding priority match rank;
It is matched using the non-match information of the matching highest priority with contact person's word slot, it is described not match Information is not carry out the information of matching operation in the information of the address list with contact person's word slot;
When not determining matching result, returns and execute the non-match information using the matching highest priority The step of being matched with contact person's word slot.
The third aspect, the embodiment of the invention provides a kind of address book contacts to search device, and the function of described device can Corresponding software realization can also be executed by hardware by hardware realization.The hardware or software include one or more Module corresponding with above-mentioned function.
It include processor and memory in the structure of described device in a possible design, the memory is used for Storage supports described device to execute the program of above-mentioned address book contact lookup method, the processor is configured to for executing The program stored in the memory.Described device can also include communication interface, for logical with other equipment or communication network Letter.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage mediums, for memory communicating record connection People searches computer software instructions used in device comprising for executing involved in above-mentioned address book contact lookup method Program.
A technical solution in above-mentioned technical proposal has the following advantages that or the utility model has the advantages that by appellation normalization creep function In combination with common expression way and user's habit, the limitation of the prime word slot information searching by contact person is got rid of, it can Corresponding contact person is correctly locked in address list for the habit appellation of user, user experience is good.
Another technical solution in above-mentioned technical proposal has the following advantages that or the utility model has the advantages that by address list information It is comprehensive matching and association, expand search range, enhance lookup dynamics, also provide higher confidence for similarity mode Degree.
Another technical solution in above-mentioned technical proposal has the following advantages that or the utility model has the advantages that institute before semanteme parsing It states voice dial instruction and carries out moditied processing, the redundancy deleted in voice dial instruction talks about art, such as eliminates auxiliary words of mood mouth Language, the voice dial instruction for crossing moditied processing are easier to carry out dissection process during carrying out semantic understanding, Keep the result of dissection process more accurate.
Above-mentioned general introduction is merely to illustrate that the purpose of book, it is not intended to be limited in any way.Except foregoing description Schematical aspect, except embodiment and feature, by reference to attached drawing and the following detailed description, the present invention is further Aspect, embodiment and feature, which will be, to be readily apparent that.
Detailed description of the invention
In the accompanying drawings, unless specified otherwise herein, otherwise indicate the same or similar through the identical appended drawing reference of multiple attached drawings Component or element.What these attached drawings were not necessarily to scale.It should be understood that these attached drawings depict only according to the present invention Disclosed some embodiments, and should not serve to limit the scope of the present invention.
Fig. 1 shows the flow chart of address book contact lookup method according to an embodiment of the present invention.
Fig. 2 shows the processes of extraction contact person's word slot of address book contact lookup method according to an embodiment of the present invention Figure.
Fig. 3 shows the matching flow chart of address book contact lookup method according to an embodiment of the present invention.
Fig. 4 shows the flow chart of address book contact lookup method according to an embodiment of the present invention.
Fig. 5 shows the structural block diagram that address book contact according to an embodiment of the present invention searches device.
Fig. 6 shows the structural block diagram that address book contact according to an embodiment of the present invention searches device.
Fig. 7 shows the structural frames that address book contact according to an embodiment of the present invention searches the word slot extraction unit of device Figure.
Fig. 8 shows the structural block diagram that address book contact according to an embodiment of the present invention searches the matching unit of device.
Fig. 9 shows the structural block diagram that address book contact according to an embodiment of the present invention searches device.
Specific embodiment
Hereinafter, certain exemplary embodiments are simply just described.As one skilled in the art will recognize that Like that, without departing from the spirit or scope of the present invention, described embodiment can be modified by various different modes. Therefore, attached drawing and description are considered essentially illustrative rather than restrictive.
Fig. 1 shows the flow chart of address book contact lookup method according to an embodiment of the present invention.As shown in Figure 1, this is logical News record contact searching method
Step S110 receives voice dial instruction;
Step S120 extracts contact person's word slot from voice dial instruction;
Step S130 obtains the information of address list;
Step S140 is carried out the information of the address list and contact person's word slot using appellation normalization creep function Match;
Step S150 determines voice dial instruction corresponding contact person in the address list according to matching result.
Name of contact person, contact phone number are generally included in the address book contact information of communication terminal, there are also right Each contact person sets the pet name or different labels and the remark information of contact person etc..For example, address book contact record 1 is protected The information deposited are as follows: " name of contact person: king xx;Telephone number: 185xxxxxxxx;Label: father ".For another example, address book contact The information that record 2 saves are as follows: " name of contact person: xx;Telephone number: 132xxxxxxxx;The pet name: Xiao Ming;Label: primary school is same It learns;Remark information: partner ".
When being linked up using communication terminal and contact person, such as when passing through voice dial phone, in many cases It may and not include name of contact person in the phonetic order that user issues, but the spoken appellation of the habit to contact person can be included. And it is usually related to the pet name set by user, label or remark information to the spoken appellation of contact person's habit in phonetic order.
