CN110225185A - A kind of processing method and terminal device of Message-text - Google Patents

A kind of processing method and terminal device of Message-text Download PDF

Info

Publication number
CN110225185A
CN110225185A CN201910393208.7A CN201910393208A CN110225185A CN 110225185 A CN110225185 A CN 110225185A CN 201910393208 A CN201910393208 A CN 201910393208A CN 110225185 A CN110225185 A CN 110225185A
Authority
CN
China
Prior art keywords
text
message
feature
value
priority degree
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
CN201910393208.7A
Other languages
Chinese (zh)
Other versions
CN110225185B (en
Inventor
张昭
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.)
Vivo Mobile Communication Co Ltd
Original Assignee
Vivo Mobile Communication 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 Vivo Mobile Communication Co Ltd filed Critical Vivo Mobile Communication Co Ltd
Priority to CN201910393208.7A priority Critical patent/CN110225185B/en
Publication of CN110225185A publication Critical patent/CN110225185A/en
Application granted granted Critical
Publication of CN110225185B publication Critical patent/CN110225185B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/52—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/724—User interfaces specially adapted for cordless or mobile telephones
    • H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
    • H04M1/7243—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/724—User interfaces specially adapted for cordless or mobile telephones
    • H04M1/72469—User interfaces specially adapted for cordless or mobile telephones for operating the device by selecting functions from two or more displayed items, e.g. menus or icons

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Human Computer Interaction (AREA)
  • Computing Systems (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The present invention provides a kind of processing method of Message-text and terminal devices, comprising: receives multiple Message-texts；According to the text feature of multiple Message-texts, at least one target message text is determined from multiple Message-texts；Displaying target Message-text, the present invention can pass through the text feature of Message-text, the target message text with higher significance level is determined from multiple Message-texts, target message text is demonstrated, achieve the purpose that carry out Message-text classification displaying, the probability that important chat messages are missed is reduced, the browsing time of Message-text is saved.

