CN103533144A - Method and equipment for storing keywords in call records of mobile communication equipment - Google Patents

Method and equipment for storing keywords in call records of mobile communication equipment Download PDF

Info

Publication number
CN103533144A
CN103533144A CN201310446351.0A CN201310446351A CN103533144A CN 103533144 A CN103533144 A CN 103533144A CN 201310446351 A CN201310446351 A CN 201310446351A CN 103533144 A CN103533144 A CN 103533144A
Authority
CN
China
Prior art keywords
word
weight allocation
words
allocation value
calling record
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.)
Granted
Application number
CN201310446351.0A
Other languages
Chinese (zh)
Other versions
CN103533144B (en
Inventor
林明
杨柳
白璐
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.)
XFusion Digital Technologies Co Ltd
Original Assignee
Huawei Technologies 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 Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to CN201310446351.0A priority Critical patent/CN103533144B/en
Publication of CN103533144A publication Critical patent/CN103533144A/en
Application granted granted Critical
Publication of CN103533144B publication Critical patent/CN103533144B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Abstract

The embodiment of the invention discloses a method and equipment for storing keywords in call records of mobile communication equipment. The method provided by the embodiment of the invention comprises the steps that call record sound corresponding to the call records is processed, a word set corresponding to the call record sound is obtained, and the word set is a word set occurring in the call record sound; in addition, one type or several types of weight assigned values corresponding to words in the word set are calculated, the weight values of the words are calculated according to the one type or several types of the weight assigned values corresponding to the words in the word set, words with the weights ranged in the front Nth in the word set or words with the weights greater than or equal to the preset value are used as keywords to be stored in the call records, so users can determine conversation contents in a way without listening to the call record sound, the problems of source occupation and power source consumption caused by call record sound playing can be effectively avoided, and resources can be effectively saved.