For example, may issue " phoning daddy " when user wishes to dial the phone of its father, " make me Father ", he " makes a phone call to my father " and etc. different instructions.If directly will appellation as " daddy ", " my father ", " my father " and " name " in address list is matched, and search can not often find matched result in address list.If by user's language Spoken appellation in sound instruction is matched comprehensively with address list information, including believing with the pet name, label and the remarks in address list Breath is matched, then can accurately lock the corresponding name of contact person of phonetic order.
For another example, when user attempts to dial the phone of its boss by voice, there is no directly deposited in the address list of user Enter contact person's boss and its corresponding number, but user inputted the label of " manager " to the xx in address list.Equally, by user Spoken appellation in phonetic order is matched comprehensively with address list information, can accurately lock the corresponding connection of phonetic order People's name can return to desired result to user.
" daddy ", " my father ", " my father " and boss in above-mentioned example are colloquial style appellations in user speech instruction, It can be described as the prime word slot information of contact person.Common spoken appellation is done normalized by this patent embodiment, and combines user Address list information matches the corresponding address book contact of colloquial style appellation in phonetic order to identify.This method supports user instruction Diversity, being embodied as not limiting in the voice dial instruction of user must include name of contact person.
Specifically, in step s 110, the voice dial instruction of user is received, includes to thinking in voice dial instruction The appellation for the contact person to be made a phone call.In the step s 120, it is instructed according to the voice dial of user, to user's intention and slot position It is parsed, extracts contact person's word slot.In step s 130, the information of address list is obtained.The information of the address list includes logical That interrogates the record information and the address list recorded records corresponding associational word.It has been observed that the record information of address list may include Name of contact person, the pet name set by user, label or remark information etc..It, will using appellation normalization creep function in step S140 The information of the address list and contact person's word slot match, and export matching result and matching similarity.In step S150 In, voice dial instruction corresponding contact person in the address list is determined according to matching result, is provided a user described Matching result and corresponding number.
Above-mentioned technical proposal has the following advantages that or the utility model has the advantages that by appellation normalization creep function in combination with common expression side Formula and user's habit, get rid of the limitation of the prime word slot information searching by contact person, can claim for the habit of user Meaning correctly locks corresponding contact person in address list, and user experience is good.
In one embodiment, before the instruction of reception voice dial, further includes:
According to the historical data of voice dial and the dictionary information training appellation normalization creep function.
In this embodiment, it can be generated according to historical data and online dictionary information training appellation normalization creep function Colloquial style entry can be rewritten and carry out the model of entry similarity mode.
Wherein, " historical data " may include the data of voice dial accumulated online.For example, certain user dials in voice When making a phone call, colloquial style instruction " phoning daddy " is said.If this appellation is not found in address list It is matching as a result, the record for namely having result not recall, then collect the record that this result is not recalled, as training mould " historical data " that type uses.In the examples described above, contact person's word slot " daddy " can be used as the entry of contact person's pet name, the spoken language Changing instruction " phoning daddy " can be used as the training sample of model.
" dictionary information " includes dictionary and knowledge mapping.It may include the entry for the related appellation being pre-created in dictionary, with And the mapping relations between entry.For example, existing mapping relations are synonyms between entry " father " and " father ".In addition, The mapping relations between entry can be recorded by knowledge mapping.Such as " father ", " father ", between " daddy " these appellations be mutual For the relationship of synonym.
" rewriting colloquial style entry " may include error correction, extension synonym and appellation normalization.
Wherein, error correction includes correcting the accent due to the voice dial instruction of user, volume etc. bring identification partially Difference.In view of user might have, mandarin is nonstandard, have an accent or enunciates not enough clear, and speaking volume is small and has external noise Situations such as, due to the above accent, volume etc. the problem of can affect greatly identification, can be first to phonetic order In the colloquial style entry that recognizes carry out error correction.Such as the tone of dialect is adjusted, VOLUME UP or removes external noise Deng.
Extension synonym includes: to obtain the synonym of current entry according to " historical data " and " dictionary information ", such as look for To other synonymous pet names.Then it according to the synonym of all current entries found, is matched with address list.
Appellation normalization includes: after carrying out synonym extension to the prime word slot information of contact person, to obtain prime word slot The synonym of information, these all synonym word slots can be represented with a word, this process is known as appellation normalization.? That is specifying a core word in the synonym collection of contact person's word slot, the common of the synonym of contact person's word slot is indicated Meaning, this core word are exactly the normalization result to the prime word slot information of contact person.In one example, appellation normalizes Processing may include colloquial style normalization.If contact person's slot position in user instruction is " old father ", carries out synonym and extend to obtain The synonym word slot of these colloquial style appellations can be normalized to " father " by " daddy ", " father ", " father ", by " father " this One group of synonym representated by a normalization result is matched with address list information.