Description

A kind of processing method and terminal device of Message-text
Technical field
The present embodiments relate to the processing methods and terminal of field of communication technology more particularly to a kind of Message-text to set It is standby.
Background technique
In communication class application, most users can be chatted in chat group at everybody in the chat group When, the terminal device of each user can receive a large amount of chat messages.
In the prior art, terminal device can pass through after being sequentially received multiple chat messages according to reception sequence These chat messages are successively shown by chat interface according to reception sequence again.
But at present in scheme, since the information content in chat group is larger, if according to reception sequence by chat messages according to It is secondary to be shown, it is missed so that often having important chat messages, or more chat of back leafing through is needed when leafing through Its message causes to waste time.
Summary of the invention
The embodiment of the present invention provides the processing method and terminal device of a kind of Message-text, with solve in the prior art according to Chat messages are successively shown by reception sequence, are missed so that often having important chat messages, or when leafing through More chat messages of back leafing through are needed, the problem of wasting time is caused.
In a first aspect, being applied to terminal device, the party the embodiment of the invention provides a kind of processing method of Message-text Method includes:
Receive multiple Message-texts；
According to the text feature of multiple Message-texts, determine that at least one target disappears from multiple Message-texts Informative text；
Show the target message text.
Preferably, the text feature according to multiple Message-texts, from multiple Message-texts determine to The step of few target message text, comprising:
Corresponding relationship between the feature classification of the text feature and default feature classification and default weighted value is carried out Matching adds corresponding weighted value for the text feature, obtains weighting text feature；
According to the weighting text feature, the priority degree value of each Message-text is determined；
According to the priority degree value, at least one target message text is determined from multiple Message-texts.
Preferably, pair by between the feature classification of the text feature and default feature classification and default weighted value The step of should being related to and be matched, adding corresponding weighted value for the text feature, obtain weighting text feature, comprising:
According to the text feature and the m feature classifications of the n Message-texts, establishing dimension is (m × n) Weighted feature matrix, wherein n and m is the integer greater than 0；
Feature classification and the default spy for each matrix element of the weighted feature matrix, when the text feature When levying categorical match, the corresponding default weighted value of the default feature classification is added to the matrix element；
When the feature classification of the text feature and the default feature classification mismatch, preset constant is added to institute State matrix element.
Preferably, described according to the weighting text feature, determine the priority degree value of each Message-text Step, comprising:
Calculating is summed up to each row in the n row data of the weighted feature matrix, obtains the n priority journeys Angle value；
It is described according to the priority degree value, at least one target message text is determined from multiple Message-texts The step of, comprising:
In the n priority degree value, Message-text corresponding to maximum priority degree value will be worth, be determined as The target message text.
Preferably, described according to the priority degree value, at least one target is determined from multiple Message-texts The step of Message-text, comprising:
If each of determining in the priority degree value of the Message-text, existing according to the weighting text feature The multiple Message-text is then worth descending suitable by the maximum priority degree values of multiple values according to the priority degree Sequence is arranged, and Message-text sequence is obtained；
According to preset constant k, since priority degree described in the Message-text sequence is worth maximum one end, choose (1+k) a Message-text, and determine the average priority degree value M of each Message-texta；
In (1+k) a described Message-text, maximum average priority degree value M will be worthaCorresponding Message-text, It is determined as the target message text；
Wherein, for a-th of Message-text in (1+k) a Message-text, a-th of Message-text is corresponding Average priority degree valueThe raIt is corresponding preferential for a-th of Message-text Stage value, the preset constant k are the integer greater than 0.
Preferably, in (1+k) a described Message-text, maximum average priority degree value M will be worthaCorresponding disappears Informative text, specifically includes the step of being determined as the target message text:
Determine (1+k) a described average priority degree value MaIn, the adjacent average priority degree value MaBetween Difference；
In all differences, preset if the quantity for being less than or equal to the difference of preset difference value threshold value is greater than or equal to Amount threshold will then be worth maximum average priority degree value MaCorresponding Message-text is determined as the target message text This.
Preferably, according to the weighting text feature, the step of the priority degree value of each Message-text is determined After rapid, further includes:
Multiple maximum priority degree values of value if it exists, it is determined that multiple maximum priority degree values of described value Corresponding Message-text, and the target that the text feature for reducing the Message-text is matched to presets weighted value.
Preferably, the default weighted value includes positive weights value and negative weighted value.
Second aspect, the embodiment of the invention provides a kind of terminal device, which includes:
Receiving module, for receiving multiple Message-texts；
Determining module is determined from multiple Message-texts for the text feature according to multiple Message-texts At least one target message text；
Display module, for determining the priority degree value of each Message-text according to the weighting text feature, And according to the priority degree value, at least one target message text is determined from multiple Message-texts.
Preferably, the determining module, comprising:
Submodule is weighted, for will be between the feature classification of the text feature and default feature classification and default weighted value Corresponding relationship matched, add corresponding weighted value for the text feature, obtain weighting text feature；
Computational submodule, for determining the priority degree of each Message-text according to the weighting text feature Value；
Classification submodule, for determining at least one from multiple Message-texts according to the priority degree value Target message text.
Preferably, the weighting submodule, comprising:
Matrix establishes unit, for the text feature and the m feature classifications according to the n Message-texts, builds Vertical dimension is the weighted feature matrix of (m × n), wherein n and m is the integer greater than 0；
Matrix weights unit, for each matrix element for the weighted feature matrix, as the spy of the text feature It levies classification and when the default feature categorical match, the corresponding default weighted value of the default feature classification is added to the square Array element；
Constant adding unit, for when the feature classification of the text feature and the default feature classification mismatch, Preset constant is added to the matrix element.
Preferably, computational submodule, comprising:
Computing unit is summed it up, calculating is summed up for each row in the n row data to the weighted feature matrix, obtains To the n priority degree values；
The classification submodule, comprising:
First division unit, for that will be worth corresponding to maximum priority degree value in the n priority degree value Message-text, be determined as the target message text.
Preferably, the classification submodule, further includes:
Sequencing unit, if for according to the weighting text feature, the priority of each of determining Message-text In degree value, there are multiple maximum priority degree values of value, then by the multiple Message-text according to the priority degree It is worth descending sequence to be arranged, obtains Message-text sequence；
Averaging unit is summed it up, is used for according to preset constant k, the priority described in the Message-text sequence message text The maximum one end of degree value starts, and chooses (1+k) a Message-text, and obtains and determine the average preferential of each Message-text Stage value Ma；
Second division unit, for maximum average priority degree value M will to be worth in (1+k) a described Message-texta Corresponding Message-text is determined as the target message text；
Wherein, for a-th of Message-text in (1+k) a Message-text, a-th of Message-text is corresponding Average priority degree valueThe raIt is corresponding preferential for a-th of Message-text Stage value, the preset constant k are the integer greater than 0.
Preferably, the second division unit, further includes:
Difference computation subunit, for determining (1+k) a described average priority degree value MaIn, adjacent is described average Priority degree value MaBetween difference；
Third divides subelement, in all differences, if being less than or equal to the difference of preset difference value threshold value Quantity be greater than or equal to preset quantity threshold value, then will be worth maximum average priority degree value MaCorresponding Message-text, It is determined as the target message text.
Preferably, the determining module, further includes:
Weight adjusting submodule, for multiple maximum priority degree values of value if it exists, it is determined that multiple described It is worth the corresponding Message-text of maximum priority degree value, and the target that the text feature for reducing the Message-text is matched to Default weighted value.
Preferably, the default weighted value includes positive weights value and negative weighted value.
The third aspect the embodiment of the invention also provides a kind of terminal device, including processor, memory and is stored in institute The computer program that can be run on memory and on the processor is stated, when the computer program is executed by the processor The step of realizing the processing method such as Message-text provided by the invention.
Fourth aspect, the embodiment of the invention also provides computer readable storage mediums, which is characterized in that the computer It is stored with computer program on readable storage medium storing program for executing, the Message-text is realized when the computer program is executed by processor Processing method the step of.
In embodiments of the present invention, terminal device can receive multiple Message-texts；According to the text of multiple Message-texts Feature determines at least one target message text from multiple Message-texts；Displaying target Message-text, the present invention can pass through The text feature of Message-text determines the target message text with higher significance level from multiple Message-texts, makes Obtaining target message text can be demonstrated, and achieved the purpose that carry out Message-text classification displaying, reduced important chat The probability that message is missed saves the browsing time of Message-text.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention, And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
Fig. 1 is a kind of step flow chart of the processing method of Message-text provided in an embodiment of the present invention；
Fig. 2 is the step flow chart of the processing method of another Message-text provided in an embodiment of the present invention；
Fig. 3 is the step flow chart of the processing method of another Message-text provided in an embodiment of the present invention；
Fig. 4 is the step flow chart of the processing method of another Message-text provided in an embodiment of the present invention；
Fig. 5 is the step flow chart of the processing method of another Message-text provided in an embodiment of the present invention；
Fig. 6 is a kind of block diagram of terminal device provided in an embodiment of the present invention；
Fig. 7 is the block diagram of the terminal device of another embodiment of the present invention.
Specific embodiment
The exemplary embodiment that the present invention will be described in more detail below with reference to accompanying drawings.Although showing the present invention in attached drawing Exemplary embodiment, it being understood, however, that may be realized in various forms the present invention without should be by embodiments set forth here It is limited.It is to be able to thoroughly understand the present invention on the contrary, providing these embodiments, and can be by the scope of the present invention It is fully disclosed to those skilled in the art.
Fig. 1 is a kind of step flow chart of the processing method of Message-text provided in an embodiment of the present invention, as shown in Figure 1, This method may include:
Step 101 receives multiple Message-texts.
In embodiments of the present invention, a kind of implementation according to an embodiment of the present invention, terminal device can pass through machine After primary user's authorization, by calling the interface of communication class application, the extraction of Message-text in communication class application is carried out, wherein disappear Informative text can be to have read Message-text, or unread message text, the embodiment of the present invention are not construed as limiting this.
It should be noted that Message-text is not limited in the chat class message in communication class application, Message-text can also Think other notice class texts, e.g., the merchandise news of online shopping application push.
Step 102, according to the text feature of multiple Message-texts, at least one is determined from multiple Message-texts A target message text.