Description

In the message registration of mobile communication equipment, preserve the method and apparatus of keyword
Technical field
The present invention relates to communication technical field, relate in particular to the method and apparatus of preserving keyword in the message registration of mobile communication equipment.
Background technology
Along with social development, the user who uses mobile communication equipment to converse is more and more, and in the message registration of mobile communication equipment, can preserve the dialing of this user, received call and missed call, and can record call object, the duration of call, air time that each is taken on the telephone, yet, because call is more, and some call is to liking stranger, conversation content when user possibly cannot remember call.
At present, the conversation content between the call object that if user need to preserve and it is conversed, can adopt the mode of calling record to preserve conversation content, and existing mobile communication equipment substantially all possesses the function of calling record, do not relating under the prerequisite of law privacy concern, user only need to open the sound-recording function on mobile communication equipment after connecting phone, so after end of conversation, calling record will be kept on the storage medium of equipment, and user can look back conversation content by playing this section of calling record at any time.
In the prior art, user if desired determines the conversation content of calling record, must play calling record, yet the broadcasting of calling record not only consumes user's time, and the system resource of mobile communication equipment will be taken, consume a large amount of electric energy, cause the wasting of resources.
Summary of the invention
The embodiment of the present invention provides a kind of method and apparatus of preserving keyword in the message registration of mobile communication equipment, make user to determine conversation content by keyword, and do not need the mode by playback, the taking and the consumption of electric energy of system resource that can effectively avoid mobile communication equipment, can economize on resources effectively.
First aspect present invention provides a kind of method of preserving keyword in the message registration of mobile communication equipment, comprising:
The calling record that described message registration is corresponding is processed, obtained the set of words that described calling record is corresponding, described word set is combined into the set of the word occurring in described calling record;
Calculate the weight allocation value of one or more types that word in described set of words is corresponding;
According to the weight allocation value of described one or more types that in described set of words, word is corresponding, calculate the weighted value of institute's predicate;
Keyword is saved in described message registration, and described keyword is the word that in described set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, described N is positive integer.
In the possible implementation of first aspect the first, in described set of words, comprise the one-to-one relationship between word and the word time point in described calling record.
In conjunction with the possible implementation of the first of first aspect, in the possible implementation of the second, the weight allocation value of one or more types that word in the described set of words of described calculating is corresponding comprises:
Calculate word in the described set of words corresponding weight allocation value of at least two types on corresponding time point in described calling record;
The weighted value that the described weight allocation value according to described one or more types that in described set of words, word is corresponding is calculated institute's predicate comprises:
On each corresponding time point using same word in described set of words in described calling record, the set of the corresponding weight allocation value of described at least two types is as subset corresponding to institute's predicate;
Calculate described in the subset that institute's predicate is corresponding product between the weight allocation value of described at least two types corresponding on word each corresponding time point in described calling record, described product and be the weighted value of institute's predicate.
In conjunction with the possible implementation of first aspect the first, in the third possible implementation, the weight allocation value of one or more types that word in the described set of words of described calculating is corresponding comprises:
Calculate the weight allocation value of same type corresponding on the time point of the word correspondence in described calling record in described set of words;
The weighted value that the described weight allocation value according to described one or more types that in described set of words, word is corresponding is calculated institute's predicate comprises:
On each corresponding time point using same word in described set of words in described calling record between the weight allocation value of corresponding described same type and as institute's predicate the weighted value corresponding to the weight allocation value of described same type;
If the type of described weight allocation value is a kind of, determine that institute's predicate is the weighted value of institute's predicate corresponding to the weighted value of the weight allocation value of described same type;
If the type of described weight allocation value is multiple, determine that institute's predicate is the weighted value of institute's predicate corresponding to the product between the weighted value of the weight allocation value of every type in described polytype weight allocation value.
In conjunction with the possible implementation of first aspect the second or the third possible implementation, in the 4th kind of possible implementation, the type of described weight allocation value comprises: one or more in air time weight allocation value, mood tone weight allocation value, part of speech weight allocation value;
The weight allocation value of one or more types that word in the described set of words of described calculating is corresponding comprises:
Calculate word in described set of words corresponding air time weight allocation value on corresponding time point in calling record;
And/or, calculate word in described set of words corresponding mood tone weight allocation value on corresponding time point in calling record;
And/or, calculate word in the described set of words part of speech weight allocation value on corresponding time point in calling record.
In conjunction with the 4th kind of possible implementation of first aspect, in the 5th kind of possible implementation, if comprise described air time weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding air time weight allocation value comprise:
The time point that calculates the word correspondence in described calling record in described set of words accounts for the percentage of the duration of described calling record;
Search the percentage of time weight allocation table setting in advance, determine the air time weight allocation value corresponding with described percentage, in described percentage weight allocation table, comprise the corresponding relation between percentage range and air time weight allocation value.
In conjunction with the 4th kind of possible implementation of first aspect, in the 6th kind of possible implementation, if comprise described air time weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding air time weight allocation value comprise:
Search the time weighting allocation table setting in advance, determine and institute predicate corresponding air time weight allocation value on corresponding time point in described calling record, described time weighting allocation table comprises the corresponding relation between time range and air time weight allocation value.
In conjunction with the 4th kind of possible implementation of first aspect, in the 7th kind of possible implementation, if comprise described mood tone weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding mood tone weight allocation value comprise:
Described calling record is carried out to audio analysis processing, obtain the audible spectrum of described calling record;
Utilize the corresponding time point in described calling record of word in described set of words to determine institute's predicate corresponding type of emotion in described audible spectrum;
Search the mood tone weight allocation table setting in advance, determine the mood tone weight allocation value corresponding with the type of emotion of word in described set of words, in described mood tone weight allocation table, comprise the corresponding relation between type of emotion and mood tone weight allocation value.
In conjunction with the 4th kind of possible implementation of first aspect, in the 8th kind of possible implementation, if comprise described part of speech weight allocation value in described at least one or polytype weight allocation value, the part of speech weight allocation value on corresponding time point in calling record of the word in the described set of words of described calculating comprises:
Search the part of speech weight allocation table setting in advance, determine on the time point of the word correspondence in described calling record in described set of words, the part of speech weight allocation value corresponding to part of speech of institute's predicate, comprises the corresponding relation between part of speech, time range, part of speech weight allocation value in described part of speech weight allocation table.
In the 9th kind of possible implementation of first aspect, described calling record corresponding to described message registration processed, obtain the set of words that described calling record is corresponding and comprise:
Described calling record is carried out to the voice word processing of larding speech with literary allusions, obtain the Word message that described calling record is corresponding;
Described Word message is carried out to word segmentation processing, obtain described set of words.
In conjunction with the 9th kind of possible implementation of first aspect, in the tenth kind of possible implementation, described method also comprises:
Word in described set of words is carried out to de-redundancy processing, obtains the set of words after de-redundancy is optimized,
The weight allocation value of one or more types that word in the described set of words of described calculating is corresponding comprises:
Calculate the weight allocation value of one or more types that word in the set of words after de-redundancy is optimized is corresponding.
Second aspect present invention provides a kind of equipment of preserving keyword in the message registration of mobile communication equipment, comprising:
Processing module, for calling record corresponding to described message registration processed, obtains the set of words that described calling record is corresponding, and described word set is combined into the set of the word occurring in described calling record;
Computing module, after obtaining described calling record set of words in described processing module, calculates the weight allocation value of one or more types that word in described set of words is corresponding;
Weight computation module, after obtaining the weight allocation value of one or more types that the word of described set of words is corresponding at described computing module, according to the weight allocation value of described one or more types that in described set of words, word is corresponding, calculate the weighted value of institute's predicate;
Preserve module, for after described weight computation module obtains the weighted value of institute's predicate, keyword is saved in described message registration, described keyword is the word that in described set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, described N is positive integer.
In the possible implementation of second aspect the first, in the described set of words that described processing module obtains, comprise the one-to-one relationship between word and the time point of word in described calling record.
In conjunction with the possible implementation of second aspect the first, in the possible implementation of the second, described computing module is specifically for after obtaining described calling record set of words in described processing module, calculates word in the described set of words corresponding weight allocation value of at least two types on corresponding time point in described calling record;
Described weight computation module specifically for:
After the weight allocation value of at least two types described in described computing module obtains, on each the corresponding time point using same word in described set of words in described calling record, the set of the corresponding weight allocation value of described at least two types is as subset corresponding to institute's predicate;
Calculate described in the subset that institute's predicate is corresponding product between the weight allocation value of described at least two types corresponding on word each corresponding time point in described calling record, described product and be the weighted value of institute's predicate.
In conjunction with the possible implementation of second aspect the first, in the third possible implementation, described computing module, specifically for after obtaining described calling record set of words in described processing module, calculates the weight allocation value of same type corresponding on the time point of the word correspondence in described calling record in described set of words;
Described weight computation module specifically for:
On each corresponding time point using same word in described set of words in described calling record between the weight allocation value of corresponding described same type and as institute's predicate the weighted value corresponding to the weight allocation value of described same type;
If the type of described weight allocation value is a kind of, determine that institute's predicate is the weighted value of institute's predicate corresponding to the weighted value of the weight allocation value of described same type;
If the type of described weight allocation value is multiple, determine that institute's predicate is the weighted value of institute's predicate corresponding to the product between the weighted value of the weight allocation value of every type in described polytype weight allocation value.
In conjunction with the possible implementation of second aspect the second or the third possible implementation, in the 4th kind of possible implementation, the type of described weight allocation value comprises: one or more in air time weight allocation value, mood tone weight allocation value, part of speech weight allocation value;
Described computing module is specifically for after obtaining described calling record set of words in described processing module, calculates word in described set of words corresponding air time weight allocation value on corresponding time point in calling record; And/or, calculate word in described set of words corresponding mood tone weight allocation value on corresponding time point in calling record; And/or, calculate word in the described set of words part of speech weight allocation value on corresponding time point in calling record.
In conjunction with the 4th kind of possible implementation of second aspect, in the 5th kind of possible implementation, if comprise described air time weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding air time weight allocation value aspect, described computing module specifically for:
The time point that calculates the word correspondence in described calling record in described set of words accounts for the percentage of the duration of described calling record;
Search the percentage of time weight allocation table setting in advance, determine the air time weight allocation value corresponding with described percentage, in described percentage weight allocation table, comprise the corresponding relation between percentage range and air time weight allocation value.
In conjunction with the 4th kind of possible implementation of second aspect, in the 6th kind of possible implementation, if comprise described air time weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding air time weight allocation value aspect, described computing module specifically for:
Search the time weighting allocation table setting in advance, determine and institute predicate corresponding air time weight allocation value on corresponding time point in described calling record, described time weighting allocation table comprises the corresponding relation between time range and air time weight allocation value.
In conjunction with the 4th kind of possible implementation of second aspect, in the 7th kind of possible implementation, if comprise described mood tone weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding mood tone weight allocation value aspect, described computing module specifically for:
Described calling record is carried out to audio analysis processing, obtain the audible spectrum of described calling record;
Utilize the corresponding time point in described calling record of word in described set of words to determine institute's predicate corresponding type of emotion in described audible spectrum;
Search the mood tone weight allocation table setting in advance, determine the mood tone weight allocation value corresponding with the type of emotion of word in described set of words, in described mood tone weight allocation table, comprise the corresponding relation between type of emotion and mood tone weight allocation value.
In conjunction with the 4th kind of possible implementation of second aspect, in the 8th kind of possible implementation, if comprise described part of speech weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record the part of speech weight allocation value on corresponding time point aspect, described computing module specifically for:
Search the part of speech weight allocation table setting in advance, determine on the time point of the word correspondence in described calling record in described set of words, the part of speech weight allocation value corresponding to part of speech of institute's predicate, comprises the corresponding relation between part of speech, time range, part of speech weight allocation value in described part of speech weight allocation table.
In conjunction with the possible implementation of first aspect the first or the possible implementation of the second or the third possible implementation or the 4th kind of possible implementation or the 5th kind of possible implementation or the 6th kind of possible implementation or the 7th kind of possible implementation or the 8th kind of possible implementation, in the 9th kind of possible implementation, described processing module comprises:
The voice word processing module of larding speech with literary allusions, for described calling record being carried out to the voice word processing of larding speech with literary allusions, obtains the Word message that described calling record is corresponding;
Word segmentation processing module, after obtaining described Word message, carries out word segmentation processing to described Word message for the word processing module of larding speech with literary allusions at described voice, obtains described set of words.
In conjunction with the 9th kind of possible implementation of second aspect, in the tenth kind of possible implementation, described equipment also comprises:
De-redundancy processing module, for obtaining, after described set of words, the word in described set of words being carried out to de-redundancy processing in described word segmentation processing module, obtains the set of words after de-redundancy is optimized,
Described computing module is for the weight allocation value of one or more types corresponding to the word of the set of words after calculating de-redundancy and optimizing.
As can be seen from the above technical solutions, the embodiment of the present invention has the following advantages:
The calling record that message registration is corresponding is processed, obtained the set of words that this calling record is corresponding, this word set is combined into the set of the word occurring in this calling record; And calculate the weight allocation value of corresponding one or more types of word in this set of words, according to the weight allocation value of one or more types corresponding to the word in this set of words, calculate the weighted value of this word, weighted value in set of words is come to the word of front N or weighted value to be more than or equal to the preset word setting in advance and to be saved in message registration as keyword, user is not needed by listening the mode of calling record to determine conversation content, the resource occupation that can effectively avoid calling record to play bringing and the problem of electrical source consumption, can effectively economize on resources.
Accompanying drawing explanation
Fig. 1 is a schematic diagram preserving the method for keyword in the embodiment of the present invention in mobile communication equipment calling record;
Fig. 2 is another schematic diagram of preserving the method for keyword in the embodiment of the present invention in the calling record of mobile communication equipment;
Fig. 3 is another schematic diagram of preserving the method for keyword in the embodiment of the present invention in the calling record of mobile communication equipment;
Fig. 3 a is the effect schematic diagram of preserving keyword in the embodiment of the present invention in the calling record of mobile communication equipment;
Fig. 4 is a schematic diagram of structure of preserving the equipment of keyword in the embodiment of the present invention in the calling record of mobile communication equipment;
Fig. 5 is another schematic diagram of structure of preserving the equipment of keyword in the embodiment of the present invention in the calling record of mobile communication equipment;
The schematic diagram of one, the structure of the mobile communication equipment that Fig. 6 provides for the embodiment of the present invention;
Fig. 7 is the configuration diagram of the operating system in the mobile communication equipment that provides of the embodiment of the present invention;
Fig. 8 is another schematic diagram of structure of the mobile communication equipment that provides of the embodiment of the present invention.
Embodiment
The embodiment of the present invention provides a kind of method and apparatus of preserving keyword in the message registration of mobile communication equipment, for calling record corresponding to user's message registration processed, obtain the keyword in this calling record, and keyword is kept in this message registration, make user to determine conversation content by keyword, and do not need the mode by playback, the taking and the consumption of electric energy of system resource that can effectively avoid mobile communication equipment, can economize on resources effectively.
Referring to Fig. 1, is a kind of embodiment that preserves the method for keyword in the message registration of mobile communication equipment in the embodiment of the present invention, comprising:
101, calling record corresponding to message registration processed, obtained the set of words that calling record is corresponding, word set is combined into the set of the word occurring in calling record;
In embodiments of the present invention, when user receives calls, can open the function of recording, therefore, mobile communication equipment by recording user and and the object of its call between conversation content, after user's communication finishes, generate message registration and calling record corresponding to this message registration.
In embodiments of the present invention, equipment can be processed calling record corresponding to this message registration, obtain the set of words that this calling record is corresponding, this word set is combined into the set of the word occurring in this calling record, this equipment can be mobile communication equipment, can be also high in the clouds equipment, wherein, if equipment is mobile communication equipment, mobile communication equipment can be mobile phone, PAD etc.If equipment is high in the clouds equipment, mobile communication equipment, after getting the calling record that message registration is corresponding, sends to high in the clouds equipment by message registration and the calling record with corresponding relation, makes high in the clouds equipment can perform step 101.
Wherein, in the set of words that device processes obtains, comprise the one-to-one relationship between word and the word time point in calling record, be each word in set of words to the time point should word occurring in calling record, and a word can comprise at least one one-to-one relationship in set of words, for example: word " film " comprises 3 one-to-one relationships in set of words, be respectively: word " film " and the time point corresponding relation of 1 minute and 20 seconds, word " film " and the time point corresponding relation of 2 minutes and 31 seconds, corresponding relation between word " film " and time point 2 minutes and 56 seconds.
The weight allocation value of one or more types that 102, the word in calculating set of words is corresponding;
In embodiments of the present invention, equipment is after obtaining the set of words of calling record, the weight allocation value of one or more types that word in the set of words calculating is corresponding, the dimensions such as the time that specifically can occur based on word, mood, part of speech determine that this word is in the weight allocation value of one or more types.
103, according to the weight allocation value of one or more types corresponding to word in set of words, calculate the weighted value of word;
In embodiments of the present invention, after the weight allocation value of one or more types that the word of equipment in calculating set of words is corresponding, the weighted value of this word will be calculated according to the weight allocation value of these one or more types corresponding to word in set of words, equipment can utilize which to calculate the weighted value of all words in set of words, makes to utilize the weighted value of word in set of words to determine keyword.
104, keyword is saved in message registration, keyword is the word that in set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, N is positive integer.
In embodiments of the present invention, equipment will utilize the weighted value of word in set of words to determine keyword, and keyword is saved in message registration, wherein, keyword is the word that in set of words, weighted value comes front N, or is more than or equal to the word of the threshold value setting in advance for weighted value, wherein, N is positive integer.Wherein, if equipment is mobile communication equipment, mobile communication equipment can directly be saved in definite keyword in message registration, if equipment is high in the clouds equipment, keyword is saved in message registration and can be comprised in step 104: high in the clouds equipment sends to mobile communication equipment by definite keyword, mobile communication equipment can be saved in keyword in message registration, or, if equipment is high in the clouds equipment, keyword is saved in message registration and can be comprised in step 104: high in the clouds equipment is saved in definite keyword in message registration, this message registration is sent to mobile communication equipment, make mobile communication equipment can utilize this message registration to replace the message registration of existing correspondence, make the keyword that comprises this message registration in the message registration after replacing.
In embodiments of the present invention, equipment is processed calling record corresponding to message registration, obtains the set of words that this calling record is corresponding, and this word set is combined into the set of the word occurring in this calling record; And calculate the weight allocation value of corresponding one or more types of word in this set of words, according to the weight allocation value of one or more types corresponding to the word in this set of words, calculate the weighted value of this word, weighted value in set of words is come to the word of front N or weighted value to be more than or equal to the preset word setting in advance and to be saved in message registration as keyword, user is not needed by listening the mode of calling record to determine conversation content, the resource occupation that can effectively avoid calling record to play bringing and the problem of electrical source consumption, can effectively economize on resources.
In embodiments of the present invention, equipment can utilize the weight allocation value of one or more types corresponding to the set of words that obtains to determine keyword, technical scheme for a better understanding of the present invention, to introduce the weight allocation value of a type that the word of equipment based in set of words is corresponding and determine the method for keyword below, refer to Fig. 2, for a kind of embodiment that preserves the method for keyword in the message registration of communication equipment in the embodiment of the present invention, comprising:
201, calling record corresponding to message registration processed, obtained the set of words that calling record is corresponding, word set is combined into the set of the word occurring in calling record, comprises the one-to-one relationship between word and the word time point in calling record in set of words;
In embodiments of the present invention, when user receives calls, can open the function of recording, therefore, mobile communication equipment by recording user and and the object of its call between conversation content, after user's communication finishes, generate message registration and calling record corresponding to this message registration.
In embodiments of the present invention, equipment can be processed calling record corresponding to this message registration, obtain the set of words that this calling record is corresponding, this word set is combined into the set of the word occurring in this calling record, and in set of words, comprise the one-to-one relationship between word and the word time point in calling record, be each word in set of words to the time point should word occurring in calling record, and a word can comprise at least one one-to-one relationship in set of words, for example: word " film " comprises 3 one-to-one relationships in set of words, be respectively: word " film " and the time point corresponding relation of 1 minute and 20 seconds, word " film " and the time point corresponding relation of 2 minutes and 31 seconds, corresponding relation between word " film " and time point 2 minutes and 56 seconds.
In embodiments of the present invention, the executive agent of carrying out the technical scheme in the present invention is equipment, and this equipment can be mobile communication equipment, can be also high in the clouds equipment, and wherein, if equipment is mobile communication equipment, mobile communication equipment can be mobile phone, PAD etc.If equipment is high in the clouds equipment, mobile communication equipment, after getting the calling record that message registration is corresponding, sends to high in the clouds equipment by message registration and the calling record with corresponding relation, makes high in the clouds equipment can perform step 101.
It should be noted that, in embodiments of the present invention, in calling record, can comprise a lot of redundancy words, for example: hello, goodbye, good-by, and some redundancy words of personal habits, in order better to determine keyword, equipment also can the weight allocation value of a type that word is corresponding in calculating set of words before, remove the redundancy word in this set of words, it should be noted that, in equipment, comprised a redundancy word database, equipment can be determined the redundancy word in set of words according to this redundancy word database, and from set of words, delete definite redundancy word, obtain removing redundancy word set of words afterwards, be the set of words after optimization, make weight allocation value corresponding to word in the set of words of equipment after can calculation optimization, to realize determining of keyword.
202, calculate the weight allocation value of same type corresponding on the time point of the word correspondence in calling record in set of words;
In embodiments of the present invention, equipment can calculate the weight allocation value of same type corresponding on the time point of the word correspondence in calling record in set of words, wherein the type of this weight allocation value comprises: air time weight allocation value, mood tone weight allocation value, part of speech weight allocation value, wherein, air time weight allocation value refers to that the time point of this word in calling record is corresponding to the weight of the duration of this calling record, mood tone weight allocation value refers to the weight of the mood that the frequency of institute's predicate in described calling record is corresponding, part of speech weight allocation value refers to the weight of the part of speech of word, wherein, part of speech comprises noun, verb, adjective, adverbial word etc.
In embodiments of the present invention, the mode of the air time weight allocation value on the time point of the word correspondence in calling record in equipment calculating set of words is: the time point that calculates the word correspondence in calling record in set of words accounts for the percentage of the duration of calling record; Search the percentage of time weight allocation table setting in advance, determine the air time weight allocation value corresponding with the percentage obtaining of this calculating, wherein, in percentage weight allocation table, comprise the corresponding relation between percentage range and air time weight allocation value.For example: if the percentage weight allocation table setting in advance is as shown in table 1:
The percentage of total duration of time point and calling record Air time weight allocation value
0-20% 2
21%-90% 1.5
91%-100% 1
Table 1
Long 100 minutes of calling record, " repair " time point of corresponding calling record of word in set of words is 10 minutes, " repair " percentage of total duration of the time point that occurs and calling record of word is 10%, and 1 of question blank can determine that the air time weight allocation value that word " repairs " is 2.
In embodiments of the present invention, on the time point of the word correspondence in calling record in calculating set of words, corresponding air time weight allocation value also has another mode to be: search the time weighting allocation table setting in advance, determine with word air time weight allocation value corresponding on the corresponding time point in calling record, wherein, time weighting allocation table comprises the corresponding relation between time range and air time weight allocation value.For example: if time weighting allocation table is as shown in table 2:
Word appears at the time point in calling record Air time weight allocation value
Front half a minute of calling record 2
Calling record finishes first 1 minute to finishing first 30 seconds 1.5
Other 1
Table 2
If word " repairs " and appears in front half a minute of calling record, question blank 2 can determine that the air time weight allocation value of this word is 2.
In embodiments of the present invention, on the time point of the word correspondence in calling record in calculating set of words, corresponding mood tone weight allocation value comprises: calling record is carried out to audio analysis processing, obtain the audible spectrum of this calling record, utilize the corresponding time point in calling record of word in set of words to determine this word corresponding type of emotion in audible spectrum, and search the mood tone weight allocation table setting in advance, determine the mood tone weight allocation value corresponding with the type of emotion of this word in set of words, wherein, in this mood tone weight allocation table, comprise the corresponding relation between type of emotion and mood tone weight allocation value, wherein, utilize word corresponding time point in calling record in set of words to determine that this word corresponding type of emotion in audible spectrum is specifically as follows: equipment utilization word corresponding time point in calling record is determined frequency and the attribute of word on this corresponding time point in audible spectrum, this frequency is the frequency of word, wherein, attribute refers to this word that man or female send, utilize frequency and the attribute equipment of this word to determine the mood that this word is corresponding by inquiry fundamental frequency, wherein, fundamental frequency refers to speech frequency under normal circumstances.For example: if fundamental tone frequency is as shown in table 3:
Table 3
And mood tone weight allocation table is as shown in table 4:
Type of emotion Mood tone weight allocation value
In surprise/happiness 3
Indignation/sadness 2
Other 1
Table 4
If word " film " appears at the 22nd second of calling record, search the audible spectrum of this calling record and determine that this word " film " belongs to female voice, and frequency is 400, therefore, by searching upper table, can determine that the type of emotion of this word " film " is for glad, its mood tone weight allocation value is 3.
It should be noted that, in embodiments of the present invention, calling record is carried out to spectrum analysis, determine that the mood of the word in this calling record and the mode of attribute belong to content of the prior art, are briefly described in the present invention, and are not described in detail.
In embodiments of the present invention, part of speech weight allocation value on the time point of the word correspondence in calling record in equipment calculating set of words comprises: search the part of speech weight allocation table setting in advance, determine on the time point of the word correspondence in calling record in set of words, the part of speech weight allocation value corresponding to part of speech of word, wherein, the corresponding relation that comprises part of speech, time range, part of speech weight allocation value in part of speech weight allocation table.For the ease of understanding, part of speech weight allocation table can be with reference to following table 5A:
Figure BDA0000388078730000141
Table 5A
In table 5A, calling record is divided into three time ranges, be respectively " front half a minute of calling record ", " calling record latter one minute " and " other ".
For example: if equipment need to be determined the part of speech weight allocation value of word " film ", the part of speech of determining this word " film " is noun, and this word " film " corresponding time point in calling record belongs to front half a minute of calling record, and searching part of speech weight allocation value corresponding to above-mentioned part of speech weight allocation table part of speech known and word " film " is 1.
Should be understood that, if each word corresponding time point in calling record of understanding in set of words is " in the duration of call ", part of speech weight allocation table can be with reference to following table 5B, and this following table 5B can be reduced to following table 5C(and be equivalent to time range row and be omitted).
Accordingly, in embodiments of the present invention, part of speech weight allocation value on the time point of the word correspondence in calling record in equipment calculating set of words comprises: search the part of speech weight allocation table setting in advance, determine on the time point of the word correspondence in calling record in set of words, the part of speech weight allocation value corresponding to part of speech of word, wherein, the corresponding relation that comprises part of speech, time range (optionally), part of speech weight allocation value in part of speech weight allocation table.For the ease of understanding, part of speech weight allocation table can be with reference to following table 5B and 5C:
Part of speech Time range Part of speech weight allocation value
Noun In the duration of call 1
Verb In the duration of call 0.5
Adjective and adverbial word In the duration of call 0.3
Other In the duration of call 0
Table 5B
Part of speech Part of speech weight allocation value
Noun
1
Verb 0.5
Adjective and adverbial word 0.3
Other 0
Table 5C
For example: if equipment need to be determined the part of speech weight allocation value of word " film ", determine that the part of speech of this word " film " is noun, searching part of speech weight allocation value corresponding to above-mentioned part of speech weight allocation table part of speech known and word " film " is 1.
It should be noted that, during the weight allocation value of a type of calculating of equipment, the type that this weight allocation value is concrete can, according to actual conditions setting or selection, not limit herein.
203, using same word in set of words on each the corresponding time point in calling record between the weight allocation value of corresponding same type and as word the weighted value corresponding to the weight allocation value of this same type, continue execution step 204, or continue execution step 205;
In embodiments of the present invention, in set of words, comprise the one-to-one relationship between word and the word time point in calling record, in order to calculate the weighted value that word is corresponding, equipment between the weight allocation value of the corresponding same type on each the corresponding time point in call record of same word in set of words and as word the weighted value corresponding to the weight allocation value of this same type, for example: if word " film " is respectively 4 air time weight allocation values corresponding to time point: 1, 2, 2, 1, word " film " equals 1+2+2+1 corresponding to the weighted value of air time weight allocation value, 6.
If the type of 204 weight allocation values is a kind of, determine the weighted value that word is word corresponding to the weighted value of the weight allocation value of same type, continue execution step 206;
In embodiments of the present invention, if the type of the weight allocation value of word is a kind of, equipment division determines that word is the weighted value of this word corresponding to the weighted value of the weight allocation value of same type, for example: if word " film " is 6 corresponding to the weighted value of air time weight allocation value, and this word only has this class weight allocation value, and the weighted value of word " film " is 6.
If the type of 205 weight allocation values is multiple, determine that in polytype weight allocation value the weighted value that word is word corresponding to the product between the weighted value of the weight allocation value of every type continues execution step 206;
In embodiments of the present invention, if the type of weight allocation value is multiple, determine in polytype weight allocation value, the weighted value that word is word corresponding to the product between the weighted value of the weight allocation value of every type, for example: if calculate in step 203, the weighted value of the air time weight allocation value of word " film " is 6, the weighted value of mood tone weight allocation value is 7, the weight allocation value of part of speech weight allocation value is 4, the weighted value of word " film " is 6*7*4, is 168.
206, keyword is saved in message registration, keyword is the word that in set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, N is positive integer.
In embodiments of the present invention, after the weighted value of equipment word in obtaining set of words, the word of threshold value that weighted value is come to the word of front N or weighted value is more than or equal to setting is as the keyword of this word, and keyword is saved in message registration, wherein, N is positive integer.Wherein, if equipment is mobile communication equipment, mobile communication equipment can directly be saved in definite keyword in message registration, if equipment is high in the clouds equipment, keyword is saved in message registration and can be comprised in step 206: high in the clouds equipment sends to mobile communication equipment by definite keyword, mobile communication equipment can be saved in keyword in message registration, or, if equipment is high in the clouds equipment, high in the clouds equipment is after execution step 206, the message registration that comprises keyword is sent to mobile communication equipment, make mobile communication equipment can utilize this message registration that comprises keyword to replace the message registration of existing correspondence, effectively realize and in the message registration of mobile communication equipment, preserve the object of keyword.
In embodiments of the present invention, equipment is processed calling record corresponding to message registration, obtain the set of words that calling record is corresponding, in this set of words, comprise the one-to-one relationship between word and the word time point in calling record, and equipment will calculate word in the set of words weight allocation value of corresponding same type on each corresponding time point in calling record, on each corresponding time point using same word in set of words in calling record between the weight allocation value of corresponding same type and as word the weighted value corresponding to the weight allocation value of this same type, if and the type of weight allocation value is a kind of, determine the weighted value that this word is this word corresponding to the weighted value of the weight allocation value of this same type, if or the type of weight allocation value is multiple, determine in this polytype weight allocation value, the weighted value that word is word corresponding to the product between the weight allocation value of every type, the definite keyword of the weighted value that utilizes word is saved in message registration, user is not needed by listening the mode of calling record to determine conversation content, the resource occupation that can effectively avoid calling record to play bringing and the problem of electrical source consumption, can effectively economize on resources.
The equipment of introducing is determined to the mode of keyword based on the weight allocation value of at least two types corresponding to word in set of words below, refer to Fig. 3, a kind of embodiment that preserves the method for keyword in the message registration of mobile communication equipment in the invention process, comprising:
301, calling record corresponding to message registration processed, obtained the set of words that calling record is corresponding, this word set is combined into the set of the word occurring in calling record, comprises the one-to-one relationship between word and the word time point in calling record in set of words;
In embodiments of the present invention, user, after using mobile communication equipment connection phone, can open sound-recording function, recording call content, and after end of conversation, generate message registration and calling record corresponding to this message registration.
In embodiments of the present invention, mobile communication equipment is after generating the calling record that message registration and this message registration are corresponding, to calling record corresponding to this message registration be processed by equipment, obtain the set of words that this calling record is corresponding, and this word set is combined into the set of words occurring in calling record, and in set of words, comprise the one-to-one relationship between word and the word time point in calling record, wherein, this equipment can be mobile communication equipment, also can be high in the clouds equipment, if this equipment is high in the clouds equipment, mobile communication equipment is after generating message registration and calling record, message registration and the calling record with corresponding relation are uploaded to high in the clouds equipment, by high in the clouds equipment, obtain the set of words that this calling record is corresponding, and mobile communication equipment is before uploading calling record, also can carry out denoising to this calling record.If this equipment is mobile communication equipment, mobile communication equipment, before this calling record being processed to set of words corresponding to acquisition, also can carry out denoising to this recording.
In embodiments of the present invention, equipment is processed to calling record the method that obtains the set of words that this calling record is corresponding and is comprised: this calling record is carried out to the voice word processing of larding speech with literary allusions, obtain the Word message that calling record is corresponding, and this Word message is carried out to word segmentation processing, obtain set of words, and in this set of words, comprise the corresponding relation one to one between word and the word time point in calling record, for example: the corresponding relation of the word in set of words " film " has: word " film " and the time point corresponding relation of 1 minute and 20 seconds, word " film " and the time point corresponding relation of 2 minutes and 31 seconds, corresponding relation between word " film " and time point 2 minutes and 56 seconds.Wherein, the lard speech with literary allusions processing mode of word processing and word segmentation processing of voice is content of the prior art, does not repeat herein.
It should be noted that, in embodiments of the present invention, in calling record, can comprise a lot of redundancy words, for example: hello, goodbye, good-by, and some redundancy words of personal habits, in order better to determine keyword, equipment also can the weight allocation value of at least two types that word is corresponding in calculating set of words before, remove the redundancy word in this set of words, it should be noted that, in equipment, comprised a redundancy word database, equipment can be determined the redundancy word in set of words according to this redundancy word database, and from set of words, delete definite redundancy word, obtain removing redundancy word set of words afterwards, be the set of words after optimization, make weight allocation value corresponding to word in the set of words of equipment after can calculation optimization, to realize determining of keyword.
302, the corresponding weight allocation value of at least two types on the time point of the word correspondence in calling record in calculating set of words;
In embodiments of the present invention, equipment is after getting the set of words of calling record, the corresponding weight allocation value of at least two types on the time point of the correspondence in calling record of the word in the set of words that computing is obtained, wherein, the type of weight allocation value comprises: air time weight allocation value, mood tone weight allocation value, part of speech weight allocation value, wherein, air time weight allocation value refers to that the time point of this word correspondence in calling record is corresponding to the weight of the duration of this calling record, mood tone weight allocation value refers to the weight of the mood that the frequency of institute's predicate in described calling record is corresponding, part of speech weight allocation value refers to the weight of the part of speech of word, wherein, part of speech comprises noun, verb, adjective, adverbial word etc.
In embodiments of the present invention, the mode of the air time weight allocation value on the time point of the word correspondence in calling record in equipment calculating set of words is: the time point that calculates the word correspondence in calling record in set of words accounts for the percentage of the duration of calling record; Search the percentage of time weight allocation table setting in advance, determine the air time weight allocation value corresponding with the percentage obtaining of this calculating, wherein, in percentage weight allocation table, comprise the corresponding relation between percentage range and air time weight allocation value.For example: if the percentage weight allocation table setting in advance is as shown in table 1, long 100 minutes of calling record, the time point of the calling record that word in set of words " five minutes " is corresponding is 30 minutes, the percentage of the time point that word " five minutes " occurs and total duration of calling record is 30%, can determine that the air time weight allocation value of word " five minutes " is 1.5.
In embodiments of the present invention, on the time point of the word correspondence in calling record in calculating set of words, corresponding air time weight allocation value also has another mode to be: search the time weighting allocation table setting in advance, determine the air time weight allocation value corresponding with word corresponding time point in calling record, wherein, time weighting allocation table comprises the corresponding relation between time range and air time weight allocation value.For example: if time weighting allocation table is as shown in table 2: if word " five minutes " appears at calling record and finishes first 1 minute to finishing in first 30 seconds, the air time weight allocation value of this word is 1.5.
In embodiments of the present invention, on the time point of the word correspondence in calling record in calculating set of words, corresponding mood tone weight allocation value comprises: calling record is carried out to audio analysis processing, obtain the audible spectrum of this calling record, utilize the corresponding time point in calling record of word in set of words to determine this word corresponding type of emotion in audible spectrum, and search the mood tone weight allocation table setting in advance, determine the mood tone weight allocation value corresponding with the type of emotion of this word in set of words, wherein, in this mood tone weight allocation table, comprise the corresponding relation between type of emotion and mood tone weight allocation value, wherein, utilize word corresponding time point in calling record in set of words to determine that this word corresponding type of emotion in audible spectrum is specifically as follows: equipment utilization word corresponding time point in calling record is determined the word frequency on this time point and attribute in audible spectrum, this frequency is the frequency of word, attribute refers to that word is that man or female send, equipment can be determined the mood that this frequency is corresponding by inquiry fundamental frequency, wherein, fundamental frequency refers to speech frequency under normal circumstances.For example: fundamental tone is frequently as shown in table 3, and mood tone weight allocation table is as shown in table 4, if " going window-shopping ", word appears at the 22nd second of calling record, the audible spectrum of searching this calling record is determined that this word " is gone window-shopping " and is belonged to female voice, and frequency is 400, therefore, by searching upper table, can determine that the type of emotion that this word " is gone window-shopping " is happiness, its mood tone weight allocation value is 3.
In embodiments of the present invention, equipment also can calculate word in the set of words part of speech weight allocation value on corresponding time point in calling record, comprise: search the part of speech weight allocation table setting in advance, determine on the time point of the word correspondence in calling record in set of words, the part of speech weight allocation value corresponding to part of speech of word, wherein, in part of speech weight allocation table, comprise the corresponding relation between part of speech, time range, part of speech weight allocation value.For the ease of understanding, part of speech weight allocation table can reference table 5, for example: if equipment need to be determined the part of speech weight allocation value of word " television set ", the part of speech of determining this word " television set " is noun, and this word corresponding time point in calling record belongs to latter one minute of calling record, and searching part of speech weight allocation value corresponding to above-mentioned part of speech weight allocation table part of speech known and word " television set " is 0.8.
It should be noted that, in embodiments of the present invention, the calculating of the air time weight allocation value that word is corresponding, mood tone weight allocation value and part of speech weight allocation value does not have sequencing, can carry out simultaneously.
303, using same word in set of words on each the corresponding time point in calling record the set of the corresponding weight allocation value of at least two types as subset corresponding to word;
In embodiments of the present invention, in set of words, comprised the corresponding relation between word and the time point of this word in calling record, in order to calculate the weighted value of word, word in calculating this set of words in calling record on corresponding time point after the weight allocation value of corresponding at least two types, equipment can be using same word in set of words on each time point in calling record the set of at least two corresponding class weight allocation values as subset corresponding to this word.For example: if what calculate is word in set of words corresponding air time weight allocation value and mood tone weight allocation value on corresponding time point in calling record, the subset that word in set of words " film " is corresponding is as shown in table 6:
Table 6
304, calculate the product between the weight allocation value of at least two types corresponding on time point corresponding to each in calling record of word in the subset that word is corresponding, product and be the weighted value of word;
In embodiments of the present invention, equipment will be determined the product of this word according to the weight allocation value of at least two types corresponding on time point corresponding to each in calling record of this word in subset corresponding to each word, be specifically as follows: calculate the product between the weight allocation value of at least two types corresponding on time point corresponding to each in calling record of word in the subset that word is corresponding, and the product on time point corresponding to each in calling record of word and be the weighted value of this word.
For better understanding, the subset that word in the set of words of take in table 6 " film " is corresponding is example, the weighted value that calculates word " film " can first calculate respectively the product of locating air time weight allocation value and mood tone weight allocation value for the 50th second, the 1st minute and 10 seconds, the 1st minute and 20 seconds, the product calculating on three different time points in calling record is added to the weighted value that the value obtaining is word " film ", the i.e. weighted value=2*2+1.5*3+1.5*2=4+4.5+3=11.5 of word " film ".
305, keyword is saved in message registration, keyword is the word that in set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, described N is positive integer.
In embodiments of the present invention, equipment is by utilizing after subset that word is corresponding obtains the weighted value of this word, by the keyword of determining in calling record, and keyword is saved in message registration, wherein, the weighted value that keyword is in set of words comes the word of front N or the word that weighted value is more than or equal to the threshold value setting in advance, and this N is positive integer, and for example N can be 3.
In embodiments of the present invention, equipment can be saved in the keyword that utilizes weight value to obtain in message registration, make not only to have preserved in this message registration call object, the duration of call, air time outstanding message, can also preserve this keyword, be convenient to the dialog context that user determines this message registration.
It should be noted that, if this equipment is mobile communication equipment, mobile communication equipment can directly be saved in keyword in corresponding message registration, if this equipment is high in the clouds equipment, high in the clouds equipment sends to mobile communication equipment by definite keyword, mobile communication equipment is after receiving the keyword of high in the clouds equipment transmission, this keyword is saved in corresponding message registration, or, if this equipment is high in the clouds equipment, high in the clouds equipment is after execution step 305, also need the message registration that comprises keyword to send to mobile communication equipment, make mobile communication equipment can utilize this message registration that comprises keyword to replace the message registration of existing correspondence, can effectively realize the object of preserving keyword in the message registration of mobile communication equipment.
In embodiments of the present invention, equipment will carry out the voice word processing of larding speech with literary allusions to calling record, obtain the Word message that this calling record is corresponding, and this Word message is carried out to word segmentation processing, obtain set of words, and in this set of words, comprise the corresponding relation between word and the word time point in calling record, and equipment also can calculate word in the set of words corresponding weight allocation value of at least two types on corresponding time point in calling record, and using same word in set of words on each the corresponding time point in calling record the set of the corresponding weight allocation value of at least two types as subset corresponding to this word, calculate the product between the weight allocation value of at least two types corresponding on time point corresponding to each in calling record of word in the subset that word is corresponding, product and be the weighted value of word, the keyword that the weighted value that utilizes word is obtained is saved in message registration, make the user can be by checking that message registration determines conversation content, and do not need to play calling record, therefore, resource occupation and the power consumption that can effectively avoid the broadcasting of calling record to bring, can effectively economize on resources.
Technical scheme in embodiment for a better understanding of the present invention, will introduce a concrete application scenarios below: calling and called all utilize mobile phone to converse, and the content of calling record comprises:
" caller: you are good.
Does is called: you are good, whom you?
Caller: Wo Shi China Telecom broadband, you made a phone call to preengage installation broadband yesterday.
Called:, you fill broadband, have you come now?
Caller: yes, does may I ask your family have people? I will fill broadband to you now.
Called: you etc. upper ten minute, I stay out now, can get home after ten minutes.
Caller: good, I made you more afterwards in ten minutes.
Called: good, thanks.
Caller: unfriendly, goodbye.
Called: goodbye.”
When called connection phone, the called sound-recording function that starts, dialog context between the lower calling and called of record, obtain above-mentioned calling record, mobile phone is after obtaining above-mentioned calling record, can carry out denoising, and can carry out in this locality the extraction of the keyword of calling record, or send to high in the clouds equipment by high in the clouds equipment, to be carried out the keyword extraction of calling record the calling record after denoising.
Under this scene, with mobile phone, being treated to example describes, mobile phone will carry out the processing that speech conversion becomes word to this calling record, obtain the Word message that calling record is corresponding, this Word message is the content of above-mentioned calling record, then, mobile phone carries out de-redundancy processing to Word message, remove redundancy word, redundancy word comprises: you are good, goodbye, Oh, eh, thanks, good, unfriendly etc.And carry out word segmentation processing to removing redundancy word Word message afterwards, obtain set of words, one-to-one relationship between word in this set of words and the time point of this word in calling record, comprise: (dress broadband, the 20th second), (dress broadband, the 24th second), (family, the 40th second), (dress broadband, the 46th second), (ten minutes, the 56th second), (ten minutes, the 1st minute 5 seconds), (ten minutes, the 1st minute 15 seconds) etc., then determine this word in conjunction with in time point place corresponding air time weight allocation value and the mood tone weight allocation value of word in calling record, and the set by the air time weight allocation value on each time point in calling record and mood tone weight allocation value using same word is as subset corresponding to this word, utilize the subset of this word to obtain the weighted value that this word is corresponding, for example, obtaining the word that weighted value comes first three is respectively: dress broadband, ten minutes, family, therefore, can determine that these three words are for the keyword in this calling record, and these three words are saved in the message registration that this calling record is corresponding, make the user can be by checking that message registration determines that in this communication process, the keyword of caller and called talk is: dress broadband, ten minutes, family.For the ease of understanding, refer to Fig. 3 a, in the message registration for mobile communication equipment, preserve the effect schematic diagram of keyword.
Refer to Fig. 4, for preserve the embodiment of structure of the equipment 400 of keyword in the embodiment of the present invention in the message registration of mobile communication equipment, comprising:
Processing module 401, for calling record corresponding to message registration processed, obtains the set of words that calling record is corresponding, and word set is combined into the set of the word occurring in calling record;
Computing module 402, for after processing module 401 obtains calling record set of words, calculates the weight allocation value of one or more types that word in set of words is corresponding;
Weight computation module 403, for obtain the weight allocation value of one or more types that the word of set of words is corresponding at computing module 402 after, calculates the weighted value of word according to the weight allocation value of one or more types corresponding to word in set of words;
Preserve module 404, for after weight computation module 403 obtains the weighted value of word, keyword is saved in message registration, keyword is the word that in set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, N is positive integer.
In embodiments of the present invention, 401 pairs of calling records corresponding to message registration of processing module in equipment 400 are processed, obtain the set of words that calling record is corresponding, word set is combined into the set of the word occurring in calling record, the weight allocation value of one or more types that then word in computing module 402 calculating set of words is corresponding, and by weight computation module 403, according to the weight allocation value of one or more types corresponding to word in set of words, calculated the weighted value of word, finally, by preserving module 404, keyword is saved in message registration, keyword is the word that in set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, N is positive integer.
It should be noted that, equipment can be mobile communication equipment in embodiments of the present invention, also can be high in the clouds equipment, if this equipment is high in the clouds equipment, high in the clouds equipment can receive message registration and the calling record that mobile communication equipment is uploaded, and the preservation module 404 in the equipment of high in the clouds also can send to mobile communication equipment by the calling record that comprises keyword after definite keyword is saved in message registration, make mobile communication equipment can utilize this message registration to replace existing message registration, effectively realize and in the message registration of mobile communication equipment, preserve the object of keyword.
In embodiments of the present invention, equipment is processed calling record corresponding to message registration, obtains the set of words that this calling record is corresponding, and this word set is combined into the set of the word occurring in this calling record; And calculate the weight allocation value of corresponding one or more types of word in this set of words, according to the weight allocation value of one or more types corresponding to the word in this set of words, calculate the weighted value of this word, weighted value in set of words is come to the word of front N or weighted value to be more than or equal to the preset word setting in advance and to be saved in message registration as keyword, user is not needed by listening the mode of calling record to determine conversation content, the resource occupation that can effectively avoid calling record to play bringing and the problem of electrical source consumption, can effectively economize on resources.
Equipment in embodiment, refers to Fig. 5 for a better understanding of the present invention, for preserve the embodiment of structure of the equipment of keyword in the embodiment of the present invention in the message registration of mobile communication equipment, comprising:
Processing module 501, computing module 502, weight computation module 503 and preservation module 504, wherein processing module 501, computing module 502, weight computation module 503 and preserve the function of module 504 can be with reference to processing module 401, computing module 402, the weight computation module 403 described in embodiment as shown in Figure 4, preserve module 404, due to similar to the content of middle description embodiment illustrated in fig. 4, repeat no more herein.
In embodiments of the present invention, in set of words, comprise the one-to-one relationship between word and the word time point in calling record.
In embodiments of the present invention, computing module 502 is specifically for after processing module 501 obtains calling record set of words, calculates word in the set of words corresponding weight allocation value of at least two types on corresponding time point in calling record;
Weight computation module 503 specifically for:
After computing module 502 obtains the weight allocation value of at least two types, on each the corresponding time point using same word in set of words in calling record, the set of the corresponding weight allocation value of at least two types is as subset corresponding to word;
And calculate the product between the weight allocation value of at least two types corresponding on time point corresponding to each in calling record of word in the subset that word is corresponding, product and be the weighted value of word.
Or in another kind of implementation, computing module 502, specifically for after processing module 501 obtains calling record set of words, calculates the weight allocation value of same type corresponding on the time point of the word correspondence in calling record in set of words;
Weight computation module 503 specifically for:
On each corresponding time point using same word in described set of words in described calling record between the weight allocation value of corresponding described same type and as institute's predicate the weighted value corresponding to the weight allocation value of described same type;
If the type of described weight allocation value is a kind of, determine that institute's predicate is the weighted value of institute's predicate corresponding to the weighted value of the weight allocation value of described same type;
If the type of described weight allocation value is multiple, determine that institute's predicate is the weighted value of institute's predicate corresponding to the product between the weighted value of the weight allocation value of every type in described polytype weight allocation value.
In embodiments of the present invention, the type of weight allocation value comprises: one or more in air time weight allocation value, mood tone weight allocation value, part of speech weight allocation value, described computing module 502 is specifically for after obtaining described calling record set of words in described processing module, calculates word in described set of words corresponding air time weight allocation value on corresponding time point in calling record; And/or, calculate word in described set of words corresponding mood tone weight allocation value on corresponding time point in calling record; And/or, calculate word in the described set of words part of speech weight allocation value on corresponding time point in calling record.
Wherein, if comprise described air time weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding air time weight allocation value aspect, described computing module 502 specifically for:
The time point that calculates the word correspondence in described calling record in described set of words accounts for the percentage of the duration of described calling record;
Search the percentage of time weight allocation table setting in advance, determine the air time weight allocation value corresponding with described percentage, in described percentage weight allocation table, comprise the corresponding relation between percentage range and air time weight allocation value.
If comprise described air time weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding air time weight allocation value aspect, described computing module 502 specifically for:
Search the time weighting allocation table setting in advance, determine and institute predicate corresponding air time weight allocation value on corresponding time point in described calling record, described time weighting allocation table comprises the corresponding relation between time range and air time weight allocation value.
If comprise described mood tone weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding mood tone weight allocation value aspect, described computing module 502 specifically for:
Described calling record is carried out to audio analysis processing, obtain the audible spectrum of described calling record;
Utilize the corresponding time point in described calling record of word in described set of words to determine institute's predicate corresponding type of emotion in described audible spectrum;
Search the mood tone weight allocation table setting in advance, determine the mood tone weight allocation value corresponding with the type of emotion of word in described set of words, in described mood tone weight allocation table, comprise the corresponding relation between type of emotion and mood tone weight allocation value.
If comprise described part of speech weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record the part of speech weight allocation value on corresponding time point aspect, described computing module 502 specifically for:
Search the part of speech weight allocation table setting in advance, determine on the time point of the word correspondence in described calling record in described set of words, the part of speech weight allocation value corresponding to part of speech of institute's predicate, comprises the corresponding relation between part of speech, time range, part of speech weight allocation value in described part of speech weight allocation table.
In embodiments of the present invention, described processing module 501 can comprise:
The voice word processing module 5011 of larding speech with literary allusions, for described calling record being carried out to the voice word processing of larding speech with literary allusions, obtains the Word message that described calling record is corresponding;
Word segmentation processing module 5012, after obtaining described Word message, carries out word segmentation processing to described Word message for the word processing module 5011 of larding speech with literary allusions at described voice, obtains described set of words.
Under a kind of implementation,, preferably, the equipment of preserving keyword in the message registration of mobile communication equipment of the embodiment of the present invention can also comprise:
De-redundancy processing module 505, for obtaining, after described set of words, the word in described set of words being carried out to de-redundancy processing in described word segmentation processing module 502, obtains the set of words after de-redundancy is optimized,
Correspondingly, described computing module 502 is for the weight allocation value of one or more types corresponding to the word of the set of words after calculating de-redundancy and optimizing.
It should be noted that, equipment can be mobile communication equipment in embodiments of the present invention, also can be high in the clouds equipment, if this equipment is high in the clouds equipment, high in the clouds equipment can receive message registration and the corresponding calling record that mobile communication equipment is uploaded, and after the preservation module 404 in the equipment of high in the clouds is saved in message registration by keyword, the message registration that high in the clouds equipment includes keyword by this sends to mobile communication equipment, makes mobile communication equipment can utilize the message registration that comprises keyword to replace the message registration of existing correspondence.
In the embodiment of the present invention, in the message registration of mobile communication equipment, preserve voice that the processing module 501 in the equipment 500 of keyword the comprises 5011 pairs of described calling records of word processing module of larding speech with literary allusions and carry out the voice word processing of larding speech with literary allusions, obtain the Word message that described calling record is corresponding, and 5012 pairs of described Word messages of the word segmentation processing module being comprised by processing module 501 carry out word segmentation processing, obtain described set of words, wherein, word set is combined into the set of the word occurring in calling record, and in set of words, comprise the one-to-one relationship between word and the word time point in calling record, and the word in 505 pairs of described set of words of de-redundancy processing module carries out de-redundancy processing, obtain the set of words after de-redundancy is optimized.
In embodiments of the present invention, after the set of words that de-redundancy processing module 505 obtains de-redundancy after optimizing, computing module 502 calculates the weight allocation value of one or more types that word in the set of words after de-redundancy are optimized is corresponding.Be specifically as follows: the corresponding weight allocation value of at least two types on the time point of the word correspondence in calling record in calculating set of words, and by weight computation module 503 using same word in set of words on each the corresponding time point in calling record the set of the corresponding weight allocation value of at least two types as subset corresponding to word, calculate the product between the weight allocation value of at least two types corresponding on time point corresponding to each in calling record of word in the subset that word is corresponding, product and be the weighted value of word;
Or computing module 502 calculates the weight allocation value of one or more types that word in the set of words after de-redundancy are optimized is corresponding.Be specifically as follows: the weight allocation value of calculating same type corresponding on the time point of the word correspondence in calling record in set of words; Then by weight computation module 503 using same word in set of words on each the corresponding time point in calling record between the weight allocation value of corresponding same type and as word the weighted value corresponding to the weight allocation value of this same type, if the type of described weight allocation value is a kind of, determine that institute's predicate is the weighted value of institute's predicate corresponding to the weighted value of the weight allocation value of described same type; If the type of described weight allocation value is multiple, determine that institute's predicate is the weighted value of institute's predicate corresponding to the product between the weighted value of the weight allocation value of every type in described polytype weight allocation value.
In embodiments of the present invention, after weight computation module 503 obtains the weighted value of word in set of words, by preserving module 504, keyword is saved in message registration, keyword is the word that in set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, N is positive integer.
In embodiments of the present invention, the type of weight allocation value comprises air time weight allocation value, mood tone weight allocation value, part of speech weight allocation value, and computing module 502 is specifically for calculating word in described set of words corresponding air time weight allocation value on corresponding time point in calling record; And/or, calculate word in described set of words corresponding mood tone weight allocation value on corresponding time point in calling record; And/or, calculate word in the described set of words part of speech weight allocation value on corresponding time point in calling record.
And if comprising described air time weight allocation value in described at least one or polytype weight allocation value, described computing module 502 is by following manner calculation of talk time weight allocation value: calculate the percentage that word corresponding time point in described calling record in described set of words accounts for the duration of described calling record; Search the percentage of time weight allocation table setting in advance, determine the air time weight allocation value corresponding with described percentage, in described percentage weight allocation table, comprise the corresponding relation between percentage range and air time weight allocation value.
If comprise described air time weight allocation value in described at least one or polytype weight allocation value, described computing module 502 is by following manner calculation of talk time weight allocation value:
Search the time weighting allocation table setting in advance, determine and institute predicate corresponding air time weight allocation value on corresponding time point in described calling record, described time weighting allocation table comprises the corresponding relation between time range and air time weight allocation value.
If comprise described mood tone weight allocation value in described at least one or polytype weight allocation value, described computing module 502 calculates mood tone weight allocation value by following manner: described calling record is carried out to audio analysis processing, obtain the audible spectrum of described calling record; Utilize the corresponding time point in described calling record of word in described set of words to determine institute's predicate corresponding type of emotion in described audible spectrum; Search the mood tone weight allocation table setting in advance, determine the mood tone weight allocation value corresponding with the type of emotion of word in described set of words, in described mood tone weight allocation table, comprise the corresponding relation between type of emotion and mood tone weight allocation value.
If comprise described part of speech weight allocation value in described at least one or polytype weight allocation value, described computing module 502 calculates part of speech weight allocation value by following manner: search the part of speech weight allocation table setting in advance, determine on the time point of the word correspondence in described calling record in described set of words, the part of speech weight allocation value corresponding to part of speech of institute's predicate, comprises the corresponding relation between part of speech, time range (optionally), part of speech weight allocation value in described part of speech weight allocation table.
In embodiments of the present invention, equipment is processed calling record corresponding to message registration, obtain the set of words that calling record is corresponding, in this set of words, comprise the one-to-one relationship between word and the word time point in calling record, and equipment will calculate word in the set of words weight allocation value of corresponding same type on each corresponding time point in calling record, on each corresponding time point using same word in set of words in calling record between the weight allocation value of corresponding same type and as word the weighted value corresponding to the weight allocation value of this same type, if and the type of weight allocation value is a kind of, determine the weighted value that this word is this word corresponding to the weighted value of the weight allocation value of this same type, if or the type of weight allocation value is multiple, determine in this polytype weight allocation value, the weighted value that word is word corresponding to the product between the weight allocation value of every type, the definite keyword of the weighted value that utilizes word is saved in message registration, user is not needed by listening the mode of calling record to determine conversation content, the resource occupation that can effectively avoid calling record to play bringing and the problem of electrical source consumption, can effectively economize on resources.
Equipment in the embodiment of the present invention can be mobile communication equipment, also can be high in the clouds equipment, while detailed description equipment being mobile communication equipment below, the structure of this mobile communication equipment, refer to Fig. 6, this mobile communication equipment 600 comprises: at least one processor 601, at least one network interface 604 or other user interfaces 603, memory 605, at least one communication bus 602.Communication bus 602 is for realizing the connection communication between these assemblies.This mobile communication equipment 600 optionally comprises user interface 603, comprise that display (for example, touch-screen, LCD, CRT, holographic imaging (Holographic) or projection (Projector) etc.), keyboard or pointing device are (for example, mouse, trace ball (trackball), touch-sensitive plate or touch-screen etc.).
In embodiments of the present invention, memory 605 can comprise read-only memory and random access memory, and provides instruction and data to processor 601.A part for memory 605 can also comprise nonvolatile RAM (NVRAM).
In certain embodiments, memory 605 has been stored following element, executable module or data structure, or their subset, or their superset:
Operating system 6051, comprises various system programs, ccf layer as shown in Figure 7 of example, core library layer, drives layer etc., for realizing various basic businesses and processing hardware based task; Processing module 401 shown in Fig. 4, computing module 402, weight computation module 403 and preserve module 404 for example can be corresponding to the core library layer in framework as shown in Figure 7, for example specifically can be corresponding to the kernel service assembly in core library layer or other extension element.Application program module 6052, comprises various application programs, and desktop (launcher) as shown in Figure 7 of example, media player (Media Player), browser (Browser) etc., for realizing various applied business.
In embodiments of the present invention, by calling program or the instruction of memory 605 storages, processor 601 for: the calling record that described message registration is corresponding is processed, obtained the set of words that described calling record is corresponding, described word set is combined into the set of the word occurring in described calling record; Calculate the weight allocation value of one or more types that word in described set of words is corresponding; According to the weight allocation value of described one or more types that in described set of words, word is corresponding, calculate the weighted value of institute's predicate; Keyword is saved in described message registration, and described keyword is the word that in described set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, described N is positive integer.
Alternatively as an embodiment, described processor 601 specifically for: the calling record that described message registration is corresponding is processed, obtain the set of words that described calling record is corresponding, described word set is combined into the set of the word occurring in described calling record, in described set of words, comprise the one-to-one relationship between word and the word time point in calling record, calculate word in the described set of words corresponding weight allocation value of at least two types on corresponding time point in described calling record, on each corresponding time point using same word in described set of words in described calling record, the set of the corresponding weight allocation value of described at least two types is as subset corresponding to institute's predicate, calculate described in the subset that institute's predicate is corresponding product between the weight allocation value of described at least two types corresponding on word each corresponding time point in described calling record, described product and be the weighted value of institute's predicate.Keyword is saved in described message registration, and described keyword is the word that in described set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, described N is positive integer.
Alternatively as an embodiment, described processor 601 is specifically for processing calling record corresponding to described message registration, obtain the set of words that described calling record is corresponding, described word set is combined into the set of the word occurring in described calling record, in described set of words, comprise the one-to-one relationship between word and the word time point in calling record, calculate the weight allocation value of same type corresponding on the time point of the word correspondence in described calling record in described set of words, on each corresponding time point using same word in set of words in calling record between the weight allocation value of corresponding same type and as word the weighted value corresponding to the weight allocation value of this same type, if the type of weight allocation value is a kind of, determine the weighted value that word is word corresponding to the weighted value of the weight allocation value of same type, if the type of weight allocation value is multiple, determine in polytype weight allocation value, the weighted value that word is word corresponding to the product between the weighted value of the weight allocation value of every type, keyword is saved in described message registration, described keyword is the word that in described set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, described N is positive integer.
Alternatively as an embodiment, described processor 601 also for: if described at least one or polytype weight allocation value comprise described air time weight allocation value, calculate the percentage that word corresponding time point in described calling record in described set of words accounts for the duration of described calling record; Search the percentage of time weight allocation table setting in advance, determine the air time weight allocation value corresponding with described percentage, in described percentage weight allocation table, comprise the corresponding relation between percentage range and air time weight allocation value.Or, search the time weighting allocation table setting in advance, determine and institute predicate corresponding air time weight allocation value on corresponding time point in described calling record, described time weighting allocation table comprises the corresponding relation between time range and air time weight allocation value.If comprise described mood tone weight allocation value in described at least one or polytype weight allocation value, described calling record is carried out to audio analysis processing, obtain the audible spectrum of described calling record; Utilize the corresponding time point in described calling record of word in described set of words to determine institute's predicate corresponding type of emotion in described audible spectrum; Search the mood tone weight allocation table setting in advance, determine the mood tone weight allocation value corresponding with the type of emotion of word in described set of words, in described mood tone weight allocation table, comprise the corresponding relation between type of emotion and mood tone weight allocation value.If comprise described part of speech weight allocation value in described at least one or polytype weight allocation value, search the part of speech weight allocation table setting in advance, determine on the time point of the word correspondence in described calling record in described set of words, the part of speech weight allocation value corresponding to part of speech of institute's predicate, comprises the corresponding relation between part of speech, time range (optionally), part of speech weight allocation value in described part of speech weight allocation table.
In addition, mobile communication equipment 600 also can execution graph 1 to the method in embodiment illustrated in fig. 3, the embodiment of the present invention does not repeat them here.
Visible, adopt after such scheme, mobile communication equipment can obtain the keyword in calling record, and keyword is saved in the message registration that calling record is corresponding, make the user can be by checking that message registration determines conversation content, and do not need to play calling record, therefore, resource occupation and the power consumption that can effectively avoid the broadcasting of calling record to bring, can effectively economize on resources.
The Fig. 7 of take preserves the logical construction of the mobile communication equipment of keyword as what example introduced that the embodiment of the present invention provides in the message registration of mobile communication equipment.This mobile communication equipment can be mobile terminal, is specifically as follows a smart mobile phone.As shown in Figure 7, the hardware layer of mobile communication equipment comprises CPU, GPU etc., certainly can also comprise memory, input-output apparatus, internal memory, Memory Controller Hub, network interface etc., input equipment can comprise keyboard, mouse, touch-screen etc., and output equipment can comprise that display device is as LCD, CRT, holographic imaging (Holographic), projection (Projector) etc.Operating system (as Android etc.) and some application programs on hardware layer, can have been moved.Core library is the core of operating system, comprises I/O service, kernel service, GDI and realizes graphics engine (Graphics Engine) of CPU, GPU graphics process etc.Graphics engine can comprise 2D engine, 3D engine, synthesizer (Composition), frame buffer zone (Frame Buffer), EGL etc.In addition, this mobile communication equipment can also comprise driving layer, ccf layer and application layer.Drive layer can comprise CPU driving, GPU driving, display controller driving etc.
Ccf layer comprises graphical services (Graphic Service), system service (System service), web service (Web Service) and user's service (Customer Service) etc.; In graphical services, can comprise as micro-(Widget), painting canvas (Canvas), view (Views), Render Script etc.Application layer can comprise desktop (launcher), media player (Media Player), browser (Browser) etc.
Referring to Fig. 8, the embodiment of the present invention also provides a kind of mobile communication equipment 800.
As shown in Figure 8, for convenience of explanation, only show the part relevant to the embodiment of the present invention, concrete ins and outs do not disclose, and please refer to embodiment of the present invention method part.Mobile communication equipment shown in Fig. 8 800 can be the terminal equipment arbitrarily such as mobile phone, panel computer, vehicle-mounted computer, mainly take below mobile communication equipment 800 as mobile phone be example:
Wherein, shown in Fig. 8, be the block diagram of the part-structure of the mobile phone that the mobile communication equipment that provides to the embodiment of the present invention is relevant.With reference to figure 8, mobile phone comprises: radio frequency (Radio Frequency, RF) parts such as circuit 810, memory 820, input unit 830, Wireless Fidelity (wireless fidelity, WiFi) module 870, display unit 840, transducer 880, voicefrequency circuit 860, processor 880 and power supply 890.
Wherein, it will be understood by those skilled in the art that the handset structure shown in Fig. 8 does not form the restriction to mobile phone, can comprise the parts more more or less than diagram, or combine some parts, or different parts are arranged.
Below in conjunction with Fig. 8, each component parts of mobile phone is carried out to concrete introduction:
RF circuit 810 be used in receive and send messages or communication process in, the reception of signal and transmission, especially, after the downlink information of base station is received, process to processor 880; In addition, the up data of design are sent to base station.Conventionally, RF circuit includes but not limited to antenna, at least one amplifier, transceiver, coupler, low noise amplifier (Low Noise Amplifier, LNA), duplexer etc.In addition, RF circuit 810 can also be by radio communication and network and other devices communicatings.Above-mentioned radio communication can be used arbitrary communication standard or agreement, include but not limited to global system for mobile communications (Global System of Mobile communication, GSM), general packet radio service (General Packet Radio Service, GPRS), code division multiple access (Code Division Multiple Access, CDMA), Wideband Code Division Multiple Access (WCDMA) (Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE)), Email, Short Message Service (Short Messaging Service, SMS) etc.
Wherein, memory 820 can be used for storing software program and module, and processor 880 is stored in software program and the module of memory 820 by operation, thereby carries out various function application and the data processing of mobile phone.Memory 820 can mainly comprise storage program district and storage data field, wherein, and the application program (as sound-playing function, image player function etc.) that storage program district can storage operation system, at least one function is required etc.; The data (as voice data, phone directory etc.) that create according to the use of mobile phone etc. can be stored in storage data field.In addition, memory 820 can comprise high-speed random access memory, can also comprise nonvolatile memory, for example at least one disk memory, flush memory device or other volatile solid-state parts.
Input unit 830 can be used for receiving numeral or the character information of input, and generation arranges with the user of mobile phone 800 and function is controlled relevant key signals input.Particularly, input unit 830 can comprise contact panel 831 and other input equipments 832.Contact panel 831, also referred to as touch-screen, can collect user or near touch operation (using any applicable object or near the operations of annex on contact panel 831 or contact panel 831 such as finger, stylus such as user) thereon, and drive corresponding jockey according to predefined formula.Optionally, contact panel 831 can comprise touch detecting apparatus and two parts of touch controller.Wherein, touch detecting apparatus detects user's touch orientation, and detects the signal that touch operation is brought, and sends signal to touch controller; Touch controller receives touch information from touch detecting apparatus, and converts it to contact coordinate, then gives processor 880, and the order that energy receiving processor 880 is sent is also carried out.In addition, can adopt the polytypes such as resistance-type, condenser type, infrared ray and surface acoustic wave to realize contact panel 831.Except contact panel 831, input unit 830 can also comprise other input equipments 832.Particularly, other input equipments 832 can include but not limited to one or more in physical keyboard, function key (controlling button, switch key etc. such as volume), trace ball, mouse, action bars etc.
Wherein, display unit 840 can be used for showing the information inputted by user or the various menus of the information that offers user and mobile phone.Display unit 840 can comprise display floater 841, optionally, can adopt the forms such as liquid crystal display (Liquid Crystal Display, LCD), Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED) to configure display floater 841.Further, contact panel 831 can cover display floater 841, when contact panel 831 detect thereon or near touch operation after, send processor 880 to determine the type of touch event, corresponding vision output is provided according to the type of touch event with preprocessor 880 on display floater 841.Although in Fig. 8, contact panel 831 and display floater 841 be as two independently parts realize the input function of mobile phone, in certain embodiments, can contact panel 831 and display floater 841 is integrated and realize the input and output function of mobile phone.
Wherein, mobile phone 800 also can comprise at least one transducer 880, as optical sensor, motion sensor and other transducers.Particularly, optical sensor can comprise ambient light sensor and proximity transducer, wherein ambient light sensor can regulate according to the light and shade of ambient light the brightness of display floater 841, and proximity transducer can, when mobile phone moves in one's ear, cut out display floater 841 and/or backlight.A kind of as motion sensor; accelerometer sensor can detect the size of the acceleration that (is generally three axles) in all directions; when static, can detect size and the direction of gravity, can be used for identifying application (such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, knock) of mobile phone attitude etc.; As for mobile phone other transducers such as configurable gyroscope, barometer, hygrometer, thermometer, infrared ray sensor also, do not repeat them here.
Voicefrequency circuit 860, loud speaker 861, microphone 862 can provide the audio interface between user and mobile phone.Voicefrequency circuit 860 can be transferred to loud speaker 861 by the signal of telecommunication after the voice data conversion receiving, and is converted to voice signal exports by loud speaker 861; On the other hand, microphone 862 is converted to the signal of telecommunication by the voice signal of collection, after being received by voicefrequency circuit 860, be converted to voice data, after again voice data output processor 880 being processed, through RF circuit 810, to send to such as another mobile phone, or export voice data to memory 820 to further process.
WiFi belongs to short range wireless transmission technology, mobile phone by WiFi module 870 can help that user sends and receive e-mail, browsing page and access streaming video etc., it provides wireless broadband internet access for user.Although Fig. 8 shows WiFi module 870, be understandable that, it does not belong to must forming of mobile phone 800, completely can be as required in not changing the essential scope of invention and omit.
Processor 880 is control centres of mobile phone, utilize the various piece of various interface and the whole mobile phone of connection, by moving or carry out software program and/or the module being stored in memory 820, and call the data that are stored in memory 820, carry out various functions and the deal with data of mobile phone, thereby mobile phone is carried out to integral monitoring.Optionally, processor 880 can comprise one or more processing units; Preferably, processor 880 can integrated application processor and modem processor, and wherein, application processor is mainly processed operating system, user interface and application program etc., and modem processor is mainly processed radio communication.Be understandable that, above-mentioned modem processor also can not be integrated in processor 880.
Mobile phone 800 also comprises that the power supply 890(powering to all parts is such as battery), preferably, power supply can be connected with processor 880 logics by power-supply management system, thereby realizes the functions such as management charging, electric discharge and power managed by power-supply management system.Although not shown, mobile phone 800 can also comprise camera, bluetooth module etc., does not repeat them here.
In embodiments of the present invention, the included processor 880 of this mobile phone specifically for: the calling record that the message registration of mobile phone is corresponding is processed, obtain the set of words that described calling record is corresponding, described word set is combined into the set of the word occurring in described calling record; Calculate the weight allocation value of one or more types that word in described set of words is corresponding; According to the weight allocation value of described one or more types that in described set of words, word is corresponding, calculate the weighted value of institute's predicate; Keyword is saved in described message registration, and described keyword is the word that in described set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, described N is positive integer.
Be understandable that, the function of the part of devices of the mobile phone 800 of the present embodiment can be according to the method specific implementation in said method embodiment, and its specific implementation process can, with reference to the associated description of said method embodiment, repeat no more herein.
One of ordinary skill in the art will appreciate that all or part of step realizing in above-described embodiment method is to come the hardware that instruction is relevant (for example processor) to complete by program, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium of mentioning can be read-only memory, disk or CD etc.
Above a kind of method and apparatus of preserving keyword in the message registration of mobile communication equipment provided by the present invention is described in detail, for one of ordinary skill in the art, thought according to the embodiment of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.

Claims (22)

1. in the message registration of mobile communication equipment, preserve a method for keyword, it is characterized in that, comprising:
The calling record that described message registration is corresponding is processed, obtained the set of words that described calling record is corresponding, described word set is combined into the set of the word occurring in described calling record;
Calculate the weight allocation value of one or more types that word in described set of words is corresponding;
According to the weight allocation value of described one or more types that in described set of words, word is corresponding, calculate the weighted value of institute's predicate;
Keyword is saved in described message registration, and described keyword is the word that in described set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, described N is positive integer.
2. method according to claim 1, is characterized in that, comprises the one-to-one relationship between word and the word time point in described calling record in described set of words.
3. method according to claim 2, is characterized in that, the weight allocation value of one or more types that word in the described set of words of described calculating is corresponding comprises:
Calculate word in the described set of words corresponding weight allocation value of at least two types on corresponding time point in described calling record;
The weighted value that the described weight allocation value according to described one or more types that in described set of words, word is corresponding is calculated institute's predicate comprises:
On each corresponding time point using same word in described set of words in described calling record, the set of the corresponding weight allocation value of described at least two types is as subset corresponding to institute's predicate;
Calculate described in the subset that institute's predicate is corresponding product between the weight allocation value of described at least two types corresponding on word each corresponding time point in described calling record, described product and be the weighted value of institute's predicate.
4. method according to claim 2, is characterized in that, the weight allocation value of one or more types that word in the described set of words of described calculating is corresponding comprises:
Calculate the weight allocation value of same type corresponding on the time point of the word correspondence in described calling record in described set of words;
The weighted value that the described weight allocation value according to described one or more types that in described set of words, word is corresponding is calculated institute's predicate comprises:
On each corresponding time point using same word in described set of words in described calling record between the weight allocation value of corresponding described same type and as institute's predicate the weighted value corresponding to the weight allocation value of described same type;
If the type of described weight allocation value is a kind of, determine that institute's predicate is the weighted value of institute's predicate corresponding to the weighted value of the weight allocation value of described same type;
If the type of described weight allocation value is multiple, determine that institute's predicate is the weighted value of institute's predicate corresponding to the product between the weighted value of the weight allocation value of every type in described polytype weight allocation value.
5. according to the method described in claim 3 or 4, it is characterized in that, the type of described weight allocation value comprises: one or more in air time weight allocation value, mood tone weight allocation value, part of speech weight allocation value;
The weight allocation value of one or more types that word in the described set of words of described calculating is corresponding comprises:
Calculate word in described set of words corresponding air time weight allocation value on corresponding time point in calling record;
And/or, calculate word in described set of words corresponding mood tone weight allocation value on corresponding time point in calling record;
And/or, calculate word in the described set of words part of speech weight allocation value on corresponding time point in calling record.
6. method according to claim 5, it is characterized in that, if comprise described air time weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding air time weight allocation value comprise:
The time point that calculates the word correspondence in described calling record in described set of words accounts for the percentage of the duration of described calling record;
Search the percentage of time weight allocation table setting in advance, determine the air time weight allocation value corresponding with described percentage, in described percentage weight allocation table, comprise the corresponding relation between percentage range and air time weight allocation value.
7. method according to claim 5, it is characterized in that, if comprise described air time weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding air time weight allocation value comprise:
Search the time weighting allocation table setting in advance, determine and institute predicate corresponding air time weight allocation value on corresponding time point in described calling record, described time weighting allocation table comprises the corresponding relation between time range and air time weight allocation value.
8. method according to claim 5, it is characterized in that, if comprise described mood tone weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding mood tone weight allocation value comprise:
Described calling record is carried out to audio analysis processing, obtain the audible spectrum of described calling record;
Utilize the corresponding time point in described calling record of word in described set of words to determine institute's predicate corresponding type of emotion in described audible spectrum;
Search the mood tone weight allocation table setting in advance, determine the mood tone weight allocation value corresponding with the type of emotion of word in described set of words, in described mood tone weight allocation table, comprise the corresponding relation between type of emotion and mood tone weight allocation value.
9. method according to claim 5, it is characterized in that, if comprise described part of speech weight allocation value in described at least one or polytype weight allocation value, the part of speech weight allocation value on corresponding time point in calling record of the word in the described set of words of described calculating comprises:
Search the part of speech weight allocation table setting in advance, determine on the time point of the word correspondence in described calling record in described set of words, the part of speech weight allocation value corresponding to part of speech of institute's predicate, comprises the corresponding relation between part of speech, time range, part of speech weight allocation value in described part of speech weight allocation table.
10. method according to claim 1, is characterized in that, described calling record corresponding to described message registration is processed, and obtains the set of words that described calling record is corresponding and comprises:
Described calling record is carried out to the voice word processing of larding speech with literary allusions, obtain the Word message that described calling record is corresponding;
Described Word message is carried out to word segmentation processing, obtain described set of words.
11. methods according to claim 10, is characterized in that, described method also comprises:
Word in described set of words is carried out to de-redundancy processing, obtains the set of words after de-redundancy is optimized,
The weight allocation value of one or more types that word in the described set of words of described calculating is corresponding comprises:
Calculate the weight allocation value of one or more types that word in the set of words after de-redundancy is optimized is corresponding.
12. 1 kinds of equipment of preserving keyword in the message registration of mobile communication equipment, is characterized in that, comprising:
Processing module, for calling record corresponding to described message registration processed, obtains the set of words that described calling record is corresponding, and described word set is combined into the set of the word occurring in described calling record;
Computing module, after obtaining described calling record set of words in described processing module, calculates the weight allocation value of one or more types that word in described set of words is corresponding;
Weight computation module, after obtaining the weight allocation value of one or more types that the word of described set of words is corresponding at described computing module, according to the weight allocation value of described one or more types that in described set of words, word is corresponding, calculate the weighted value of institute's predicate;
Preserve module, for after described weight computation module obtains the weighted value of institute's predicate, keyword is saved in described message registration, described keyword is the word that in described set of words, weighted value comes front N, or for weighted value is more than or equal to the word of the threshold value setting in advance, described N is positive integer.
13. equipment according to claim 12, is characterized in that, comprise the one-to-one relationship between word and the time point of word in described calling record in the described set of words that described processing module obtains.
14. equipment according to claim 13, it is characterized in that, described computing module is specifically for after obtaining described calling record set of words in described processing module, calculates word in the described set of words corresponding weight allocation value of at least two types on corresponding time point in described calling record;
Described weight computation module specifically for:
After the weight allocation value of at least two types described in described computing module obtains, on each the corresponding time point using same word in described set of words in described calling record, the set of the corresponding weight allocation value of described at least two types is as subset corresponding to institute's predicate;
Calculate described in the subset that institute's predicate is corresponding product between the weight allocation value of described at least two types corresponding on word each corresponding time point in described calling record, described product and be the weighted value of institute's predicate.
15. equipment according to claim 13, it is characterized in that, described computing module, specifically for after obtaining described calling record set of words in described processing module, calculates the weight allocation value of same type corresponding on the time point of the word correspondence in described calling record in described set of words;
Described weight computation module specifically for:
On each corresponding time point using same word in described set of words in described calling record between the weight allocation value of corresponding described same type and as institute's predicate the weighted value corresponding to the weight allocation value of described same type;
If the type of described weight allocation value is a kind of, determine that institute's predicate is the weighted value of institute's predicate corresponding to the weighted value of the weight allocation value of described same type;
If the type of described weight allocation value is multiple, determine that institute's predicate is the weighted value of institute's predicate corresponding to the product between the weighted value of the weight allocation value of every type in described polytype weight allocation value.
16. according to the equipment described in claims 14 or 15, it is characterized in that, the type of described weight allocation value comprises: one or more in air time weight allocation value, mood tone weight allocation value, part of speech weight allocation value;
Described computing module is specifically for after obtaining described calling record set of words in described processing module, calculates word in described set of words corresponding air time weight allocation value on corresponding time point in calling record; And/or, calculate word in described set of words corresponding mood tone weight allocation value on corresponding time point in calling record; And/or, calculate word in the described set of words part of speech weight allocation value on corresponding time point in calling record.
17. equipment according to claim 16, it is characterized in that, if comprise described air time weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding air time weight allocation value aspect, described computing module specifically for:
The time point that calculates the word correspondence in described calling record in described set of words accounts for the percentage of the duration of described calling record;
Search the percentage of time weight allocation table setting in advance, determine the air time weight allocation value corresponding with described percentage, in described percentage weight allocation table, comprise the corresponding relation between percentage range and air time weight allocation value.
18. equipment according to claim 16, it is characterized in that, if comprise described air time weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding air time weight allocation value aspect, described computing module specifically for:
Search the time weighting allocation table setting in advance, determine and institute predicate corresponding air time weight allocation value on corresponding time point in described calling record, described time weighting allocation table comprises the corresponding relation between time range and air time weight allocation value.
19. equipment according to claim 16, it is characterized in that, if comprise described mood tone weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record on corresponding time point corresponding mood tone weight allocation value aspect, described computing module specifically for:
Described calling record is carried out to audio analysis processing, obtain the audible spectrum of described calling record;
Utilize the corresponding time point in described calling record of word in described set of words to determine institute's predicate corresponding type of emotion in described audible spectrum;
Search the mood tone weight allocation table setting in advance, determine the mood tone weight allocation value corresponding with the type of emotion of word in described set of words, in described mood tone weight allocation table, comprise the corresponding relation between type of emotion and mood tone weight allocation value.
20. equipment according to claim 16, it is characterized in that, if comprise described part of speech weight allocation value in described at least one or polytype weight allocation value, the word in the described set of words of described calculating in calling record the part of speech weight allocation value on corresponding time point aspect, described computing module specifically for:
Search the part of speech weight allocation table setting in advance, determine on the time point of the word correspondence in described calling record in described set of words, the part of speech weight allocation value corresponding to part of speech of institute's predicate, comprises the corresponding relation between part of speech, time range, part of speech weight allocation value in described part of speech weight allocation table.
21. according to claim 12 to the equipment described in 20 any one, it is characterized in that, described processing module comprises:
The voice word processing module of larding speech with literary allusions, for described calling record being carried out to the voice word processing of larding speech with literary allusions, obtains the Word message that described calling record is corresponding;
Word segmentation processing module, after obtaining described Word message, carries out word segmentation processing to described Word message for the word processing module of larding speech with literary allusions at described voice, obtains described set of words.
22. equipment according to claim 21, is characterized in that, described equipment also comprises:
De-redundancy processing module, for obtaining, after described set of words, the word in described set of words being carried out to de-redundancy processing in described word segmentation processing module, obtains the set of words after de-redundancy is optimized,
Described computing module is for the weight allocation value of one or more types corresponding to the word of the set of words after calculating de-redundancy and optimizing.
CN201310446351.0A 2013-09-26 2013-09-26 The method and apparatus of keyword is preserved in the message registration of mobile communication equipment Active CN103533144B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310446351.0A CN103533144B (en) 2013-09-26 2013-09-26 The method and apparatus of keyword is preserved in the message registration of mobile communication equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310446351.0A CN103533144B (en) 2013-09-26 2013-09-26 The method and apparatus of keyword is preserved in the message registration of mobile communication equipment

Publications (2)

Publication Number Publication Date
CN103533144A true CN103533144A (en) 2014-01-22
CN103533144B CN103533144B (en) 2017-06-06

Family

ID=49934805

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310446351.0A Active CN103533144B (en) 2013-09-26 2013-09-26 The method and apparatus of keyword is preserved in the message registration of mobile communication equipment

Country Status (1)

Country Link
CN (1) CN103533144B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104184870A (en) * 2014-07-29 2014-12-03 小米科技有限责任公司 Call log marking method and device and electronic equipment
CN104869217A (en) * 2014-02-21 2015-08-26 宇龙计算机通信科技(深圳)有限公司 Method and terminal for marking communication information
CN105657129A (en) * 2016-01-25 2016-06-08 百度在线网络技术（北京）有限公司 Call information obtaining method and device
CN106598621A (en) * 2016-12-22 2017-04-26 维沃移动通信有限公司 Working method for application program and mobile terminal
CN109150885A (en) * 2018-08-29 2019-01-04 承启通（福建）科技有限公司 The processing method and processing device of communicating data
WO2020007192A1 (en) * 2018-07-03 2020-01-09 中兴通讯股份有限公司 Recording processing method and apparatus, recording playing method and apparatus, server, terminal and storage medium
CN112445813A (en) * 2020-12-01 2021-03-05 深圳市中博科创信息技术有限公司 Search semantic analysis method for enterprise service portal platform

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007096961A (en) * 2005-09-29 2007-04-12 Saxa Inc Telephone apparatus
CN102289523A (en) * 2011-09-20 2011-12-21 北京金和软件股份有限公司 Method for intelligently extracting text labels
CN103067608A (en) * 2013-01-23 2013-04-24 广东欧珀移动通信有限公司 Method and system for mobile terminal recent call searching

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007096961A (en) * 2005-09-29 2007-04-12 Saxa Inc Telephone apparatus
CN102289523A (en) * 2011-09-20 2011-12-21 北京金和软件股份有限公司 Method for intelligently extracting text labels
CN103067608A (en) * 2013-01-23 2013-04-24 广东欧珀移动通信有限公司 Method and system for mobile terminal recent call searching

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104869217A (en) * 2014-02-21 2015-08-26 宇龙计算机通信科技(深圳)有限公司 Method and terminal for marking communication information
CN104869217B (en) * 2014-02-21 2018-05-25 宇龙计算机通信科技(深圳)有限公司 Mark the method and terminal of communication information
CN104184870A (en) * 2014-07-29 2014-12-03 小米科技有限责任公司 Call log marking method and device and electronic equipment
CN105657129A (en) * 2016-01-25 2016-06-08 百度在线网络技术（北京）有限公司 Call information obtaining method and device
CN106598621A (en) * 2016-12-22 2017-04-26 维沃移动通信有限公司 Working method for application program and mobile terminal
WO2020007192A1 (en) * 2018-07-03 2020-01-09 中兴通讯股份有限公司 Recording processing method and apparatus, recording playing method and apparatus, server, terminal and storage medium
CN109150885A (en) * 2018-08-29 2019-01-04 承启通（福建）科技有限公司 The processing method and processing device of communicating data
CN109150885B (en) * 2018-08-29 2021-05-11 承启通（福建）科技有限公司 Call data processing method and device
CN112445813A (en) * 2020-12-01 2021-03-05 深圳市中博科创信息技术有限公司 Search semantic analysis method for enterprise service portal platform

Also Published As

Publication number Publication date
CN103533144B (en) 2017-06-06

Similar Documents

Publication Publication Date Title
CN104243671B (en) Volume adjusting method, device and electronic equipment
CN103533144A (en) Method and equipment for storing keywords in call records of mobile communication equipment
US10193834B2 (en) Method and apparatus for downloading and displaying pictures
CN104298491B (en) Message treatment method and device
CN104978115A (en) Content display method and device
CN105187930A (en) Video live broadcasting-based interaction method and device
CN104252341B (en) The client device of the skin change method of application program, device and application program
CN105554522A (en) Method for playing audio in group, server and terminal
CN106776036A (en) A kind of resource allocation methods and device
CN104965843A (en) Method and apparatus for acquiring comment information
CN103313139A (en) History display method and device and electronic device
CN104158506A (en) Method, device and terminal for adjusting volume
CN103179026B (en) Communication means in user interactive system, system and server and client side
CN104144312A (en) Video processing method and related device
CN104519404A (en) Graphics interchange format file playing method and device
CN104298666A (en) Web page sharing method and web page sharing device
CN104954159A (en) Network information statistics method and device
CN104618223A (en) Information recommendation management method, device and system
CN106797336A (en) The method and apparatus of history chat record displaying
CN103346921A (en) User management method, relevant equipment and communication system
CN105630846A (en) Head portrait updating method and apparatus
CN103945241A (en) Streaming data statistical method, system and related device
CN103713943A (en) Native terminal operating system based application function realization method and device
CN104281610B (en) The method and apparatus for filtering microblogging
CN105550316A (en) Pushing method and device of audio list

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20211222

Address after: 450046 Floor 9, building 1, Zhengshang Boya Plaza, Longzihu wisdom Island, Zhengdong New Area, Zhengzhou City, Henan Province

Patentee after: Super fusion Digital Technology Co.,Ltd.

Address before: 518129 Bantian HUAWEI headquarters office building, Longgang District, Guangdong, Shenzhen

Patentee before: HUAWEI TECHNOLOGIES Co.,Ltd.