Fig. 2 shows the processes of extraction contact person's word slot of address book contact lookup method according to an embodiment of the present invention Figure.As shown in Fig. 2, in one embodiment, the step S120 in Fig. 1 extracts contact person's word slot from voice dial instruction, Include:
Step S210 carries out moditied processing from instructing to the voice dial, and the moditied processing includes deleting institute's predicate Sound dials the redundancy words art in instruction;
Step S220 extracts contact person's word slot from from the voice dial instruction after the moditied processing.
For example, sending the voice dial instruction that user issues to cloud server.Then language of the cloud service to user Sound is dialed instruction and is modified, and art if redundancy is left out.Such as can remove the informals such as auxiliary words of mood, after making moditied processing Voice dial instructs words more succinct, is ready for the semantic understanding in later period.In one example, user issues voice and dials Play instruction: ", I must make a phone call to mother ", become " making a phone call to mother " after moditied processing.
In the examples described above, contact person's word slot " mother " is extracted again after instructing moditied processing to voice dial.Wherein, word Slot is exactly keyword, is to be intended to be converted by user in dialog procedure clearly to reply the information for instructing required completion.In task In formula conversational system, it is intended that and word slot integrally represents conversational system to the understanding result of user session.For example, in user session Some necessary qualifications be to need to be understood by system, and influence the implementing result of conversational system, this restriction Condition is referred to as word slot (slot).In one example, " change to central station " in " central station " be exactly " TV station " language Adopted word slot, it can influence the system execution that this is intended to " zapping " to a certain extent.
Another technical solution in above-mentioned technical proposal has the following advantages that or the utility model has the advantages that institute before semanteme parsing It states voice dial instruction and carries out moditied processing, delete the redundancy in voice dial instruction and talk about art, the voice for crossing moditied processing is dialled It plays instruction and is easier to carry out dissection process during carrying out semantic understanding, also make the result of dissection process more accurate.
In one embodiment, contact person's word slot is extracted from the voice dial instruction after the moditied processing, comprising:
Voice dial instruction after the moditied processing is parsed, user's intention and slot position are obtained;
In the case where in the slot position that the user parsed is intended to make a phone call and parses containing contact person's slot position, mention Take contact person's word slot.
For example, the voice dial for user instructs " making a phone call to mother ", can obtain being intended to dial by parsing Phone parses containing contact person's slot position, can extract contact person's word slot " mother ".
In one embodiment, using appellation normalization creep function by the information of the address list and contact person's word slot It is matched, comprising:
Appellation normalized is carried out to contact person's word slot using the appellation normalization creep function;
Contact person's word slot after the information and normalized of the address list is matched.
It has been observed that the prime word slot to contact person can be believed after carrying out appellation normalized to contact person's word slot One group of synonym representated by the normalization result of breath is matched with address list information.By appellation normalized, get rid of By the limitation of the prime word slot information searching of contact person, can correctly be locked in address list for the habit appellation of user Fixed corresponding contact person.
In one embodiment, appellation normalization is carried out to contact person's word slot using the appellation normalization creep function Processing, comprising:
Obtain the synonym collection of contact person's word slot;
Using the either element in the synonym collection of contact person's word slot as contact person's word slot after normalized, For being matched with the information of the address list.
For example, the contact person's word slot extracted is " mother ", then can be wrapped in the synonym collection of the contact person's word slot obtained Include " mother ", " old mother ", " mother " etc..When matching contact person's word slot with the information of user communication record, need to join It is that either element in the synonym collection of people's word slot is matched with the information of user communication record.At appellation normalization Reason is accustomed to, even if the habit appellation of user and the information of user communication record are not same in conjunction with common expression way and user Entry, can also lock corresponding contact person, and user experience is good.
In one embodiment, the information of address list is obtained, comprising:
The record of the address list is obtained, the record of the address list includes name of contact person, the contact tag, contact person At least one of the pet name, contact person's remarks;
Obtain the address list records corresponding associational word;
Using the record of the address list and the associational word as the information of the address list, it is used for and the contact person Word slot is matched.
For example, the information that address book contact record saves are as follows: " name of contact person: xx;Telephone number: 132xxxxxxxx;The pet name: Xiao Ming;Label: primary school classmate;Remark information: partner ".It is recorded for this, remarks letter can be obtained Cease " partner " corresponding associational word, such as " partner ", " companion ", " partner ".By the letter of contact person's word slot and user communication record When breath is matched, need also to match the corresponding associational word that records of user communication record with contact person's word slot.
Another technical solution in above-mentioned technical proposal has the following advantages that or the utility model has the advantages that by address list information It is comprehensive matching and association, expand search range, enhance lookup dynamics, also provide higher confidence for similarity mode Degree.
Fig. 3 shows the matching flow chart of address book contact lookup method according to an embodiment of the present invention.As shown in figure 3, In one embodiment, the step S140 in Fig. 1, using appellation normalization creep function by the information of the address list and described It is that people's word slot matches, comprising:
Step S310 is the information setting matching priority of the address list, and the matching priority includes: the connection People's name, the contact tag, contact person's pet name, contact person's remarks and the associational word are contacted with described When people's word slot matches, corresponding priority match rank;
Step S320 is matched using the non-match information of the matching highest priority with contact person's word slot, The non-match information is not carry out the information of matching operation in the information of the address list with contact person's word slot;
In step S330, in the case of not determining matching result, return execute it is described using the matching highest priority The step of non-match information is matched with contact person's word slot.
It specifically, can be logical for the user in advance when matching contact person's word slot with the information of user communication record The information setting matching priority of news record, to enrich the level of contact information.In above-mentioned steps S310, it can be set up according to user Label and/or the abundant informations contact information such as the pet name level.For example, the first level can be name of contact person;Second Level can be the pet name or label to contact person's setting;Third level can be the word for associating out for the pet name and label Item, if label is that " boudoir honey " can associate " girl friend ".In one example, the sequence of settable matching priority from high to low For the first level, the second level and third level.
After matching priority is arranged for the information of the user communication record, using appellation normalization creep function by abundant layer The information of user communication record and contact person's word slot of extraction after grade match.Specifically, in above-mentioned steps S320 and In step S330, if contact person's word slot is matched with the information of user communication record, the case where finding multiple contact persons Under, that is, at this moment do not determine matching result, then according to the carry out sequence matching of the height of the level of contact person, level more it is high then It is higher with priority.Such as first match the name of contact person of the first level with contact person's word slot, such as by contact person's word slot It is matched with contact person in address list name, if matching result only finds a contact person, using the contact person as matching As a result;If the above-mentioned name of contact person according to the first level is matched to obtain multiple contact persons, by the connection of the second level People's pet name or label are matched with contact person's word slot, if matching result only finds a contact person, using the contact person as Matching result;If matching above-mentioned contact person's pet name or label according to the second level to be matched to obtain multiple contact persons, then will Association's entry of third level is matched with contact person's word slot.
After obtaining matching result by the above matching process, determine the voice dial instruction in institute according to matching result State corresponding contact person in address list.Then matching result is provided a user, and searches for corresponding number and is supplied to user.
Fig. 4 shows the flow chart of address book contact lookup method according to an embodiment of the present invention.As shown in figure 4, one Illustrative address book contact lookup method can comprise the following steps that
Step S41: the voice dial instruction of user's sending: " help is made a phone call to my old father " is received.
Step S42: after carrying out moditied processing to the voice dial instruction of user, " making a phone call to old father " is obtained.
Step S43: carrying out intents to the voice dial instruction after moditied processing and slot position understand, obtains being intended to dial It makes a phone call, contact person's slot position is " old father ".
Step S44: user communication record is imported.
Step S45: the associated information of user communication record, including name of contact person, label, the pet name, remark information are obtained Deng.Such as: the information of address list record 1 are as follows: " contact person: xx.Label: father ";The information of address list record 2 are as follows: " contact person: Boss ... ... ".
Step S46: carrying out colloquial style normalization to " old father " in contact person's slot position using appellation normalization creep function, will The associated information for normalizing one group of synonym representated by result and user communication record carries out similarity mode.
As shown in figure 4, matching example one: " old father " in contact person's slot position matches with the information of address list record 1, " old father " in contact person's slot position and the contact tag " father " of address list record 1 are obtained, there is common meaning (Common): father, and similarity is 90%.
Referring to fig. 4, match example two: " old father " in contact person's slot position matches with the information of address list record 2, obtains The information of " old father " and address list record 2 on to contact person's slot position: " contact person: boss ... ... " has common meaning (Common): nothing, and similarity is 20%.That is, the meaning that the two is not common, similarity are lower.
Step S47: the in summary matching result in step S46, make the conclusion of similarity judgement: similarity is maximum Matching result (max): old father-xx, father.The contact person of " old father " and address list record 1 namely in contact person's slot position mark Sign " father " successful match.
Step S48: matching result is exported to user.Such as output prompt information: " you are intended to dial the phone of xx ? ".
Fig. 5 shows the structural block diagram that address book contact according to an embodiment of the present invention searches device.As shown in figure 5, this The address book contact of inventive embodiments searches device
Instruction receiving unit 100, for receiving voice dial instruction;
Word slot extraction unit 200, for extracting contact person's word slot from voice dial instruction;
Address list acquiring unit 300, for obtaining the information of address list;
Matching unit 400, is used for: using appellation normalization creep function by the information of the address list and contact person's word slot It is matched;
Determination unit 500, is used for: determining that the voice dial instruction is corresponding in the address list according to matching result Contact person.