In embodiments of the present invention, it is characterized in that a certain class object is different from the corresponding feature or characteristic of other class objects, or It is the set of these features and characteristic, is characterized in by measuring or handling the data that can be extracted, the main purpose of feature extraction Dimensionality reduction, and its main thought is that original sample is projected to a low-dimensional feature space, obtain capable of most reacting sample essence or Carry out the low-dimensional sample characteristics of sample differentiation.
For Message-text information, it is that can allow that the purpose of the text feature of Message-text information, which is by text representation, Computer is come the form understood, i.e., by text vector, the extraction of text feature can also pass through corresponding Text Feature Extraction algorithm Model is realized, for example, built-in network model.
Specifically, in the processing scene of Message-text, it, can be by text spy according to the difference of the characteristic value of text feature Sign is divided into different feature classifications.Specifically, characteristic value can be used to express the different attribute difference of Message-text, the attribute Difference include but is not limited to text size difference between Message-text, in Message-text special word, special expression appearance Frequency difference, semantic Sentiment orientation of Message-text etc..According to text feature, the importance of each Message-text can be determined, To determine at least one more important target message text from multiple Message-texts.
Step 103, the target message text is shown.
In this step, by being shown to target message text, reached and classification displaying is carried out to Message-text Purpose reduces the probability that important chat messages are missed, saves the browsing time of Message-text.
In embodiments of the present invention, displaying target Message-text, specifically can in terminal device first displaying target message Text, later other texts except displaying target Message-text again.It top set can also be shown in the chat interface of terminal device Show target message text.Re-mark can also be added to the target message text of display in the chat interface of terminal device.
To sum up, the processing method of a kind of Message-text provided in an embodiment of the present invention, comprising: receive multiple Message-texts； According to the text feature of multiple Message-texts, at least one target message text is determined from multiple Message-texts；Displaying target Message-text, the present invention can be by the text features of Message-text, and determining from multiple Message-texts has compared with Gao Chong The target message text for wanting degree, is demonstrated target message text, has reached and has carried out classification displaying to Message-text Purpose, reduce the probability that important chat messages are missed, save the browsing time of Message-text.
Fig. 2 is a kind of step flow chart of the processing method of Message-text provided in an embodiment of the present invention, as shown in Fig. 2, This method may include:
Step 201 receives multiple Message-texts.
The step is referred to above-mentioned steps 101, and details are not described herein again.
It step 202, will be corresponding between the feature classification of the text feature and default feature classification and default weighted value Relationship is matched, and adds corresponding weighted value for the text feature, obtains weighting text feature.
It in embodiments of the present invention,, can according to the difference of the characteristic value of text feature in the processing scene of Message-text Text feature to be divided into different feature classifications.Specifically, characteristic value can be used to express the different attribute of Message-text Difference, which includes but is not limited to text size difference between Message-text, special word in Message-text, special The frequency of occurrences difference of expression, semantic Sentiment orientation of Message-text etc..
For example, being directed to two Message-texts " notifying everybody 4 point set in afternoon, receive R. S. V. P. " and " good, to receive ", lead to Often it is found that having keyword " notice ", the message of " R. S. V. P. " is often important message, disappear in addition, length is longer Breath also tends to be prior message, and therefore, it is " good that the importance of " notifying everybody 4 point set in afternoon, receive R. S. V. P. " is greater than , receive " importance can establish preset feature classification for the difference of this 2 kinds of message attributes in the citing are as follows: 1, There are keywords " notice ", " R. S. V. P. " in Message-text.2, the text size of Message-text is greater than a certain threshold value.For feature Classification 1 can preset a biggish weighted value a for it.For feature classification 2, a lesser weight can be preset for it Value b.When receiving a new Message-text, if the Message-text meets feature classification 1, weighted value a can be weighted Onto the Message-text, if the Message-text meets feature classification 2, weighted value b can be weighted on the Message-text, if The Message-text meets feature classification 1 and feature classification 2, then weighted value a and b can be weighted on the Message-text.
Further, for the processing scene of the Message-text in the embodiment of the present invention, the embodiment of the present invention can be provided One table 1 includes corresponding for 5 category feature classifications of the processing scene partitioning of Message-text and 5 category feature classifications in table 1 Characteristic value, characteristic is to, weighted value.
According to upper table 1 it is found that be directed to Message-text processing scene, can by feature category division be make a speech it is humanized, Message content, message Sentiment orientation, message-length, expression 5 classification, include several characteristic values in each classification, use In the different attribute difference of statement Message-text, wherein characteristic is in, and positive tropism is to referring to that the text is characterized in for important The beneficial category feature of degree.Negative tropism is to referring to that the text is characterized in that the non-beneficial category feature for different degree, weighted value can have There are high, medium and low three class to divide, and weighted value can reflect the class belonging to it by specific assignment.
For example, dividing in the feature classification of message content the text feature for determining obtained target message text Analysis can determine whether target message text includes " good ", and " thanks ", " thanks ", " receiving " etc. replies class phrase, if depositing The importance of, then it is assumed that the target message text may be lower, for the target message text text feature assign negative sense and Biggish weighted value obtains weighting text feature, so that it is subsequent according to the weighting text feature, carry out the priority of Message-text Degree value calculates.
It should be noted that being directed to a Message-text, the Message-text is obtained by that can extract to above-mentioned steps 202 Multiple text features, analyzed for multiple text feature, can by this multiple text feature one by one with corresponding spy Sign classification is associated, e.g., referring to table 1, it is assumed that there are three text feature (K1, K2, K3) for a Message-text tool, wherein K1 Can be associated with message-length feature classification, K2 can be associated with message content feature classification, and K3 can be with message emotion It is associated to be inclined to feature classification, K3 can it is associated with message Sentiment orientation feature classification then when text feature K1, K2, K3 all The characteristic value being respectively matched in respective feature classification, and assume the corresponding weighted value of characteristic value that is matched to be respectively a1, a2, A3, then respectively text feature K1, K2, K3 weights corresponding weighted value a1, a2, a3, obtain weighting text feature (K1a1, K2a2、K3a3)。
Optionally, default weighted value includes positive weights value and negative weighted value.
In embodiments of the present invention, preset weighted value have positive negativity to, positivity to the weighted value that is positive, for indicating it The text feature of weighting is the beneficial category feature for significance level.Negativity is to being negative weighted value, for indicating its weighting Text feature is the non-beneficial category feature for different degree, and in general, the value of positive weights value is positive number, and negative weighted value takes Value is negative value.
Step 203, according to the weighting text feature, the priority degree value of each Message-text is determined.
In this step, the preferential of each Message-text can be carried out according to the weighting text feature of each Message-text The calculating of stage value can obtain the preferential of Message-text by adduction in an implementation of the embodiment of the present invention Stage value, e.g., for providing exemplary Message-text and the corresponding weighting text of the Message-text in above-mentioned steps 203 Feature (K1a1, K2a2, K3a3), then the priority degree value of the Message-text can be (K1a1+K2a2+K3a3).
Step 204, according to the priority degree value, at least one target message is determined from multiple Message-texts Text.
In this step, when there are multiple Message-texts, it can be calculated according to adduction, obtain the excellent of each Message-text First stage value, priority degree value is bigger, illustrates that the significance level of corresponding Message-text is bigger, multiple Message-texts are pressed It is arranged according to the sequence of priority degree value from big to small, the Message-text sequence that available significance level arranges from big to small Column, wherein priority degree can be worth to maximum Message-text and be determined as target message text, it can also be by priority degree Value is greater than or equal to one or more Message-texts of preset threshold, is determined as target message text.
Further, it can be divided to according to practical business demand by Message-text according to the difference of priority degree value In different priority class, it is such as directed to three Message-texts A1, A2, A3.The priority degree value of A1 is the preferential of 10, A2 The priority degree value that stage value is 5, A3 is 1, it is assumed that establishes three priority class B1, B2, B3, B1 expression is high preferential Grade classification, B2 indicate normal priority classification, and B3 indicates lower priority class, then Message-text A1 can be divided to high priority Classification B1, Message-text A2 can be divided to normal priority classification B2, and Message-text A3 can be divided to lower priority class B3.When the subsequent displaying to Message-text operates, the Message-text in high priority class B1 can be first shown, then show one As Message-text in priority class B2, finally show the Message-text in lower priority class B3, reach to Message-text The purpose of classification displaying is carried out according to importance.
Step 205, the target message text is shown.
The step is referred to above-mentioned steps 103, and details are not described herein again.
To sum up, the processing method of a kind of Message-text provided in an embodiment of the present invention, comprising: receive multiple Message-texts； According to the text feature of multiple Message-texts, at least one target message text is determined from multiple Message-texts；Displaying target Message-text, the present invention utilize Message-text by the corresponding relationship established between default feature classification and default weighted value The corresponding feature classification of text feature is matched with default feature classification, and the text feature matched is added default feature class Not corresponding default weighted value, so that the priority degree value for carrying out Message-text calculates according to the text feature after weighting, from And determine the priority of Message-text, realize the purpose classified to Message-text according to priority, due to the present invention according to The feature classification of Message-text realizes the weighting to Message-text, and the priority degree value obtained according to weighting text feature, Carry out the significance level of Precise Representation Message-text, to realize the classification of Message-text, solves based on semantic analysis to message The problem of classification results inaccuracy is classified and caused to text, improves the nicety of grading to Message-text.
Fig. 3 is the step flow chart of the processing method of another Message-text provided in an embodiment of the present invention, such as Fig. 3 institute Show, this method may include:
Step 301 receives multiple Message-texts.
The implementation of this step is similar with the realization process of above-mentioned steps 101, and this will not be detailed here for the embodiment of the present invention.
Step 302, according to the text feature and the m feature classifications of the n Message-texts, establishing dimension is The weighted feature matrix of (m × n), wherein n and m is the integer greater than 0.
In this step, if terminal device receives n Message-text, and the text that each Message-text extracts is special Sign may have m feature classification, then according to the text feature of this n Message-text and m feature classification, establishes one A dimension is the weighted feature matrix of (m × n), which arranges with n row m.
For example, acquiring n Message-text (M1, M2, M3 ... Mn), it is assumed that divided m feature classification, then each message Text can extract to obtain m text feature, and e.g., Message-text M1 can extract to obtain text feature (K11, K12, K13 ... K1m), then according to the text feature of this n Message-text and m feature classification, establish and obtain the weighting that dimension is (m × n) Eigenmatrix is as follows:
<k11, k12 ..., k1m>
<k21, k22 ..., k2m>
…