Fig. 6 shows the structural block diagram that address book contact according to an embodiment of the present invention searches device.As shown in fig. 6, In a kind of embodiment, described device further includes model training unit 600, and the model training unit 600 is used for:
According to the historical data of voice dial and the dictionary information training appellation normalization creep function.
Fig. 7 shows the structural frames that address book contact according to an embodiment of the present invention searches the word slot extraction unit of device Figure.As shown in fig. 7, in one embodiment, institute's predicate slot extraction unit 200 includes:
Subelement 210 is modified, carries out moditied processing for instructing to the voice dial, the moditied processing includes deleting Redundancy in the voice dial instruction talks about art;
Subelement 220 is extracted, for extracting contact person's word slot from the voice dial instruction after the moditied processing.
In one embodiment, the extraction subelement 220 is used for:
Voice dial instruction after the moditied processing is parsed, user's intention and slot position are obtained;
In the case where in the slot position that the user parsed is intended to make a phone call and parses containing contact person's slot position, mention Take contact person's word slot.
Fig. 8 shows the structural block diagram that address book contact according to an embodiment of the present invention searches the matching unit of device.Such as Shown in Fig. 8, in one embodiment, the matching unit 400 includes:
Normalized subelement 410, is used for: being claimed using the appellation normalization creep function to contact person's word slot Call normalized;
Coupling subelement 420, for contact person's word slot progress after the information and normalized by the address list Match.
In one embodiment, the normalized subelement 410 is used for:
Obtain the synonym collection of contact person's word slot;
Using the either element in the synonym collection of contact person's word slot as contact person's word slot after normalized, For being matched with the information of the address list.
In one embodiment, the address list acquiring unit 300 is used for:
The record of the address list is obtained, the record of the address list includes name of contact person, the contact tag, contact person At least one of the pet name, contact person's remarks;
Obtain the address list records corresponding associational word;
Using the record of the address list and the associational word as the information of the address list, it is used for and the contact person Word slot is matched.
In one embodiment, the matching unit 400 is used for:
For the information setting matching priority of the address list, the matching priority includes: the name of contact person, institute State the contact tag, contact person's pet name, contact person's remarks and the associational word with contact person's word slot into When row matching, corresponding priority match rank;
It is matched using the non-match information of the matching highest priority with contact person's word slot, it is described not match Information is not carry out the information of matching operation in the information of the address list with contact person's word slot;
When not determining matching result, returns and execute the non-match information using the matching highest priority The step of being matched with contact person's word slot.
The function that address book contact of the embodiment of the present invention searches each unit in device may refer in the above method Corresponding description, details are not described herein.
Fig. 9 shows the structural block diagram that address book contact according to an embodiment of the present invention searches device.As shown in figure 9, should Device includes: memory 910 and processor 920, and the computer journey that can be run on processor 920 is stored in memory 910 Sequence.The processor 920 realizes the address book contact lookup method in above-described embodiment when executing the computer program.Institute The quantity for stating memory 910 and processor 920 can be one or more.
The device further include:
Communication interface 930 carries out data interaction for being communicated with external device.
Memory 910 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non- Volatile memory), a for example, at least magnetic disk storage.
If memory 910, processor 920 and the independent realization of communication interface 930, memory 910,920 and of processor Communication interface 930 can be connected with each other by bus and complete mutual communication.The bus can be Industry Standard Architecture Structure (ISA, Industry Standard Architecture) bus, external equipment interconnection (PCI, Peripheral Component Interconnect) bus or extended industry-standard architecture (EISA, Extended Industry Standard Architecture) bus etc..The bus can be divided into address bus, data/address bus, control bus etc..For Convenient for indicating, only indicated with a thick line in Fig. 9, it is not intended that an only bus or a type of bus.
Optionally, in specific implementation, if memory 910, processor 920 and communication interface 930 are integrated in one piece of core On piece, then memory 910, processor 920 and communication interface 930 can complete mutual communication by internal interface.
The embodiment of the invention provides a kind of computer readable storage mediums, are stored with computer program, the program quilt Processor realizes any method in above-described embodiment when executing.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example Point is included at least one embodiment or example of the invention.Moreover, particular features, structures, materials, or characteristics described It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples Sign is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance Or implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or hidden It include at least one this feature containing ground.In the description of the present invention, the meaning of " plurality " is two or more, unless otherwise Clear specific restriction.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wirings Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory (ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable read-only memory (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other suitable Jie Matter, because can then be edited, be interpreted or when necessary with other for example by carrying out optical scanner to paper or other media Suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer In readable storage medium storing program for executing.The storage medium can be read-only memory, disk or CD etc..
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in its various change or replacement, These should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the guarantor of the claim It protects subject to range.

Claims (18)

1. a kind of address book contact lookup method characterized by comprising
Receive voice dial instruction;
Contact person's word slot is extracted from voice dial instruction;
Obtain the information of address list;
The information of the address list and contact person's word slot are matched using appellation normalization creep function;
Voice dial instruction corresponding contact person in the address list is determined according to matching result.
2. the method according to claim 1, wherein before receiving voice dial instruction, further includes:
According to the historical data of voice dial and the dictionary information training appellation normalization creep function.
3. the method according to claim 1, wherein extracting contact person's word slot from voice dial instruction, comprising:
The voice dial is instructed and carries out moditied processing, the moditied processing include delete it is superfluous in voice dial instruction Remaining words art;
Contact person's word slot is extracted from the voice dial instruction after the moditied processing.
4. according to the method described in claim 3, it is characterized in that, being extracted from the voice dial instruction after the moditied processing Contact person's word slot, comprising:
Voice dial instruction after the moditied processing is parsed, user's intention and slot position are obtained;
In the case where in the slot position that the user parsed is intended to make a phone call and parses containing contact person's slot position, connection is extracted It is people's word slot.
5. method according to claim 1 to 4, which is characterized in that will be described using appellation normalization creep function The information of address list and contact person's word slot match, comprising:
Appellation normalized is carried out to contact person's word slot using the appellation normalization creep function;
Contact person's word slot after the information and normalized of the address list is matched.
6. according to the method described in claim 5, it is characterized in that, using the appellation normalization creep function to contact person's word Slot carries out appellation normalized, comprising:
Obtain the synonym collection of contact person's word slot;
Using the either element in the synonym collection of contact person's word slot as contact person's word slot after normalized, it is used for It is matched with the information of the address list.
7. method according to claim 1 to 4, which is characterized in that obtain the information of address list, comprising:
Obtain the record of the address list, the record of the address list includes that name of contact person, the contact tag, contact person are close At least one of title, contact person's remarks;
Obtain the address list records corresponding associational word;
Using the record of the address list and the associational word as the information of the address list, it is used for and contact person's word slot It is matched.
8. the method according to the description of claim 7 is characterized in that using appellation normalization creep function by the information of the address list It is matched with contact person's word slot, comprising:
For the information setting matching priority of the address list, the matching priority includes: the name of contact person, described Be people's label, contact person's pet name, contact person's remarks and the associational word carries out with contact person's word slot Timing, corresponding priority match rank;
It is matched using the non-match information of the matching highest priority with contact person's word slot, the non-match information It is the information for not carrying out matching operation in the information of the address list with contact person's word slot;
When not determining matching result, returns and execute the non-match information using the matching highest priority and institute State the step of contact person's word slot matches.
9. a kind of address book contact searches device characterized by comprising
Instruction receiving unit, for receiving voice dial instruction;
Word slot extraction unit, for extracting contact person's word slot from voice dial instruction;
Address list acquiring unit, for obtaining the information of address list;
Matching unit is used for: being carried out the information of the address list and contact person's word slot using appellation normalization creep function Match;
Determination unit is used for: determining voice dial instruction corresponding contact person in the address list according to matching result.
10. device according to claim 9, which is characterized in that described device further includes model training unit, the model Training unit is used for:
According to the historical data of voice dial and the dictionary information training appellation normalization creep function.
11. device according to claim 9, which is characterized in that institute's predicate slot extraction unit includes:
Subelement is modified, carries out moditied processing for instructing to the voice dial, the moditied processing includes deleting institute's predicate Sound dials the redundancy words art in instruction;
Subelement is extracted, for extracting contact person's word slot from the voice dial instruction after the moditied processing.
12. device according to claim 11, which is characterized in that the extraction subelement is used for:
Voice dial instruction after the moditied processing is parsed, user's intention and slot position are obtained;
In the case where in the slot position that the user parsed is intended to make a phone call and parses containing contact person's slot position, connection is extracted It is people's word slot.
13. the device according to any one of claim 9 to 12, which is characterized in that the matching unit includes:
Normalized subelement, is used for: carrying out appellation normalizing to contact person's word slot using the appellation normalization creep function Change processing;
Coupling subelement is matched for contact person's word slot after the information and normalized by the address list.
14. device according to claim 13, which is characterized in that the normalized subelement is used for:
Obtain the synonym collection of contact person's word slot;
Using the either element in the synonym collection of contact person's word slot as contact person's word slot after normalized, it is used for It is matched with the information of the address list.
15. the device according to any one of claim 9 to 12, which is characterized in that the address list acquiring unit is used for:
Obtain the record of the address list, the record of the address list includes that name of contact person, the contact tag, contact person are close At least one of title, contact person's remarks;
Obtain the address list records corresponding associational word;
Using the record of the address list and the associational word as the information of the address list, it is used for and contact person's word slot It is matched.
16. device according to claim 15, which is characterized in that the matching unit is used for:
For the information setting matching priority of the address list, the matching priority includes: the name of contact person, described Be people's label, contact person's pet name, contact person's remarks and the associational word carries out with contact person's word slot Timing, corresponding priority match rank;
It is matched using the non-match information of the matching highest priority with contact person's word slot, the non-match information It is the information for not carrying out matching operation in the information of the address list with contact person's word slot;
When not determining matching result, returns and execute the non-match information using the matching highest priority and institute State the step of contact person's word slot matches.
17. a kind of address book contact searches device characterized by comprising
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors Realize such as method described in any item of the claim 1 to 8.
18. a kind of computer readable storage medium, is stored with computer program, which is characterized in that the program is held by processor Such as method described in any item of the claim 1 to 8 is realized when row.
CN201910372690.6A 2019-05-06 2019-05-06 Address book contact lookup method, device and storage medium Pending CN110246493A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910372690.6A CN110246493A (en) 2019-05-06 2019-05-06 Address book contact lookup method, device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910372690.6A CN110246493A (en) 2019-05-06 2019-05-06 Address book contact lookup method, device and storage medium