<kn1, kn2 ..., knm>
Wherein, the data line in weighted feature matrix is used to reflect the text feature of a piece of news text.
Step 303, feature classification and institute for each matrix element of the weighted feature matrix, when the text feature When stating default feature categorical match, the corresponding default weighted value of the default feature classification is added to the matrix element.
In embodiments of the present invention, the feature classification of text feature is matched with default feature classification, in particular to will The characteristic value that the feature classification of text feature includes is matched with the characteristic value that default feature classification includes, to determine the two Between whether matched in the dimension of characteristic value, e.g., Message-text " notifying everybody 4 point set in afternoon, receive R. S. V. P. " can be by According to each keyword feature of feature classification extraction of message content, then the characteristic value of the Message-text may include each keyword Feature, and in default feature classification include the feature classification of a presetting message content, characteristic value includes that " whether Message-text Including certain predetermined keyword features ", if precisely the presence of default in each keyword feature that the characteristic value of Message-text includes Keyword feature, it may be considered that the message content feature classification of Message-text and presetting message content characteristic categorical match.
It further, can be weighted feature square according to the corresponding relationship between default feature classification and default weighted value Each matrix element of battle array carries out weight addition, obtains the weighted feature matrix that dimension is (m × n).
For example, for the weighted feature matrix provided in the example of step 302:
<k11, k12 ..., k1m>
<k21, k22 ..., k2m>
…
<kn1, kn2 ..., knm>
Assuming that the feature classification of every Message-text is all matched to corresponding m default feature classifications, and m feature class Default weighted value (a1, a2, a3 ... am) is not respectively corresponded, then processing is weighted to each matrix element of the weighted feature matrix Afterwards, available weighted feature matrix is as follows:
<k11a1, k12a2 ..., k1m am>
<k21a1, k22a2 ..., k2m am>
…
<kn1a1, kn2a2 ..., knm am>
Wherein, after each matrix element of the data line in weighted feature matrix is for reflecting the weighting of a piece of news text Text feature.
In addition, in embodiments of the present invention, when the feature classification of the text feature and the default feature classification not Preset constant is added to the matrix element by timing.
In embodiments of the present invention, when there are some more complicated Message-texts, what which extracted The feature classification of text feature can not all with default feature categorical match, there are the text features of some Message-texts Under feature classification and the default unmatched situation of feature classification, preset constant can be set, and preset constant is added to matrix Member.For example, under the feature classification and the default unmatched situation of feature classification of the text feature of Message-text, it is believed that should Text feature different degree is lower, therefore it is 0 that pre-set constant value, which can be set, which is added to matrix element, so that When calculating Message-text different degree, ignore the influence of this article eigen.
Step 304, according to the weighting text feature, the priority degree value of each Message-text is determined.
The step is referred to above-mentioned steps 203, and details are not described herein again.
Optionally, the step 304 can specifically include:
Sub-step 3041 sums up calculating to each row in the n row data of the weighted feature matrix, obtains n The priority degree value.
At this point, by summing up calculating to each row, so that n priority degree value is obtained, it can be to Message-text Priority clearly defined, consequently facilitating determine target text.
In embodiments of the present invention, the specific implementation that calculating process is summed it up in the step is indicated with an example, for example, false If there are 4 continuous message, message 1: " notice XXXXXXX, receive R. S. V. P. ".Message 2: " receiving ".Message 3: " good ". Message 4: " receiving ", and there are m default feature classifications, m feature classification respectively corresponds default weighted value (a1, a2, a3 ... Am), the feature classification of every Message-text is all matched to corresponding m default feature classifications, then the weighted feature matrix established It is as follows:
<k11a1, k12a2 ..., k1mam>// (weighted feature for indicating message 1)
<k21a1, k22a2 ..., k2mam>// (weighted feature for indicating message 2)
<k31a1, k32a2 ..., k3mam>// (weighted feature for indicating message 3)
<k41a1, k42a2 ..., k4mam>// (weighted feature for indicating message 4)
The then priority degree value R1=k11a1+k12a2+ ...+k1mam of message 1.
The priority degree value R2=k21a1+k22a2+ ...+k2mam of message 2.
The priority degree value R3=k31a1+k32a2+ ...+k3mam of message 3.
The priority degree value R4=k41a1+k42a2+ ...+k4mam of message 4.
In conjunction with the actual content of message, R1 > > R2 ≈ R3=R4 can be determined.
Step 305, according to the priority degree value, at least one target message is determined from multiple Message-texts Text.
The step is referred to above-mentioned steps 204, and details are not described herein again.
Optionally, when step 304 specifically includes 3041, step 305 be can specifically include:
Step 3051, in the n priority degree value, the text of message corresponding to maximum priority degree value will be worth This, is determined as the target message text.
In this step, the example provided for above-mentioned sub-step 3041, can choose 4 priority degree value intermediate values most Big priority degree value R1, and by the corresponding message 1 of the maximum priority degree R1 of the value, it is determined as highest priority, and The message 1 is determined as the target message text.
It should be noted that non-priority classification can also be established according to actual needs, it can be by priority degree value not High and similar message 2, message 3 and message 4 are divided in non-priority classification.
Step 306, the target message text is shown.
The step is referred to above-mentioned steps 103, and details are not described herein again.
In conclusion the processing method of another kind Message-text provided in an embodiment of the present invention, comprising: receive multiple message Text；According to the text feature of multiple Message-texts, at least one target message text is determined from multiple Message-texts；Display Target message text, the present invention utilize message text by the corresponding relationship established between default feature classification and default weighted value This corresponding feature classification of text feature is matched with default feature classification, and the text feature matched is added default spy The corresponding default weighted value of classification is levied, so that carrying out the priority degree value meter of Message-text according to the text feature after weighting It calculates, so that it is determined that the priority of Message-text, realizes the purpose classified to Message-text according to priority, due to the present invention The weighting to Message-text, and the priority degree obtained according to weighting text feature are realized according to the feature classification of Message-text Value, is carried out the significance level of Precise Representation Message-text, to realize the classification of Message-text, solves and offseted based on semantic analysis The problem of classification results inaccuracy is classified and caused to informative text, improves the nicety of grading to Message-text.
Fig. 4 is the step flow chart of the processing method of another Message-text provided in an embodiment of the present invention, such as Fig. 4 institute Show, this method may include:
Step 401 receives multiple Message-texts.
The implementation of this step is similar with the realization process of above-mentioned steps 101, and this will not be detailed here for the embodiment of the present invention.
Step 402, will be corresponding between the feature classification of the text feature and default feature classification and default weighted value Relationship is matched, and adds corresponding weighted value for the text feature, obtains weighting text feature.
The implementation of this step is similar with the realization process of above-mentioned steps 202, and this will not be detailed here for the embodiment of the present invention.
Step 403, according to the weighting text feature, determine the priority degree value of each Message-text.
The step is referred to above-mentioned steps 203, and details are not described herein again.
If step 404, in the priority degree value for each of according to the weighting text feature, determining the Message-text In, there are the maximum priority degree values of multiple values, then by the multiple Message-text according to the priority degree value by big It is arranged to small sequence, obtains Message-text sequence.
In this step, in certain actual scenes, if according to the weighting text feature, each of determining message In the priority degree value of text, there are multiple maximum priority degree values of value, such as, it is assumed that there are continuous meassage: message 1: It notifies XXXXXXX, receives R. S. V. P. message.2: supplement XXX, PLSCONFM.Message 3:XX confirmation.Message 4:XX is received.It calculates To the priority degree value R1 of message 1, the priority degree value R2 of message 2, the priority degree value R3 of message 3, message 4 it is excellent First stage value R4, R1=R2 > R3=R4.
Multiple Message-texts can be worth descending sequence according to the priority degree at this time to arrange, obtained Message-text sequence (message 1, message 2, message 3, message 4).
Step 405, according to preset constant k, the priority degree described in the Message-text sequence is worth maximum one end Start, chooses (1+k) a Message-text, and determine the average priority degree value M of each Message-texta。
In this step, for the example of above-mentioned steps 404, message 1 is the first important information, and message 2 is supplemental information (non-most important information), the simple priority degree value R for calculating the two can be mutually isolated due to calculating process between the two, To the equal situation of the priority degree value R of the two occur, but message 1 is only most important source information, such case Under can be by least calculating message 1 and the corresponding average priority degree value (k=1 at this time) of message 2, according to average preferential The size of stage value, further screening, which has more, in the message 1 and message 2 equal from priority degree value R makes a difference Message.
Specifically, for a-th of Message-text in described (1+k) a Message-text, a Message-text pair The average priority degree value answeredThe raIt is corresponding excellent for a-th of Message-text First stage value, the preset constant k are the integer greater than 0.
Then, in case of k=1, it since priority degree described in Message-text sequence is worth maximum one end, chooses (1+k) a Message-text, i.e. message 1 and message 2.
The average priority degree value of message 1
The average priority degree value of message 2
It should be noted that in embodiments of the present invention, (1+k) a Message-text being chosen from Message-text, first may be used It is arranged so that all Message-texts are worth descending sequence according to corresponding priority degree, and most from priority degree value Big starts on one side, chooses (1+k) a Message-text.
Furthermore it is possible to according to actual needs, be adjusted to the value of constant k, the value of k is bigger, illustrates to message severities The precision of judgement is higher, e.g., when k=1, during calculating average priority degree value of the message 1 to message 2, only should Message 1 and message 2 are associated with respectively adjacent another 1 message, average preferential to message 3 calculating message 1 when k=2 During stage value, message 1, message 2 and message 3 and respective adjacent another 2 message are associated.
Optionally, the step 405 can specifically include:
Sub-step 4051 determines in (1+k) a described average priority degree value M_a, the adjacent average priority Difference between degree value M_a.
In this step, it is assumed that there are new continuous meassage: message 1: notice XX receives R. S. V. P..Message 2:XXX is received It arrives.Message 3:XX confirmation.Message 4: it receives.The average priority degree value M1 of message 1 is calculated, being averaged for message 2 is preferential Stage value M2, the average priority degree value M3 of message 3, the average priority degree value M4 of message 4.Wherein, message 2 and disappear Breath 3 is noise data, needs to be screened out, then may further calculate between 4 (k value is 3) a average priority degree values Difference.That is difference 1=M1-M2, difference 2=M2-M3, difference 3=M4-M3, difference 4=M4-M2, difference 5=M1-M4.
Sub-step 4052, in all differences, if the quantity of target difference is greater than or equal to preset quantity threshold value, Maximum average priority degree value M will be then worthaCorresponding Message-text is determined as the target message text, the mesh It marks difference and is less than or equal to preset difference value threshold value.
In this step, the example provided in conjunction with above-mentioned steps 4051, if being less than or equal to the target of preset difference value threshold value The quantity of difference is greater than or equal to preset quantity threshold value, then it is assumed that and the average priority degree value of 4 message is unevenly distributed, And the average priority degree value of 4 message is suddenly big or suddenly small in distribution upper value, may thereby determine that there are more in 4 message Noise data then will can directly be worth Message-text corresponding to maximum average priority degree value at this time, be determined as important The highest Message-text of degree, and the Message-text is determined as the target message text.