Publications (1)

Publication Number Publication Date
CN110246493A true CN110246493A (en) 2019-09-17

Family

ID=67883734

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910372690.6A Pending CN110246493A (en) 2019-05-06 2019-05-06 Address book contact lookup method, device and storage medium

Country Status (1)

Country Link
CN (1) CN110246493A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111225100A (en) * 2020-02-18 2020-06-02 北京声智科技有限公司 Method and device for ordering friends in mobile address list
CN111899736A (en) * 2020-07-27 2020-11-06 江西小辣椒通讯技术有限责任公司 Method and system for inputting dialect to make call by robot for old people
CN113992780A (en) * 2021-09-13 2022-01-28 珠海格力电器股份有限公司 Voice dialing method, device, storage medium and equipment
CN115579008A (en) * 2022-12-05 2023-01-06 广州小鹏汽车科技有限公司 Voice interaction method, server and computer readable storage medium

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1432943A (en) * 2002-01-17 2003-07-30 北京标杆网络技术有限公司 Biaogan intelligent searching engine system
CN101146155A (en) * 2007-11-16 2008-03-19 中国电信股份有限公司 An information query method and system based on keys on the voice platform
CN101287203A (en) * 2008-05-28 2008-10-15 宁波高新区同瞻科技有限公司 Rapid searching method for name card holder embedded in mobile phone
CN101986293A (en) * 2010-09-03 2011-03-16 百度在线网络技术(北京)有限公司 Method and equipment for displaying search answer information on search interface
CN102231147A (en) * 2010-11-08 2011-11-02 百度在线网络技术(北京)有限公司 Method, equipment and system for displaying associational words in real time
CN103064962A (en) * 2012-12-31 2013-04-24 安徽科大讯飞信息科技股份有限公司 Information query method and system
CN103139048A (en) * 2011-12-05 2013-06-05 北京神州泰岳软件股份有限公司 Group information reminding method and system
CN103631822A (en) * 2012-08-27 2014-03-12 联想(北京)有限公司 Query method and electronic equipment
CN104580631A (en) * 2013-10-14 2015-04-29 中兴通讯股份有限公司 Dialing method and dialing device
CN107204912A (en) * 2017-04-24 2017-09-26 深圳市元征科技股份有限公司 The voice management method and device of contact person
CN107346325A (en) * 2016-05-04 2017-11-14 中国石油集团长城钻探工程有限公司 Information query method and device
CN107679184A (en) * 2017-09-30 2018-02-09 苏州亿科赛卓电子科技有限公司 A kind of instant communication software contact searching method and device
CN108122555A (en) * 2017-12-18 2018-06-05 北京百度网讯科技有限公司 The means of communication, speech recognition apparatus and terminal device
US10089981B1 (en) * 2017-03-09 2018-10-02 Amazon Technologies, Inc. Messaging account disambiguation
CN108766437A (en) * 2018-05-31 2018-11-06 平安科技(深圳)有限公司 Audio recognition method, device, computer equipment and storage medium
CN109063166A (en) * 2018-08-15 2018-12-21 中国联合网络通信集团有限公司 A kind of voice inquiry method and device, user equipment