Step 406, in (1+k) a described Message-text, maximum average priority degree value M will be worthaCorresponding Message-text is determined as the target message text.
In this step, the example provided in conjunction with above-mentioned steps 405, disappears since message 1 to message 4 is continuous four It ceases, then the average priority degree value M of above-mentioned message 11Calculating process, the priority degree value for reflecting message 1 is associated with The priority degree value of message 2 adjacent thereto, the average priority degree value M of message 22Calculating process, reflect message 2 Priority degree value be associated with the priority degree value of message 3 adjacent thereto, last calculated result is M1>M2, thus root It is the first important information to message 1 in conjunction with the context of message, message 2 is to mend according to the calculating of average priority degree value It fills information to be distinguished, message 1 can be determined as in the target message text, the embodiment of the present invention is passed through The context determination of the message message severities improve the accuracy of Message-text processing.
Step 407, the display target message text.
The step is specifically referred to above-mentioned steps 103, and details are not described herein again.
In conclusion the processing method of another kind Message-text provided in an embodiment of the present invention, comprising: receive multiple message Text；According to the text feature of multiple Message-texts, at least one target message text is determined from multiple Message-texts；Display Target message text, the present invention utilize message text by the corresponding relationship established between default feature classification and default weighted value This corresponding feature classification of text feature is matched with default feature classification, and the text feature matched is added default spy The corresponding default weighted value of classification is levied, so that carrying out the priority degree value meter of Message-text according to the text feature after weighting It calculates, so that it is determined that the priority of Message-text, realizes the purpose classified to Message-text according to priority, due to the present invention The weighting to Message-text, and the priority degree obtained according to weighting text feature are realized according to the feature classification of Message-text Value, is carried out the significance level of Precise Representation Message-text, to realize the classification of Message-text, solves and offseted based on semantic analysis The problem of classification results inaccuracy is classified and caused to informative text, improves the nicety of grading to Message-text.
Also, the embodiment of the present invention is realized by the further calculating to the average priority degree value of Message-text It is worth the purpose that further screening in equal multiple Message-texts has more the Message-text made a difference from priority degree, separately The outer embodiment of the present invention is by further calculating the difference between the average priority degree value of Message-text, according to the difference It is abnormal to judge that the average priority degree value of multiple message whether there is in distribution, realizes and is screened out from multiple Message-texts The purpose of noise data.
Fig. 5 is the step flow chart of the processing method of another Message-text provided in an embodiment of the present invention, such as Fig. 5 institute Show, this method may include:
Step 501 receives multiple Message-texts.
The implementation of this step is similar with the realization process of above-mentioned steps 101, and this will not be detailed here for the embodiment of the present invention.
Step 502, will be corresponding between the feature classification of the text feature and default feature classification and default weighted value Relationship is matched, and adds corresponding weighted value for the text feature, obtains weighting text feature.
The implementation of this step is similar with the realization process of above-mentioned steps 202, and this will not be detailed here for the embodiment of the present invention.
Step 503, according to the weighting text feature, determine the priority degree value of each Message-text.
The implementation of this step is similar with the realization process of above-mentioned steps 203, and this will not be detailed here for the embodiment of the present invention.
Step 504, according to the priority degree value, at least one target message is determined from multiple Message-texts Text.
The implementation of this step is similar with the realization process of above-mentioned steps 204, and this will not be detailed here for the embodiment of the present invention.
Step 505, if it exists multiple maximum priority degree values of value, it is determined that multiple described values are maximum preferential The corresponding Message-text of stage value, and the target that the text feature for reducing the Message-text is matched to presets weighted value.
In embodiments of the present invention, multiple if it exists to be worth maximum priority degree values, it may be considered that these are equal There is repeatability in Message-text corresponding to priority degree value, the default feature classification being matched to, which destroys Uniqueness (if Message-text is unique, illustrating that its importance is higher) in Message-text importance deterministic process, then may be used It is turned down with the value that there is the corresponding target of default feature classification of repeatability to preset weighted value to these, to reach optimization The purpose of corresponding relationship between default feature classification and default weighted value improves subsequent according to corresponding relationship progress message text The precision of this importance deterministic process.
In addition, multiple if it exists be worth maximum priority degree values, it can also be by these equal priority degree value institutes Corresponding Message-text carries out folding, and specially these Message-texts are stored in an openable label, and only will The openable label display is to user, when user executes the opening operation to the label, the message that can include by the label Text is shown, and reduces the time cost that user consults message.
It should be noted that the target that the text feature for reducing the Message-text is matched to preset weighted value it Afterwards, optionally, the process that can also re-start step 502 to step 504 reaches and presets weight according to the target after reduction Value, redefines the purpose of target message text.
Step 506, the display target message text.
The step is specifically referred to above-mentioned steps 103, and details are not described herein again.
In conclusion the processing method of another kind Message-text provided in an embodiment of the present invention, comprising: receive multiple message Text；According to the text feature of multiple Message-texts, at least one target message text is determined from multiple Message-texts；Display Target message text, the present invention utilize message text by the corresponding relationship established between default feature classification and default weighted value This corresponding feature classification of text feature is matched with default feature classification, and the text feature matched is added default spy The corresponding default weighted value of classification is levied, so that carrying out the priority degree value meter of Message-text according to the text feature after weighting It calculates, so that it is determined that the priority of Message-text, realizes the purpose classified to Message-text according to priority, due to the present invention The weighting to Message-text, and the priority degree obtained according to weighting text feature are realized according to the feature classification of Message-text Value, is carried out the significance level of Precise Representation Message-text, to realize the classification of Message-text, solves and offseted based on semantic analysis The problem of classification results inaccuracy is classified and caused to informative text, improves the nicety of grading to Message-text.
Also, the present invention can to have repeatability the corresponding target of default feature classification preset weighted value value into Row is turned down, and to achieve the purpose that optimize the corresponding relationship between default feature classification and default weighted value, improving subsequent basis should The precision of corresponding relationship progress Message-text importance deterministic process.
Fig. 6 is a kind of block diagram of terminal device provided in an embodiment of the present invention, as shown in fig. 6, the terminal device 60 includes:
Receiving module 601, for receiving multiple Message-texts；
Determining module 602, for the text feature according to multiple Message-texts, from multiple Message-texts really At least one fixed target message text；
Optionally, determining module 602, comprising:
Submodule is weighted, for will be between the feature classification of the text feature and default feature classification and default weighted value Corresponding relationship matched, add corresponding weighted value for the text feature, obtain weighting text feature；
Optionally, the default weighted value includes positive weights value and negative weighted value.
Optionally, submodule is weighted, comprising:
Matrix establishes unit, for the text feature and the m feature classifications according to the n Message-texts, builds Vertical dimension is the weighted feature matrix of (m × n), wherein n and m is the integer greater than 0.In embodiments of the present invention, weighted feature The text feature of all Message-texts can be gathered in a set, in order to reduce subsequent processing mistake by the foundation of matrix The calculation amount of journey.
Matrix weights unit, for each matrix element for the weighted feature matrix, as the spy of the text feature It levies classification and when the default feature categorical match, the corresponding default weighted value of the default feature classification is added to the square Array element；In embodiments of the present invention, operation is weighted to weighted feature matrix, can made subsequent according to weighted feature square Battle array, the priority degree value for carrying out Message-text calculates, so that it is determined that the priority of Message-text.
Constant adding unit, for when the feature classification of the text feature and the default feature classification mismatch, Preset constant is added to the matrix element.In embodiments of the present invention, operation is weighted to weighted feature matrix, can made Must be subsequent according to weighted feature matrix, the priority degree value for carrying out Message-text calculates, so that it is determined that Message-text is preferential Grade.
Computational submodule, for determining the priority degree of each Message-text according to the weighting text feature Value；
Optionally, computational submodule, comprising:
Computing unit is summed it up, calculating is summed up for each row in the n row data to the weighted feature matrix, obtains To the n priority degree values；
Classification submodule, for determining at least one from multiple Message-texts according to the priority degree value Target message text.In embodiments of the present invention, according to weighted feature matrix, the priority degree value of Message-text can be carried out It calculates, so that it is determined that the priority of Message-text.
The classification submodule, comprising:
First division unit, for that will be worth corresponding to maximum priority degree value in the n priority degree value Message-text, be determined as the target message text.In embodiments of the present invention, it according to weighted feature matrix, can carry out The priority degree value of Message-text calculates, so that it is determined that the priority of Message-text, realizes the sort operation to Message-text.
Optionally, classification submodule, comprising:
Sequencing unit, if for according to the weighting text feature, the priority of each of determining Message-text In degree value, there are multiple maximum priority degree values of value, then by the multiple Message-text according to the priority degree It is worth descending sequence to be arranged, obtains Message-text sequence.The embodiment of the present invention is by further pressing Message-text It is ranked up according to the size of priority degree value, realizes the mesh according to priority degree value size selection target Message-text 's.
Averaging unit is summed it up, is used for according to preset constant k, the priority described in the Message-text sequence message text The maximum one end of degree value starts, and chooses (1+k) a Message-text, and obtains and determine the average preferential of each Message-text Stage value Ma.The embodiment of the present invention by the further calculating to the average priority degree value of Message-text, realize from Priority degree is worth the purpose that further screening in equal multiple Message-texts has more the Message-text made a difference.
Second division unit is used for the second division unit, for that will be worth maximum in (1+k) a described Message-text Average priority degree value MaCorresponding Message-text is determined as the target message text.The embodiment of the present invention by into Calculating of one step to the average priority degree value of Message-text, realizes and is worth equal multiple Message-texts from priority degree Middle further screening has more the purpose for the Message-text made a difference.
Wherein, for a-th of Message-text in (1+k) a Message-text, a-th of Message-text is corresponding Average priority degree valueThe raIt is corresponding preferential for a-th of Message-text Stage value, the preset constant k are the integer greater than 0.
Second division unit, further includes:
Difference computation subunit, for determining (1+k) a described average priority degree value MaIn, adjacent is described average Priority degree value MaBetween difference；The embodiment of the present invention by further to the average priority degree value of Message-text it Between difference calculate, according to the difference judge the average priority degree values of multiple message in distribution with the presence or absence of abnormal, it is real The purpose that noise data is screened out from multiple Message-texts is showed.
Third divides subelement, in all differences, if being less than or equal to the difference of preset difference value threshold value Quantity be greater than or equal to preset quantity threshold value, then will be worth maximum average priority degree value MaCorresponding Message-text, It is determined as the target message text.The embodiment of the present invention passes through further between the average priority degree value of Message-text Difference calculate, judge that the average priority degree values of multiple message with the presence or absence of abnormal, is realized in distribution according to the difference Screen out from multiple Message-texts the purpose of noise data.
Optionally, determining module 602, comprising:
Weight adjusting submodule, for multiple maximum priority degree values of value if it exists, it is determined that multiple described It is worth the corresponding Message-text of maximum priority degree value, and the target that the text feature for reducing the Message-text is matched to Default weighted value.The embodiment of the present invention can achieve the mesh for optimizing the corresponding relationship between default feature classification and default weighted value , improve the subsequent precision that Message-text importance deterministic process is carried out according to the corresponding relationship.
Display module 603, for determining the priority degree of each Message-text according to the weighting text feature Value, and according to the priority degree value, at least one target message text is determined from multiple Message-texts.
In conclusion a kind of terminal device provided in an embodiment of the present invention, including, receive multiple Message-texts；According to more The text feature of a Message-text determines at least one target message text from multiple Message-texts；Displaying target message text This, the present invention utilizes the text spy of Message-text by the corresponding relationship established between default feature classification and default weighted value It levies corresponding feature classification to be matched with default feature classification, it is corresponding that the text feature matched is added default feature classification Default weighted value so that according to the text feature after weighting, the priority degree value for carrying out Message-text is calculated, so that it is determined that The priority of Message-text realizes the purpose classified to Message-text according to priority, since the present invention is according to message text This feature classification realizes the weighting to Message-text, and the priority degree value obtained according to weighting text feature, comes accurate Indicate Message-text significance level, to realize the classification of Message-text, solve based on semantic analysis to Message-text into The problem of classification results inaccuracy is classified and caused to row, improves the nicety of grading to Message-text.
Fig. 7 is the block diagram of the terminal device of another embodiment of the present invention.Terminal device 700 shown in Fig. 7 include: to A few processor 701, memory 702, at least one network interface 704, user interface 703 and camera 706.Terminal is set Various components in standby 700 are coupled by bus system 705.It is understood that bus system 705 is for realizing these components Between connection communication.Bus system 705 further includes power bus, control bus and state letter in addition to including data/address bus Number bus.But for the sake of clear explanation, various buses are all designated as bus system 705 in Fig. 7.
Wherein, user interface 703 may include display, keyboard or pointing device (for example, mouse, trace ball (trackball), touch-sensitive plate or flexible screen etc..
It is appreciated that the memory 702 in the embodiment of the present invention can be volatile memory or nonvolatile memory, It or may include both volatile and non-volatile memories.Wherein, nonvolatile memory can be read-only memory (Read- OnlyMemory, ROM), programmable read only memory (ProgrammableROM, PROM), the read-only storage of erasable programmable Device (ErasablePROM, EPROM), electrically erasable programmable read-only memory (ElectricallyEPROM, EEPROM) or Flash memory.Volatile memory can be random access memory (RandomAccessMemory, RAM), be used as external high speed Caching.By exemplary but be not restricted explanation, the RAM of many forms is available, such as static random access memory (StaticRAM, SRAM), dynamic random access memory (DynamicRAM, DRAM), Synchronous Dynamic Random Access Memory (SynchronousDRAM, SDRAM), double data speed synchronous dynamic RAM (DoubleDataRate SDRAM, DDRSDRAM), enhanced Synchronous Dynamic Random Access Memory (Enhanced SDRAM, ESDRAM), synchronous connect Connect dynamic random access memory (SynchlinkDRAM, SLDRAM) and direct rambus random access memory (DirectRambusRAM, DRRAM).The memory 702 of the system and method for description of the embodiment of the present invention is intended to include but unlimited In the memory of these and any other suitable type.
In some embodiments, memory 702 stores following element, executable modules or data structures, or Their subset of person or their superset: operating system 7021 and application program 7022.
Wherein, operating system 7021 include various system programs, such as ccf layer, core library layer, driving layer etc., are used for Realize various basic businesses and the hardware based task of processing.Application program 7022 includes various application programs, such as media Player (MediaPlayer), browser (Browser) etc., for realizing various applied business.Realize embodiment of the present invention side The program of method may be embodied in application program 7022.
In embodiments of the present invention, by the program or instruction of calling memory 702 to store, specifically, can be application The program or instruction stored in program 7022, processor 701 are used for: determining multiple Message-texts；Extract each Message-text Text feature；By the way that the corresponding relationship between the feature classification of text feature and default feature classification and default weighted value is carried out Matching adds corresponding weighted value for text feature, obtains weighting text feature；According to weighting text feature, determination each disappears The priority degree value of informative text, and according to priority degree value, Message-text is divided to corresponding priority class.
The method that the embodiments of the present invention disclose can be applied in processor 701, or be realized by processor 701. Processor 701 may be a kind of IC chip, the processing capacity with signal.During realization, the above method it is each Step can be completed by the integrated logic circuit of the hardware in processor 701 or the instruction of software form.Above-mentioned processing Device 701 can be general processor, digital signal processor (DigitalSignalProcessor, DSP), specific integrated circuit (ApplicationSpecificIntegratedCircuit, ASIC), ready-made programmable gate array (FieldProgrammableGateArray, FPGA) either other programmable logic device, discrete gate or transistor logic Device, discrete hardware components.It may be implemented or execute disclosed each method, step and the logical box in the embodiment of the present invention Figure.General processor can be microprocessor or the processor is also possible to any conventional processor etc..In conjunction with the present invention The step of method disclosed in embodiment, can be embodied directly in hardware decoding processor and execute completion, or use decoding processor In hardware and software module combination execute completion.Software module can be located at random access memory, and flash memory, read-only memory can In the storage medium of this fields such as program read-only memory or electrically erasable programmable memory, register maturation.The storage Medium is located at memory 702, and processor 701 reads the information in memory 702, and the step of the above method is completed in conjunction with its hardware Suddenly.
It is understood that the embodiment of the present invention description these embodiments can with hardware, software, firmware, middleware, Microcode or combinations thereof is realized.For hardware realization, processing unit be may be implemented in one or more specific integrated circuit (App LicationSpecificIntegratedCircuits, ASIC), digital signal processor (DigitalSignalProcessing, DSP), digital signal processing appts (DSPDevice, DSPD), programmable logic are set Standby (ProgrammableLogicDevice, PLD), field programmable gate array (Field-ProgrammableGateArray, FPGA), general processor, controller, microcontroller, microprocessor, other electronics lists for executing herein described function In member or combinations thereof.
For software implementations, can by execute the embodiment of the present invention described in function module (such as process, function etc.) come Realize technology described in the embodiment of the present invention.Software code is storable in memory and is executed by processor.Memory can With portion realizes in the processor or outside the processor.
Terminal device 700 can be realized each process that terminal device is realized in previous embodiment, to avoid repeating, here It repeats no more.
In the embodiment of the present invention, since the present invention receives multiple Message-texts；According to the text feature of multiple Message-texts, At least one target message text is determined from multiple Message-texts；Displaying target Message-text, the present invention can pass through message The text feature of text determines the target message text with higher significance level, so that mesh from multiple Message-texts Mark Message-text can be demonstrated, and achieved the purpose that carry out Message-text classification displaying, reduced important chat messages The probability being missed saves the browsing time of Message-text.
For above-mentioned apparatus embodiment, since it is basically similar to the method embodiment, so be described relatively simple, The relevent part can refer to the partial explaination of embodiments of method.
The embodiment of the present invention also provides a kind of terminal device, and in conjunction with Fig. 7, including processor 701, memory 702 is stored in On the memory and the computer program that can run on the processor, the computer program is by the processor 701 Each process of the processing method embodiment of above-mentioned Message-text is realized when execution, and can reach identical technical effect, to keep away Exempt to repeat, which is not described herein again.
The embodiment of the present invention also provides a kind of computer readable storage medium, and meter is stored on computer readable storage medium Calculation machine program, the computer program realize each mistake of the processing method embodiment of above-mentioned Message-text when being executed by processor Journey, and identical technical effect can be reached, to avoid repeating, which is not described herein again.Wherein, the computer-readable storage medium Matter, such as read-only memory (Read-Only Memory, abbreviation ROM), random access memory (Random Access Memory, abbreviation RAM), magnetic or disk etc..
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
It would have readily occurred to a person skilled in the art that: any combination application of above-mentioned each embodiment is all feasible, therefore Any combination between above-mentioned each embodiment is all embodiment of the present invention, but this specification exists as space is limited, This is not just detailed one by one.
The processing method of Message-text is not solid with any certain computer, virtual system or other equipment provided herein There is correlation.Various general-purpose systems can also be used together with teachings based herein.As described above, construction has this hair Structure required by the system of bright scheme is obvious.In addition, the present invention is also not directed to any particular programming language.It should Understand, can use various programming languages and realize summary of the invention described herein, and language-specific is done above Description is in order to disclose the best mode of carrying out the invention.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the present invention and help to understand one or more of the various inventive aspects, Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect Shield the present invention claims features more more than feature expressly recited in each claim.More precisely, such as right As claim reflects, inventive aspect is all features less than single embodiment disclosed above.Therefore, it then follows tool Thus claims of body embodiment are expressly incorporated in the specific embodiment, wherein each claim conduct itself Separate embodiments of the invention.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention Within the scope of and form different embodiments.For example, in detail in the claims, embodiment claimed it is one of any Can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice In the processing method of microprocessor or digital signal processor (DSP) to realize Message-text according to an embodiment of the present invention The some or all functions of some or all components.The present invention is also implemented as executing method as described herein Some or all device or device programs (for example, computer program and computer program product).Such reality Existing program of the invention can store on a computer-readable medium, or may be in the form of one or more signals. Such signal can be downloaded from an internet website to obtain, and perhaps be provided on the carrier signal or in any other forms It provides.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims, Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame Claim.