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1432943A (en) * 2002-01-17 2003-07-30 北京标杆网络技术有限公司 Biaogan intelligent searching engine system
CN101146155A (en) * 2007-11-16 2008-03-19 中国电信股份有限公司 An information query method and system based on keys on the voice platform
CN101287203A (en) * 2008-05-28 2008-10-15 宁波高新区同瞻科技有限公司 Rapid searching method for name card holder embedded in mobile phone
CN101986293A (en) * 2010-09-03 2011-03-16 百度在线网络技术(北京)有限公司 Method and equipment for displaying search answer information on search interface
CN102231147A (en) * 2010-11-08 2011-11-02 百度在线网络技术(北京)有限公司 Method, equipment and system for displaying associational words in real time
CN103139048A (en) * 2011-12-05 2013-06-05 北京神州泰岳软件股份有限公司 Group information reminding method and system
CN103631822A (en) * 2012-08-27 2014-03-12 联想(北京)有限公司 Query method and electronic equipment
CN103064962A (en) * 2012-12-31 2013-04-24 安徽科大讯飞信息科技股份有限公司 Information query method and system
CN104580631A (en) * 2013-10-14 2015-04-29 中兴通讯股份有限公司 Dialing method and dialing device
CN107346325A (en) * 2016-05-04 2017-11-14 中国石油集团长城钻探工程有限公司 Information query method and device
US10089981B1 (en) * 2017-03-09 2018-10-02 Amazon Technologies, Inc. Messaging account disambiguation
CN107204912A (en) * 2017-04-24 2017-09-26 深圳市元征科技股份有限公司 The voice management method and device of contact person
CN107679184A (en) * 2017-09-30 2018-02-09 苏州亿科赛卓电子科技有限公司 A kind of instant communication software contact searching method and device
CN108122555A (en) * 2017-12-18 2018-06-05 北京百度网讯科技有限公司 The means of communication, speech recognition apparatus and terminal device
CN108766437A (en) * 2018-05-31 2018-11-06 平安科技(深圳)有限公司 Audio recognition method, device, computer equipment and storage medium
CN109063166A (en) * 2018-08-15 2018-12-21 中国联合网络通信集团有限公司 A kind of voice inquiry method and device, user equipment

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111225100A (en) * 2020-02-18 2020-06-02 北京声智科技有限公司 Method and device for ordering friends in mobile address list
CN111899736A (en) * 2020-07-27 2020-11-06 江西小辣椒通讯技术有限责任公司 Method and system for inputting dialect to make call by robot for old people
CN113992780A (en) * 2021-09-13 2022-01-28 珠海格力电器股份有限公司 Voice dialing method, device, storage medium and equipment
CN113992780B (en) * 2021-09-13 2022-11-18 珠海格力电器股份有限公司 Voice dialing method, device, storage medium and equipment
CN115579008A (en) * 2022-12-05 2023-01-06 广州小鹏汽车科技有限公司 Voice interaction method, server and computer readable storage medium

Similar Documents

Publication Publication Date Title
CN110246493A (en) Address book contact lookup method, device and storage medium
CN110377716B (en) Interaction method and device for conversation and computer readable storage medium
KR102222317B1 (en) Speech recognition method, electronic device, and computer storage medium
US10917758B1 (en) Voice-based messaging
US11049493B2 (en) Spoken dialog device, spoken dialog method, and recording medium
US9666188B2 (en) System and method of performing automatic speech recognition using local private data
CN102473413B (en) Speech translation system, dictionary server device, and program
CN113793603A (en) Recognizing accented speech
US20060206324A1 (en) Methods and apparatus relating to searching of spoken audio data
CN108647194B (en) Information extraction method and device
US11062701B2 (en) Answering device, control method for answering device, and recording medium
CN108039175B (en) Voice recognition method and device and server
US20220093103A1 (en) Method, system, and computer-readable recording medium for managing text transcript and memo for audio file
KR101763679B1 (en) Method and computer system of analyzing communication situation based on dialogue act information
CN110164416B (en) Voice recognition method and device, equipment and storage medium thereof
CN108121455A (en) Identify method and device for correcting
US10417345B1 (en) Providing customer service agents with customer-personalized result of spoken language intent
TWI752406B (en) Speech recognition method, speech recognition device, electronic equipment, computer-readable storage medium and computer program product
CN109635125B (en) Vocabulary atlas building method and electronic equipment
CN106603792A (en) Number search device
CN113051384A (en) User portrait extraction method based on conversation and related device
CN109712613B (en) Semantic analysis library updating method and device and electronic equipment
CA3131060A1 (en) Speech analysis system
US11582174B1 (en) Messaging content data storage
CN111626059B (en) Information processing method and device

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
TA01 Transfer of patent application right

Effective date of registration: 20211013

Address after: 100176 Room 101, 1st floor, building 1, yard 7, Ruihe West 2nd Road, economic and Technological Development Zone, Daxing District, Beijing

Applicant after: Apollo Zhilian (Beijing) Technology Co.,Ltd.

Address before: 100085 Baidu Building, 10 Shangdi Tenth Street, Haidian District, Beijing

Applicant before: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd.

TA01 Transfer of patent application right