Claims (10)

1. a kind of processing method of Message-text is applied to terminal device, which is characterized in that the described method includes:
Receive multiple Message-texts；
According to the text feature of multiple Message-texts, at least one target message text is determined from multiple Message-texts This；
Show the target message text.
2. the method according to claim 1, wherein the text feature according to multiple Message-texts, The step of at least one target message text is determined from multiple Message-texts, comprising:
Corresponding relationship between the feature classification of the text feature and default feature classification and default weighted value is matched, Corresponding weighted value is added for the text feature, obtains weighting text feature；
According to the weighting text feature, the priority degree value of each Message-text is determined；
According to the priority degree value, at least one target message text is determined from multiple Message-texts.
3. according to the method described in claim 2, it is characterized in that, the feature classification by the text feature and default spy Corresponding relationship between sign classification and default weighted value is matched, and is added corresponding weighted value for the text feature, is obtained The step of weighting text feature, comprising:
According to the text feature and the m feature classifications of the n Message-texts, the weighting that dimension is (m × n) is established Eigenmatrix, wherein n and m is the integer greater than 0；
For each matrix element of the weighted feature matrix, when the feature classification and the default feature class of the text feature Not Pi Pei when, the corresponding default weighted value of the default feature classification is added to the matrix element；
When the feature classification of the text feature and the default feature classification mismatch, preset constant is added to the square Array element.
4. according to the method described in claim 2, it is characterized in that, described according to the priority degree value, from multiple described The step of at least one target message text is determined in Message-text, comprising:
If each of being determined in the priority degree value of the Message-text, there are multiple according to the weighting text feature Be worth maximum priority degree value, then by the multiple Message-text according to the priority degree be worth descending sequence into Row arrangement, obtains Message-text sequence；
According to preset constant k, since priority degree described in the Message-text sequence is worth maximum one end, (1+ is chosen K) a Message-text, and determine the average priority degree value M of each Message-texta；
In (1+k) a described Message-text, maximum average priority degree value M will be worthaCorresponding Message-text determines For the target message text；
Wherein, for a-th of Message-text in (1+k) a Message-text, a-th of Message-text is corresponding average Priority degree valueThe raFor the corresponding priority degree of a-th of Message-text Value, the preset constant k are the integer greater than 0.
5. a kind of terminal device, which is characterized in that the terminal device includes:
Receiving module, for receiving multiple Message-texts；
Determining module determines at least from multiple Message-texts for the text feature according to multiple Message-texts One target message text；
Display module, for determining the priority degree value of each Message-text, and root according to the weighting text feature According to the priority degree value, at least one target message text is determined from multiple Message-texts.
6. terminal device according to claim 5, which is characterized in that the determining module, comprising:
Submodule is weighted, for by pair between the feature classification of the text feature and default feature classification and default weighted value It should be related to and be matched, add corresponding weighted value for the text feature, obtain weighting text feature；
Computational submodule, for determining the priority degree value of each Message-text according to the weighting text feature；
Classification submodule, for determining at least one target from multiple Message-texts according to the priority degree value Message-text.
7. terminal device according to claim 6, which is characterized in that the weighting submodule, comprising:
Matrix establishes unit, for the text feature and the m feature classifications according to the n Message-texts, establishes dimension Degree is the weighted feature matrix of (m × n), wherein n and m is the integer greater than 0；
Matrix weights unit, for each matrix element for the weighted feature matrix, when the feature class of the text feature When not with the default feature categorical match, the corresponding default weighted value of the default feature classification is added to the matrix Member；
Constant adding unit will be pre- for when the feature classification of the text feature and the default feature classification mismatch If constant is added to the matrix element.
8. terminal device according to claim 6, which is characterized in that the classification submodule, further includes:
Sequencing unit, if for according to the weighting text feature, the priority degree of each of determining Message-text In value, there are the maximum priority degree values of multiple values, then by the multiple Message-text according to the priority degree value by Small sequence is arrived greatly to be arranged, and Message-text sequence is obtained；
Averaging unit is summed it up, is used for according to preset constant k, the priority degree described in the Message-text sequence message text It is worth maximum one end to start, chooses (1+k) a Message-text, and obtains the average priority journey for determining each Message-text Angle value Ma；
Second division unit, for maximum average priority degree value M will to be worth in (1+k) a described Message-textaInstitute is right The Message-text answered is determined as the target message text；
Wherein, for a-th of Message-text in (1+k) a Message-text, a-th of Message-text is corresponding average Priority degree valueThe raFor the corresponding priority degree of a-th of Message-text Value, the preset constant k are the integer greater than 0.
9. a kind of terminal device, which is characterized in that including processor, memory and be stored on the memory and can be described The computer program run on processor is realized when the computer program is executed by the processor as in Claims 1-4 The step of processing method of described in any item Message-texts.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium Program, the computer program realize the place of Message-text according to any one of claims 1 to 4 when being executed by processor The step of reason method.
CN201910393208.7A 2019-05-13 2019-05-13 Message text processing method and terminal equipment Active CN110225185B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910393208.7A CN110225185B (en) 2019-05-13 2019-05-13 Message text processing method and terminal equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910393208.7A CN110225185B (en) 2019-05-13 2019-05-13 Message text processing method and terminal equipment

Publications (2)

Publication Number Publication Date
CN110225185A true CN110225185A (en) 2019-09-10
CN110225185B CN110225185B (en) 2021-01-08

Family

ID=67820828

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910393208.7A Active CN110225185B (en) 2019-05-13 2019-05-13 Message text processing method and terminal equipment

Country Status (1)

Country Link
CN (1) CN110225185B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112364128A (en) * 2020-11-06 2021-02-12 北京乐学帮网络技术有限公司 Information processing method and device, computer equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2787714A3 (en) * 2013-04-04 2015-03-18 Samsung Electronics Co., Ltd. Apparatus and method for providing additional information by using caller phone number
US20170245125A1 (en) * 2016-02-18 2017-08-24 Vivint, Inc. Event triggered messaging
CN107426448A (en) * 2016-05-23 2017-12-01 上海神计信息系统工程有限公司 A kind of automatic calling allocation method being lined up based on dynamic priority
CN107835495A (en) * 2017-12-08 2018-03-23 维沃移动通信有限公司 A kind of message prompt method, device and mobile terminal
CN108337374A (en) * 2018-01-23 2018-07-27 维沃移动通信有限公司 A kind of message prompt method and mobile terminal
CN108574732A (en) * 2018-03-22 2018-09-25 平安科技（深圳）有限公司 A kind of PUSH message processing method, computer readable storage medium and terminal device
CN109274814A (en) * 2018-08-20 2019-01-25 维沃移动通信有限公司 A kind of message prompt method, device and terminal device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2787714A3 (en) * 2013-04-04 2015-03-18 Samsung Electronics Co., Ltd. Apparatus and method for providing additional information by using caller phone number
US20170245125A1 (en) * 2016-02-18 2017-08-24 Vivint, Inc. Event triggered messaging
CN107426448A (en) * 2016-05-23 2017-12-01 上海神计信息系统工程有限公司 A kind of automatic calling allocation method being lined up based on dynamic priority
CN107835495A (en) * 2017-12-08 2018-03-23 维沃移动通信有限公司 A kind of message prompt method, device and mobile terminal
CN108337374A (en) * 2018-01-23 2018-07-27 维沃移动通信有限公司 A kind of message prompt method and mobile terminal
CN108574732A (en) * 2018-03-22 2018-09-25 平安科技（深圳）有限公司 A kind of PUSH message processing method, computer readable storage medium and terminal device
CN109274814A (en) * 2018-08-20 2019-01-25 维沃移动通信有限公司 A kind of message prompt method, device and terminal device

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112364128A (en) * 2020-11-06 2021-02-12 北京乐学帮网络技术有限公司 Information processing method and device, computer equipment and storage medium
CN112364128B (en) * 2020-11-06 2024-05-24 北京乐学帮网络技术有限公司 Information processing method, device, computer equipment and storage medium

Also Published As

Publication number Publication date
CN110225185B (en) 2021-01-08

Similar Documents

Publication Publication Date Title
TWI777010B (en) Prediction of information conversion rate, information recommendation method and device
US9864586B2 (en) Code quality improvement
WO2021057250A1 (en) Commodity search query strategy generation method and apparatus
CN109656815B (en) Test statement writing method, device and medium with configuration file and electronic equipment
CN109783346A (en) Keyword-driven automatic testing method and device and terminal equipment
CN111160950A (en) Resource information processing and outputting method and device
CN104966190A (en) Network payment method and apparatus
CN108681564A (en) The determination method, apparatus and computer readable storage medium of keyword and answer
CN110362563A (en) The processing method and processing device of tables of data, storage medium, electronic device
WO2020003109A1 (en) Facet-based query refinement based on multiple query interpretations
CN111383651A (en) Voice noise reduction method and device and terminal equipment
CN106649110B (en) Software testing method and system
CN111475402A (en) Program function testing method and related device
CN111159040A (en) Test data generation method, device, equipment and storage medium
CN110225185A (en) A kind of processing method and terminal device of Message-text
CN109542785A (en) A kind of invalid bug determines method and apparatus
US20230385554A1 (en) Supervised machine learning for automated assistants
CN112162982A (en) Data query method, device, equipment and medium
CN105893614A (en) Information recommendation method and device and electronic equipment
CN111338958A (en) Parameter generation method and device of test case and terminal equipment
CN110955548A (en) Data processing method and device
CN114697127A (en) Service session risk processing method based on cloud computing and server
CN112184074A (en) Prompt message output method and device
CN113656549A (en) Content searching method of electronic book, electronic device and computer storage medium
CN113641823A (en) Text classification model training method, text classification device, text classification equipment and medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant