WO2021218158A1 - Harmony matching method and apparatus, electronic device, and computer readable medium - Google Patents

Abstract

A harmony matching method and apparatus, an electronic device, and a computer readable medium. The method comprises: dividing a melody segment into multiple target segments on the basis of a meter of the melody segment (S101); respectively calculating, on the basis of note sequences of the respective target segments, matching degrees between multiple preset chords and each target segment, and for each target segment, using a preset chord having the highest matching degree as a target chord of the corresponding target segment (S102); and generating, on the basis of target chords respectively corresponding to the multiple target segments, a harmony segment matching the melody segment (S103). The invention improves the accuracy of matching between harmony segments and melody segments, and improves the smoothness of the overall performance of harmony segments. In addition, the invention further relates to blockchain technology, and allows melody segments to be stored in a blockchain.

Description

Method, device, electronic equipment and computer readable medium for matching harmony

This application claims the priority of the Chinese patent application filed with the Chinese Patent Office on April 30, 2020, the application number is 202010364461.2, and the invention title is "Methods, devices, electronic equipment and computer-readable media for collocation of harmony", all of which The content is incorporated in this application by reference.

Technical field

This application relates to the field of computer technology. Specifically, this application relates to a method, a device, an electronic device, and a computer-readable medium for matching harmony.

Background technique

Harmony is a very important part in tonal music, and it is one of the basic means of music. Although a melody can be presented independently, the addition of harmony for accompaniment can increase the richness of the melody and make the sense of hearing fuller. In the analysis of western traditional music, harmony is a very important dimension.

In the prior art, the method of using the first note of each bar as the root note of the chord is generally used as the melody to match the corresponding harmony. The inventor of the present application has discovered that there are multiple possible harmony combinations for the same melody. When the unit of measure is one measure and the first note of each measure is used as the root note of the melody match harmony, its limitations are more limited. Large; and the harmony corresponding to a melody segment is closely related to the information of all the notes in the entire melody segment. The prior art cannot consider the correlation between the chords matched by adjacent bars in the melody and the information of all the notes between adjacent chords , Resulting in an abrupt harmony performance effect matched by the melody.

Summary of the invention

The content of the invention is provided in order to introduce concepts in a brief form, and these concepts will be described in detail in the following specific embodiments. The content of the invention is not intended to identify the key features or essential features of the technical solution required to be protected, nor is it intended to be used to limit the scope of the technical solution required to be protected.

In the first aspect of the present application, a method for matching harmony is provided, which includes: dividing the melody segment into multiple target segments based on the beat of the melody segment; respectively calculating multiple preset chords and chords based on the note sequence of each target segment The matching degree of each target segment, and for each target segment, the preset chord with the highest matching degree is used as the target chord of the corresponding target segment; based on the target chords corresponding to the multiple target segments, the Harmony clips with melody clips.

In a second aspect of the present application, a device for matching harmony is provided, including: a dividing module for dividing the melody segment into multiple target segments based on the beat of the melody segment; The note sequence calculates the matching degree between a plurality of preset chords and the respective target segments, and for each target segment, the preset chord with the highest matching degree is used as the target chord of the corresponding target segment; a generating module is used to generate The target chords respectively corresponding to the multiple target segments generate a harmony segment matched with the melody segment.

In a third aspect of the present application, an electronic device is provided, the electronic device includes: a memory and a processor; a computer program is stored in the memory; and the processor is configured to execute the following method when the computer program is running:

Dividing the melody segment into multiple target segments based on the beat of the melody segment;

Calculate the matching degree between a plurality of preset chords and each target segment based on the note sequence of each target segment, and for each target segment, use the preset chord with the highest matching degree as the target chord of the corresponding target segment;

Based on the target chords respectively corresponding to the multiple target segments, a harmony segment matched with the melody segment is generated.

In a fourth aspect of the present application, a computer-readable medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following method is implemented:

Dividing the melody segment into multiple target segments based on the beat of the melody segment;

Calculate the matching degree between a plurality of preset chords and each target segment based on the note sequence of each target segment, and for each target segment, use the preset chord with the highest matching degree as the target chord of the corresponding target segment;

Based on the target chords respectively corresponding to the multiple target segments, a harmony segment matched with the melody segment is generated.

The present application divides the melody segments based on the beats of the melody segments. Among the multiple target segments that are divided into, adjacent target segments are closely related; because the adjacent target segments are strongly related, it makes adjacent note sequences It also has strong relevance; when calculating the matching degree of multiple preset chords with each target segment based on the note sequence of each target segment, and using the preset chord with the highest matching degree as the target chord of the corresponding target segment, it is beneficial Fully consider the information of all the notes between the chords matched by the adjacent target segments, and the adjacent target chords corresponding to the adjacent target segments are strongly related. Generating harmony segments based on the target chords corresponding to multiple target segments is beneficial to improve the melody-based segments Match the accuracy of the harmony segment and the smoothness of the overall performance of the harmony segment.

Description of the drawings

With reference to the drawings and the following specific implementations, the above and other features, advantages, and aspects of the embodiments of the present application will become more apparent. Throughout the drawings, the same or similar reference signs indicate the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

FIG. 1 is a flowchart of a method for matching harmony provided by an embodiment of the application;

FIG. 2 is a flowchart of a method for matching harmony provided by an embodiment of the application;

FIG. 3 is a flowchart of a method for matching harmony provided by an embodiment of the application;

FIG. 4 is a flowchart of a method for matching harmony provided by an embodiment of the application;

FIG. 5 is a flowchart of a method for matching harmony provided by an embodiment of the application;

FIG. 6 is a flowchart of a method for matching harmony provided by an embodiment of the application;

FIG. 7 is a flowchart of a method for matching harmony provided by an embodiment of the application;

FIG. 8 is a schematic diagram of generating a harmony segment in the method for collocation harmony provided by an embodiment of the application; FIG.

FIG. 9 is a schematic structural diagram of a device for matching harmony provided by an embodiment of the application;

FIG. 10 is a schematic structural diagram of an electronic device provided by an embodiment of the application.

Detailed ways

Hereinafter, embodiments of the present application will be described in more detail with reference to the accompanying drawings. Although some embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided for Have a more thorough and complete understanding of this application. It should be understood that the drawings and embodiments of the present application are only used for exemplary purposes, and are not used to limit the protection scope of the present application.

It should be understood that the steps described in the method embodiments of the present application may be executed in a different order, and/or executed in parallel. In addition, method implementations may include additional steps and/or omit to perform the illustrated steps. The scope of this application is not limited in this respect.

The term "including" and its variations as used herein are open-ended includes, that is, "including but not limited to". The term "based on" is "based at least in part on." The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments." Related definitions of other terms will be given in the following description.

It should be noted that the “first”, “second” and other concepts mentioned in this application are only used to distinguish devices, modules, or units, and are not used to limit these devices, modules, or units to be different devices, modules, or Units are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

It should be noted that the modification of “a” and “a plurality of” mentioned in this application is illustrative and not restrictive, and those skilled in the art should understand that unless the context clearly indicates otherwise, it should be understood as “one or Multiple".

The technical solution of this application can be applied to the fields of artificial intelligence, smart city, blockchain and/or big data technology to perform harmony matching and realize smart life. Optionally, the data involved in this application, such as melody segments and/or harmony segments, can be stored in a database, or can be stored in a blockchain, such as distributed storage through a blockchain, which is not limited in this application.

The names of messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

In order to make the purpose, technical solutions, and advantages of the present application clearer, the implementation manners of the present application will be described in further detail below in conjunction with the accompanying drawings.

First, introduce and explain several terms involved in this application:

Melody segment: Melody is the primary element of music. It usually refers to an organized and rhythmic sequence formed by several musical tones through artistic conception. The melody fragment can be a certain part of the sequence, or it can be a complete sequence.

Beat: Beat is a unit of measuring rhythm. In music, a series of beats with a certain strength and weakness are repeated at regular intervals. Such as 2/4, 4/4, 3/4 beat and so on. The beat expresses the fixed unit time value and the organizational form of strength and weakness in the music.

Note sequence: Note is a symbol used to record notes of different lengths. Whole notes, half notes, quarter notes, eighth notes, and sixteenth notes are the most common notes. The note sequence refers to a sequence composed of multiple notes, which specifically includes note information and the order of each note name, where the note information includes the duration of the note.

Chord: Chord refers to a group of sounds with a certain interval relationship, that is, three or more tones are combined in the vertical direction according to the superimposed relationship of thirds or non-thirds, and they are called chords.

Harmony segment: Harmony refers to a sound combination composed of two or more different sounds sounded at the same time according to a certain rule. It includes chords and harmony progression, among which chords are the basic material of harmony, consisting of 3 or more different sounds, combined according to three-degree stacking or other methods at the same time. This is the longitudinal structure of harmony; harmony Progression refers to the sequential connection of chords, which is the horizontal structure of harmony. Harmony segment refers to a sequence formed by successively connecting multiple chords, and its length is generally the same as the melody segment.

The technical solution of the present application and how the technical solution of the present application solves the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

Please refer to FIG. 1, this application provides a method of matching harmony, which can be specifically executed by the electronic device of the embodiment of this application. This application includes:

S101 divides the melody segment into multiple target segments based on the beat of the melody segment;

S102, based on the note sequence of each target segment, respectively calculates the matching degree between a plurality of preset chords and the target segment, and for each target segment, the chord with the highest matching degree is used as the target chord of the corresponding target segment;

S103 generates a harmony segment matched with the melody segment based on the target chords respectively corresponding to the multiple target segments.

In step S101, the melody segment is divided into a plurality of target segments based on the beat of the melody segment. Specifically, the melody segment may be inputted locally by the user or obtained from a third-party application program, or inputted by the user in an existing storage. It is specified in multiple melody segments; the acquired melody segment is a MIDI file, which is a binary file, and each note of the melody segment is recorded as a number. The beat in the same melody segment is fixed, such as 4/4 beats. The melody segment can be divided into one target segment per measure based on the beat of the melody segment, or it can be divided into multiple target segments per measure. Multiple bars are divided into a target segment; a melody segment is divided into at least one target segment.

It should be emphasized that, in order to further ensure the privacy and security of the above melody segment, the above melody segment can also be stored in a node of a blockchain.

In step S102, based on the note sequence of each target segment, the matching degree between a plurality of preset chords and the target segment is calculated, and for each target segment, the chord with the highest matching degree is used as the target chord of the corresponding target segment , Specifically, the note sequence is composed of the notes in the target segment arranged in the order of performance; the preset chords include at least two, which can be adjusted according to actual matching requirements; different preset chords and target segments will have different collocations In this embodiment, the matching degree between the preset chord and the target segment is calculated based on the note sequence, specifically related to the note name corresponding to the note, and the matching degree obtained by matching multiple preset chords with each target segment The highest preset chord serves as the target chord corresponding to the corresponding target segment, and one target segment corresponds to one target chord. Among them, this embodiment uses the hidden Markov model combined with the Viterbi algorithm (HMM Viterbi algorithm) to calculate the matching degree between multiple preset chords and each target segment, and for each target segment, the preset with the highest matching degree is calculated The chord as the target chord of the corresponding target segment is specifically based on the HMM Viterbi algorithm to backtrack from the target segment sorted at the end of the melody segment to obtain the chord sequence with the greatest probability (consisting of the target chord corresponding to each target segment), namely The hidden state sequence.

In step S103, based on the target chords respectively corresponding to the multiple target segments, a harmony segment that matches the melody segment is generated. Specifically, the harmony segment is used to add when the melody segment is performed, so as to enrich the overall performance of the music. ; Harmony segment is formed by successively connecting multiple target chords (harmonization progress), wherein since each target chord corresponds to the beat of the melody segment, the harmony segment generated based on the multiple target chords has the same beat as the melody segment. Specifically, each target chord is sorted based on the performance order of the corresponding target segment in the melody segment, and one target segment corresponds to one target chord, and a harmony segment with the same performance form as the melody segment is generated.

The embodiment of the present application divides the melody segment based on the beat of the melody segment, and the adjacent target segments among the multiple target segments that are divided into are closely related; because the adjacent target segments are strongly related, it makes the adjacent target segments The note sequence also has a strong correlation; when calculating the matching degree of multiple preset chords with each target segment based on the note sequence of each target segment, and using the preset chord with the highest matching degree as the target chord of the corresponding target segment, It is helpful to fully consider the information of all the notes between the chords matched by the adjacent target segments, and the adjacent target chords corresponding to the adjacent target segments are strongly related. Generating harmony segments based on the target chords corresponding to multiple target segments is beneficial to improve the melody The accuracy of the segment matching the harmony segment, and the smoothness of the overall performance of the harmony segment.

In an embodiment, referring to FIG. 2, step S101 divides the melody segment into multiple target segments based on the beat of the melody segment, including:

S201 Determine a variable parameter based on the beat of the melody segment; wherein the variable parameter is a preset value or a chord density set by the user based on the beat of the melody segment;

S202 divides the melody segment into multiple target segments based on the variable parameter.

Specifically, the variable parameter (chords_per_bar) is the parameter that can be matched with chords in each measure of the melody segment. For example, a target segment of 4/4 beats of a measure has a total note length of 4 beats, and the maximum number of chords that can be matched is 4; When it is the default value, the variable parameter can be set to 1, that is, assuming that the beat of the melody segment is 4/4 beats, and the variable parameter is the minimum number of chords that can be matched, the melody segment is performed in a unit of 4 beats. Divide multiple notes into a target segment with a total length of 4 beats; when the variable parameter is a preset value, the variable parameter can also be set to a random value that can match the chord value interval, such as a 4/4 beat melody segment, The range of possible chord values is [1-4]. If the random value is 2, the melody segment is divided into a unit of 2 beats to form multiple target segments with a total length of 2 beats. Chord density refers to the number of chords matched in a target segment. For example, a target segment in 4/4 time. The chord density includes 1, 2, 3, and 4. When the chord density is 1, a target segment matches one chord. When the variable parameter is the chord density set by the user based on the beat of the melody segment, first determine the beat of the melody segment, assuming it is 4/4 beats, and the user sets the chord density to 2, then each measure will be divided into 2 segments. Unit, the melody segment is divided to form multiple target segments with a note length of 2 beats.

In one embodiment, the step S101 to divide the melody segment into multiple target segments based on the beat of the melody segment further includes:

Determine the note time value of each note in each bar based on the beat of the melody segment;

The melody segment is divided into multiple target segments based on the note duration.

Specifically, the note duration value of a whole note is 1, the note duration value of a half note is 1/2, and so on. In a melody segment in 4/4 time, if a whole note is included, it can match up to one chord; if it includes two half notes, it can match up to two chords.

In this embodiment, the standard for dividing the melody segment is a variable parameter, which can be set by the user based on the beat of the melody segment (in the harmony model, an interface is provided for the user to set the variable parameter) In the process of matching the harmony, the user can adjust the variable parameters (chord density) based on actual needs. For example, when the user is not familiar with the melody segment, lower the variable parameters, so that fewer chords are matched and the performance is reduced. Difficulty. Further, this embodiment divides the melody segment according to the variable parameters to form multiple target segments, which is beneficial to enrich the number of matched chords and strengthen the relevance of the chords matched by adjacent target segments; further, when the variable parameter is When the chord density is set by the user, based on the different needs of the user, the number of chords and the types of chords that need to be matched to divide the melody segment into multiple target segments are different, which is beneficial to strengthen the closeness of human-computer interaction and improve the user experience.

In one embodiment, referring to FIG. 3, step S102 calculates the matching degree between a plurality of preset chords and each target segment based on the note sequence of each target segment, and for each target segment, the highest matching degree is calculated The preset chord of as the target chord of the corresponding target segment, including:

S301 determines target parameters based on the note sequence of each target segment and multiple preset chords;

In S302, a Hidden Markov Model is used to calculate the matching degree of multiple preset chords with the respective target segments based on the target parameters, and the target chords corresponding to the respective target segments are obtained, and the target chords are corresponding to the corresponding target segments. The preset chord with the highest matching degree.

Specifically, through the Hidden Markov Model (HMM) combined with the Viterbi algorithm (Viterbi algorithm), a multi-selection and multi-step model is constructed to solve the optimal selection problem, and multiple preset chords and each target are calculated in sequence The matching degree of the segment collocation (log likelihood value). The pitch names (pitches_name_class) involved in this embodiment include: C, #C, D, #D, E, F, #F, G, #G, A, #A, B; preset chords (chords) Including a variety of chord types. In this embodiment, the chord types include: major, minor, augmented, diminished, major7, minor7, dominant7, half The minus triad is half-diminished. Due to the situation that some note compositions may not correspond to any chords, a no chord is added to the preset chords to indicate no chord collocation; through the collocation of each note name with multiple preset chords, a total of 97 (12*8+1) The possibility of chord candidates, that is, there are a total of 97 chord candidates. Specifically, the probability of each note name appears is 1/12; when the preset chord corresponds to a certain note name, the probability of each preset chord appears is 1/9. The above note names and preset chords can be adjusted based on actual conditions.

Among them, the target parameter is the calculation parameter of the hidden Markov model, which is determined by the note sequence of each target segment and multiple preset chords. The note sequence of the target segment includes note information and the order of each note name in the target segment, and the note information includes the length of time each note name appears in the corresponding target segment. In this embodiment, a set of target parameters is jointly determined based on the note sequence of each target segment and multiple preset chords.

Among them, the hidden Markov model can infer the matching degree of multiple preset chords with each target segment based on the target parameters through the Viterbi algorithm, and obtain the corresponding target chords of each target segment, and output the multiple target chords in sequence The target chord sequence. The target chord is the preset chord with the highest degree of matching with the corresponding target segment.

In one embodiment, referring to FIG. 4, step S301 determines target parameters based on the note sequence of each target segment and a plurality of preset chords, including:

S401, based on the note sequence of each target segment, determine the collocation probability of a plurality of preset chords and each target segment;

S402, based on the interval relationship between the multiple key signatures in the melody segment and each preset chord, determine the probability distribution of the multiple preset chords in each key signature;

S403 calculates the state transition probability of a combination of multiple preset chords and each key signature based on the preset change probability; wherein, the preset change probability includes the key signature change probability and the preset chord change probability;

S404 generates target parameters based on the note sequence, collocation probability, probability distribution, and state transition probability of each target segment.

In step S401, determining the collocation probability of a plurality of preset chords and each target segment based on the note sequence of each target segment. Specifically, according to the note sequence of each target segment, determine the number of 97 chord candidates in the corresponding target segment. Probability. Among them, the note sequence includes note information.

In step S402, the probability distribution of multiple preset chords in each key signature is determined based on the interval relationship between the multiple key signatures in the melody segment and each preset chord. The relationship between pitches, that is, the distance between two tones in pitch, is called degree. Each key signature corresponds to each note name involved in the melody segment. According to the interval relationship of the major scale under different key signatures and the interval relationship of each preset chord composition, calculate each preset chord composition tone in and out of the key, and get the preset chord under each key signature Probability distribution (key_chord_distribution). Among them, the external tone of the tonal can be considered as a certain key signature key, the component tone of the preset chord is not the natural tone under the key. The preset chords are called the external chord of this key. For example, in the key of C major, the D major triad D#F A is the outer key, and the D minor triad D F A is the inner key. Based on the above background, in this embodiment, there are multiple key signatures, such as C, D, E, etc. Although they correspond to the same melody segment, the melody segment can be transformed by transposing the chord when matching the harmony segment. The overall style, therefore, needs to consider the probability distribution of collocation with multiple preset chords under different key signatures. When the key signature is C major, if the preset chord only includes D major and D minor, then 50% of the C major down is the probability distribution within the key, and 50% is the probability distribution outside the key; In the example, the probability distribution of multiple preset chords under each key signature can also be calculated according to the condition of minor tonality, polytonality, and the accompaniment effect of the collocation of out-of-tune chords and melody.

In step S403, the state transition probability of a combination of multiple preset chords and each key signature is calculated based on the preset change probability; wherein, the preset change probability includes the key signature change probability and the preset chord change probability, specifically, each tone The key signature corresponding to the name includes C,#C,D,#D,E,F,#F,G,#G,A,#A,B. In an embodiment, the note name may include all note names in music theory knowledge. Among them, the number of combinations of a key signature and multiple preset chords is determined by the number of preset chords, and the combination of a certain key signature and a certain preset chord is characterized as a combination of key signature and preset chord. In this embodiment Under the multiple note names and multiple preset chords involved, there are a total of 1164 (97*12) key-chord combinations (key-chord). The state transition probability represents the probability of each key signature and multiple preset chords conversion. For example, in the C major key, the probability of the preset chords being converted from 1, 3, and 5 to #1, 3, and #5. In the HMM Viterbi algorithm solution method, it is specifically characterized as a matrix corresponding to the state transition probability of all key signatures and preset chord combinations. Specifically, the preset change probability includes a key signature change probability of 0.001, key_change_prob (=0.001), and a preset chord change probability of 0.5, chord_change_prob (=0.5). The preset variation probability matches the multiple note names and multiple preset chords involved in this embodiment after multiple tests, and can be adapted and adjusted under actual conditions. The following formulas (1) and (2) can be used to calculate the state transition probability of each key signature and multiple preset chord combinations.

In formula (1), γ is the probability that the preset chord chord changes, ρ is the probability that the key signature key changes, and f(h _t ) is the probability key_chord_distribution of the preset chord and key signature combination in a certain key signature key The binomial distribution of multiple preset chord pitches under the initial setting γ=0.5, ρ=0.001.

In step S404, target parameters are generated based on the note sequence, collocation probability, probability distribution, and state transition probability of each target segment, specifically, the visible state sequence is determined based on the note sequence of each target segment; for example, a target segment of 4/4 beat The note sequence of A|4 3 5 2| is 4-3-5-2, and the note sequence of target segment B|1 4 6 7| is 1-4-6-7, and the visible state sequence is 4-3- 5-2-1-4-6-7. In the HMM Viterbi algorithm, the visible state sequence is in a known observation state, and the visible state sequence corresponds to the sequence of notes in the melody segment. Specifically, the visible state sequence derived from the observable melody segment, the collocation probability of multiple preset chords and each target segment, the probability distribution of multiple preset chords in each key signature, and multiple preset chords and each The state transition probability of the key signature combination generates the target parameter, and the process of generating the target parameter is the training process of the hidden Markov model.

In one embodiment, referring to FIG. 5, step S401 determines the matching probabilities of multiple preset chords and each target segment based on the note sequence of each target segment, including:

S501 Determine the duration vector of each note name in each target segment based on the note sequence of each target segment;

S502, based on the duration vector, determines the collocation probability of a plurality of preset chords and the respective target segments.

In step S501, determining the duration vector of each note name in each target segment based on the note sequence of each target segment. Specifically, the note sequence includes determining the duration information of each note name appearing in each target segment, which may be based on the duration. The information determines the duration vector, and the duration vector represents the length and direction of each sound name corresponding to the middle sound of each target segment. In one embodiment, the time length vector (note_pitch_vector) of each note name in each target segment is determined, such as 4/4 shot target segment A: |5-2 3|, then G appears in target segment A for 2 Beat, the duration of D appearing in target segment A is 1 beat, and the duration of appearing E in target segment A is 1 beat; the corresponding duration vector can be determined based on the duration information; among them, the duration of appearance is related to the time value.

In step S502, determining the collocation probability of multiple preset chords and each target segment based on the duration vector. Specifically, assume that the target segment A is shot in 4/4: |5-2 3|, where G is in the target segment A The appearance duration is 2 beats, the appearance duration of D in the target segment A is 1 beat, and the appearance duration of E in the target segment A is 1 beat. Then, the probability of 97 chord candidates in the target segment A can be determined according to the note composition of the target segment A, that is, the chords containing the note names G, D, and E are more likely to be considered as the chord collocation of the target segment A. Among them, assuming that multiple preset chords include DFA, CEG, CbEG, and BDF, in the target segment A, the matching probability of the preset chord DFA is 0.5, the matching probability of CEG is 0.75, the matching probability of CbEG is 0.75, and the matching probability of BDF is 0.5. The matching probability is 0.25. Through the implementation of this step, it is possible to know the probability (chord_frame_loglike) of each chord candidate (97 types in total) and each target segment.

In an implementation, referring to FIG. 6, step S302 respectively calculates the matching degree between a plurality of preset chords and the respective target segments based on the target parameters, and obtains the target chords corresponding to the respective target segments, including:

S601, based on the target parameters, respectively calculate the matching degree between a plurality of preset chords and the target segment sorted at the top of the melody segment;

S602 If the currently calculated target segment is sorted after the first of the melody segment, it is determined that the currently calculated target segment is the first target segment, and the step of calculating the matching degree between a plurality of preset chords and the first target segment is performed: Target parameters, and the matching degree between multiple preset chords and the previous target segment, respectively calculating the matching degrees between the multiple preset chords and the first target segment, and sorting the next target after the first target segment A segment as a first target segment; wherein the preamble target segment is a previous target segment sorted before the first target segment in the melody segment;

S603 re-execute the step of calculating the matching degree between the multiple preset chords and the first target segment, until the calculation of the matching degree between the multiple preset chords and the respective target segment is completed;

S604 Backward from the target segment sorted at the end of the melody segment to determine the target chord corresponding to each target segment.

Specifically, according to the Viterbi algorithm in combination with the target parameters, for the ordering of each target segment in the melody segment, the degree of matching between a plurality of preset chords and each target segment is sequentially calculated, and the target chord corresponding to each target segment is obtained. , The target chord is the preset chord with the highest degree of matching with the corresponding target segment, which is specifically the prediction process of the hidden Markov model.

In step S601, the matching degree between a plurality of preset chords and the target segment sorted at the top of the melody segment is calculated separately based on the target parameter. Specifically, the calculation of the matching degree starts with the target segment sorted at the top of the melody segment, and combines The target parameters respectively calculate the matching degree of multiple preset chords with the target segment.

In step S602, if the currently calculated target segment is ranked first in the melody segment, it is determined that the currently calculated target segment is the first target segment, and the step of calculating the matching degree between a plurality of preset chords and the first target segment is performed: The target parameter and the matching degree between the multiple preset chords and the pre-order target segment are calculated respectively, and the matching degree between the multiple preset chords and the first target segment is calculated, and the sequence is sorted after the first target segment. A target segment as the first target segment; wherein the preamble target segment is the previous target segment sorted before the first target segment in the melody segment, specifically, the calculation of the matching degree is in progress When it is sorted after the first position of the melody segment, combine the target segment and the matching degree of multiple preset chords with the previous target segment, respectively calculate the matching degree of multiple preset chords with the target segment sorted after the first position of the melody segment .

In step S603, the step of calculating the matching degree between the multiple preset chords and the first target segment is re-executed, until the matching degree calculation between the multiple preset chords and the respective target segment is completed, specifically, in the calculation process of the matching degree , Obtain each target segment sorted after the first position of the melody segment in order, combine the target segment and the matching degree of multiple preset chords with the previous target segment, calculate the multiple preset chords and sort them after the first position of the melody segment. The matching degree of each target segment.

Based on steps S601, S602, S603, S604, for example, Example 1: The melody segment is divided into 4 target segments. Based on the sort position in the melody segment, the sequence composed of the 4 target segments is: D1-D2-D3- D4; In the step of calculating the matching degree, the first step is to obtain the target segment D1, and the target parameters are combined to calculate the matching degree of multiple preset chords with the target segment D1; the second step is to obtain the target segment D2, combining the target parameters, And the matching degree between multiple preset chords and the target segment D1, respectively calculate the matching degree between multiple preset chords and the target segment D2; the third step, obtain the target segment D3, combine the target parameters, and multiple preset chords and targets The matching degree of segment D2 is calculated separately for the matching degree of multiple preset chords and the target segment D3; the fourth step is to obtain the target segment D4, combining the target parameters and the matching degree of multiple preset chords with the target segment D3, respectively The degree of matching between multiple preset chords and the target segment D4; since then, the calculation of the degree of matching between multiple preset chords and the 4 target segments has been completed. In the backtracking step, the first step is to obtain the target segment D4, and the target chord H4 of the target segment D4 is determined; the second step is to obtain the target segment D3, and the target chord H3 of the target segment D3 is determined; the third step is to obtain the target segment D2 , Determine the target chord H2 of the target segment D2; the fourth step, obtain the target segment D1, determine the target chord H1 of the target segment D1; since then, the step of backtracking is completed. After the step of backtracking is completed, based on the target chord H1, H2, The sequence of H3 and H4 can form the target chord sequence. It can be seen from the above example that in the present embodiment, in the calculation of the matching degree between multiple preset chords and each target segment, the obtained matching degree is not only calculated for a single target segment, it comprehensively considers multiple preset chords. The matching degree with the previous target segment, and the matching degree between the target segment sorted in other positions of the melody segment and multiple preset chords has nothing to do. This improves the relevance of the target chords matched between adjacent segments and also improves The overall performance smoothness of the harmony segment generated by the target chords corresponding to the multiple target segments.

Specifically, when the model calculates the matching degree based on the target parameters, the matching degree between multiple preset chords and each target segment is the multiple pairs of each target segment under all key signatures and preset chord combinations (that is, 1164 combinations). Log-likelihood (log-likelihood), the log-likelihood is calculated by the Viterbi algorithm based on the target parameters. When multiple target segments are spliced in the order of division of the melody segment, the degree of matching of the target segment sorted at the top of the melody segment with multiple preset chords is calculated to obtain multiple combinations of the target segment under all key signatures and preset chords. Log likelihood value; each target segment sorted after the first place of the melody segment is based on the matrix of the state transition probability of the combination of the key signature and the preset chord, and combined with the relevant information of the previous target segment (multiple preset chords and pre-targets Segment matching degree), and calculate the multiple log-likelihood values of each target segment sorted after the first of the melody segment under all key signatures and preset chord combinations. The final model corresponds to how much each target segment will be stored. A matrix (path_matrix) of key signatures and preset chord combinations corresponding to log likelihood values (path_matrix), which stores the matching degrees of each target segment with multiple preset chords, and the corresponding key signatures and preset chord combinations; that is, through The HMM Viterbi algorithm saves the matching degree of each target segment to the currently calculated target segment and the current preset chord in the calculation of the matching degree of each target segment with all preset chords (log-likelihood) Value), and when the currently calculated target segment has the highest matching degree with the current preset chord, each pre-order target segment corresponds to the preset chord with the highest matching degree. Furthermore, the model determines the target chords corresponding to each target fragment by tracing back from the target fragments sorted at the end of the melody fragment, and outputs a target chord sequence composed of multiple target chords; among them, the target chord is corresponding to The preset chord with the highest matching degree of the target segment.

In this embodiment, by using the HMM Viterbi algorithm, the hidden state sequence (target chord sequence) is inferred based on the observable visible state sequence (melody segment) and state transition probability; specifically, the following 5 are included step:

(1) After dividing the melody segment into multiple target segments, the note information of each target segment (frame) is counted to obtain the time length vector (note_pitch_vector) containing the appearance of each note name in each target segment;

(2) According to the duration vector, determine the collocation probability (chord_frame_loglike) of multiple preset chords corresponding to various chord candidates under each note name definition and each target segment.

(3) According to the interval relationship of the major scale under different key signatures and the interval relationship of each preset chord composition, calculate the situation of each preset chord composition in and out of the key, and obtain each preset under each key signature. Let the probability distribution of the chord.

(4) Based on the preset change probability, calculate the state transition probability of each key signature and multiple preset chord combinations according to the above formula (1).

Hidden Markov model is used to calculate the matching degree of each target segment with multiple preset chords based on the visible state sequence, collocation probability, probability distribution and state transition probability through the Viterbi algorithm. For each target segment, the highest matching degree is calculated. The preset chord is used as the target chord of the corresponding target segment, and a target chord sequence (consisting of multiple target chords in sequence) that is composed of each target chord and has the greatest probability of matching with the melody segment is obtained. Specifically, the degree of matching between a plurality of preset chords and the target segment sorted at the top of the melody segment is calculated based on the target parameters; if the currently calculated target segment is sorted after the top of the melody segment, it is determined that the currently calculated The target segment is the first target segment, and the step of calculating the matching degree between a plurality of preset chords and the first target segment is performed: based on the target parameter and the matching degree between the plurality of preset chords and the pre-order target segment, calculating the matching degree respectively The degree of matching between a preset chord and the first target segment will be the next target segment sorted after the first target segment as the first target segment; wherein, the preamble target segment is in the melody The previous target segment sorted before the first target segment in the segments (that is, the target segment sorted one digit before the first target segment); re-execute the step of calculating the matching degree between a plurality of preset chords and the first target segment , Until the matching degree calculation between multiple preset chords and each target segment is completed; in the matching degree calculation process, the model stores a matrix (path_matrix) of the key signature with the highest matching degree in each target segment and the preset chord combination; And self-sort the target segment at the end of the melody segment to go back and get the path with the highest matching degree (the target chord sequence with the highest matching degree corresponding to the overall melody segment).

In an embodiment, obtaining the target chords corresponding to the respective target segments in step S302 includes:

Traverse each target segment, and add the same mark to the target segments with the same note sequence;

Backtracking from the last-ordered target segment, the chord with the highest matching degree is used as the target chord. If the current backtracking target segment has the same identifier as the backtracked target segment, then the target chord corresponding to the backtracked target segment is used as the current backtracking target segment The target chord.

Specifically, in this embodiment, by traversing each target segment, the target segments with the same note sequence are added with the same identifier. When the later model backtracks to determine the target chords corresponding to each target segment, if the current backtracked target segment and the backtracked target segment have the same Mark, the target chord corresponding to the backtracked target segment is taken as the target chord of the current backtracked target segment, which reduces the amount of backtracking calculations and effectively improves the efficiency of the model.

In an embodiment, referring to FIG. 7, step S103 generates a harmony segment matched with the melody segment based on the target chords respectively corresponding to the multiple target segments, including:

In S701, it is determined that a measure in the melody segment is divided into at least two or more target segments;

In S702, among the target chords respectively corresponding to at least two or more target segments that constitute one measure of the melody segment, merge the timing values of the same and adjacent target chords;

S703 generates a harmony segment matched with the melody segment based on the target chord after the combined time value.

In step S701, it is determined that one measure in the melody segment is divided into at least two or more target segments. Specifically, when dividing the melody segment, one measure may not necessarily be divided into one target segment, and it is possible to divide one measure. There are two or more target segments; since one target segment corresponds to one target chord, when a measure of the melody segment is divided into two or more target segments, each measure will include two or more target chords.

In step S702, in the target chords corresponding to at least two or more target segments that constitute one measure of the melody segment, the timings of the same and adjacent target chords are merged. Specifically, if one of the melody segments is The bar includes two or more target chords. If there are the same and adjacent target chords, the time values of the two are merged, and after the merge, the first target chord is left; when one measure of the melody segment is divided into four When there are two target segments, the four target segments included in each measure correspond to four target chords. If the four target chords are the same and adjacent to each other, their time values will be combined, such as: a measure includes four identical targets For chords, four identical target chord progression time values are merged, and after the merging time values, the first target chord sequence remains after the merging; The smoothness of the harmony segment generated by the target chord.

In step S703, based on the target chords after merging the timing value, generating a harmony segment matched with the melody segment, specifically, the target chord after merging the timing value still corresponds to the sorted position of the target segment in the melody segment, forming a merge For the target chord sequence after the time value, the performance form of the corresponding melody segment of the target chord sequence after the combined time value is generated to generate a harmony segment. For example, based on the beat of the melody segment, the target chord sequence after the time value is combined to generate the corresponding harmony Fragment.

In this embodiment, if the melody segment has only one target segment per measure, there is no need to merge the timing of the target chord; or each melody segment includes two or more target segments, but the two or more targets If the target chords corresponding to the segments are not the same or not adjacent, there is no need to merge the timing values of the target chords.

According to the method provided by the above-mentioned embodiment, in a system with harmony collocation, when the melody segment input by the user is obtained, the harmony segment corresponding to the melody segment can be obtained based on the above-mentioned method of collocation harmony, and then the file is edited On the track of, the track corresponding to the input melody segment is added to the track of the harmony segment, as shown in Figure 8, to obtain a result file based on the melody and harmony, and then output it to the user.

Please refer to FIG. 9, which is a schematic structural diagram of a harmony-matching device provided by an embodiment of the present application. The harmony-matching device 900 of the embodiment of the present application may include:

The dividing module 901 is configured to divide the melody segment into multiple target segments based on the beat of the melody segment;

The matching module 902 is configured to calculate the matching degree between a plurality of preset chords and each target segment based on the note sequence of each target segment, and for each target segment, use the preset chord with the highest matching degree as the corresponding target The target chord of the segment;

The generating module 903 is configured to generate a harmony segment matched with the melody segment based on the target chords respectively corresponding to the multiple target segments.

In an embodiment, the dividing module 901 includes: a determining unit for determining a variable parameter based on the beat of the melody segment; wherein the variable parameter is a preset value or a user based on the beat setting of the melody segment The chord density of; a dividing unit for dividing the melody segment into multiple target segments based on the variable parameter.

In an embodiment, the matching module includes: a determining unit, configured to determine target parameters based on the note sequence of each target segment and a plurality of preset chords; and the matching unit, configured to adopt a hidden Markov model based on the target parameters The degree of matching between a plurality of preset chords and the respective target segments is calculated respectively, and the target chords corresponding to the respective target segments are obtained, and the target chord is the preset chord with the highest degree of matching with the corresponding target segment.

In an embodiment, the determining unit includes: a first subunit, configured to determine the collocation probability of a plurality of preset chords and the respective target segment based on the note sequence of each target segment; and a second subunit, configured to The interval relationship between the multiple key signatures in the melody segment and each preset chord determines the probability distribution of the multiple preset chords in each key signature; the third subunit is used to calculate multiple presets based on the preset change probability Set the state transition probability of the combination of a chord and each key signature; wherein, the preset change probability includes the key signature change probability and the preset chord change probability; the fourth subunit is used for the note sequence and collocation based on each target segment Probability, probability distribution and state transition probability generate target parameters.

In an embodiment, the first subunit is further configured to determine the duration vector of each note name in each target segment based on the note sequence of each target segment; determine multiple preset chords and chords based on the duration vector The collocation probability of each target segment.

In an embodiment, the matching unit includes: a first matching subunit, configured to calculate the matching degree between a plurality of preset chords and the target segment ranked first in the melody segment based on the target parameter; and a second matching The subunit is used to determine that the currently calculated target segment is the first target segment if the currently calculated target segment is sorted after the first of the melody segment, and execute the step of calculating the matching degree between a plurality of preset chords and the first target segment : Based on the target parameter and the matching degree between the multiple preset chords and the pre-order target segment, respectively calculate the matching degree between the multiple preset chords and the first target segment, and sort them after the first target segment The next target segment of, as the first target segment; wherein, the preamble target segment is the previous target segment sorted before the first target segment in the melody segment; the third matching subunit is used for Re-execute the step of calculating the matching degree between the multiple preset chords and the first target segment until the calculation of the matching degree between the multiple preset chords and the respective target segment is completed; the backtracking subunit is used for self-sorting in the melody segment The last target segment goes backward to determine the target chord corresponding to each target segment.

In an embodiment, the generating module 903 includes: a target determining unit, configured to determine that a measure in the melody segment is divided into at least two or more target segments; a merging unit, configured to compose the melody Among the target chords corresponding to at least two or more target segments in one measure of the segment, the timing values of the same and adjacent target chords are merged; the generating unit is used to generate and the said chords based on the merged timing values of the target chords. Harmony clips with melody clips.

The device with harmony in the embodiments of this application can execute a method of harmony with the method provided in the embodiments of this application, and its implementation principle is similar. Each module in the device with harmony in each embodiment of this application The actions performed correspond to the steps in the method for matching harmony in each embodiment of the present application. For the detailed function description of each module of the device with harmony, please refer to the corresponding combination and harmony shown in the preceding text. The description in the sound method will not be repeated here.

10, which shows a schematic structural diagram of an electronic device (such as a mobile terminal) 600 suitable for implementing the embodiments of the present application. The mobile terminal in the embodiment of the present application may include, but is not limited to, a device such as a computer. The electronic device shown in FIG. 10 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present application.

The electronic device includes a memory and a processor. The processor here may be referred to as the processing device 601 below, and the memory may include a read-only memory (ROM) 602, a random access memory (RAM) 603, and a storage device 608 below. At least one item of, as follows:

As shown in FIG. 10, the electronic device 600 may include a processing device (such as a central processing unit, a graphics processor, etc.) 601, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 602 or from a storage device 608. The program in the memory (RAM) 603 executes various appropriate actions and processing. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to the bus 604.

Generally, the following devices can be connected to the I/O interface 605: including input devices 606 such as touch screens, touch pads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; including, for example, liquid crystal displays (LCD), speakers, vibration An output device 607 such as a device; a storage device 608 such as a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to perform wireless or wired communication with other devices to exchange data. Although FIG. 10 shows an electronic device 600 having various devices, it should be understood that it is not required to implement or have all of the illustrated devices. It may be implemented alternatively or provided with more or fewer devices.

In particular, according to the embodiments of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments of the present application include a computer program product, which includes a computer program carried on a non-transitory computer readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, it executes the above-mentioned functions defined in the method of the embodiment of the present application.

The embodiments of the present application also provide a computer-readable (storage) medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method in the above embodiments are realized, or when the computer program is executed by the processor, the steps of the method in the above embodiments are realized. The function of each module/unit of the device in the above embodiment will not be repeated here. Optionally, the media involved in this application, such as computer-readable media, may be non-volatile or volatile.

It should be noted that the above-mentioned computer-readable medium in the present application may be a computer-readable signal medium or a computer-readable medium or any combination of the two. The computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable Read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this application, the computer-readable medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device. In this application, the computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable medium, and the computer-readable signal medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.

In some embodiments, the client and server can communicate with any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium. Communication (e.g., communication network) interconnects. Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (for example, the Internet), and end-to-end networks (for example, ad hoc end-to-end networks), as well as any currently known or future research and development network of.

The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.

The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device is caused to perform the following steps: divide the melody segment into multiple targets based on the beat of the melody segment Segment; calculate the matching degree of multiple preset chords with the target segment based on the note sequence of each target segment, and for each target segment, use the preset chord with the highest matching degree as the target chord of the corresponding target segment ; Generate a harmony segment matched with the melody segment based on the target chords respectively corresponding to the multiple target segments.

The computer program code used to perform the operations of the present application can be written in one or more programming languages or a combination thereof. The above-mentioned programming languages include but are not limited to object-oriented programming languages—such as Java, Smalltalk, C++, etc. Including conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).

The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation of the system architecture, functions, and operations of the system, method, and computer program product according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logic function. Executable instructions. It should also be noted that, in some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown one after another can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.

The modules or units involved in the embodiments described in this application can be implemented in software or hardware. Wherein, the name of the module or unit does not constitute a limitation on the unit itself under certain circumstances. For example, the generating module can also be described as "generating the melody segment based on the target chords corresponding to the multiple target segments. Harmony clips with matching modules".

The functions described above in this document may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logical device (CPLD) and so on.

The blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information for verification. The validity of the information (anti-counterfeiting) and the generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

In the context of the present application, a machine-readable medium may be a tangible medium, which may contain or store a program for use by the instruction execution system, apparatus, or device or in combination with the instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.

The above description is only a preferred embodiment of the present application and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in this application is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover the above technical features or technical solutions without departing from the above disclosed concept. Other technical solutions formed by arbitrarily combining the equivalent features. For example, the above-mentioned features and the technical features disclosed in this application (but not limited to) with similar functions are mutually replaced to form a technical solution.

In addition, although the operations are depicted in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present application. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable subcombination. Although the subject matter has been described in language specific to structural features and/or logical actions of the method, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely exemplary forms of implementing the claims.

Claims (20)

1. A method of matching harmony, which includes:

   Dividing the melody segment into multiple target segments based on the beat of the melody segment;

   Calculate the matching degree between a plurality of preset chords and each target segment based on the note sequence of each target segment, and for each target segment, use the preset chord with the highest matching degree as the target chord of the corresponding target segment;

   Based on the target chords respectively corresponding to the multiple target segments, a harmony segment matched with the melody segment is generated.
2. The method according to claim 1, wherein the dividing the melody segment into a plurality of target segments based on the beat of the melody segment comprises:

   Determining a variable parameter based on the beat of the melody segment; wherein the variable parameter is a preset value or a chord density set by the user based on the beat of the melody segment;

   The melody segment is divided into a plurality of target segments based on the variable parameter.
3. The method according to claim 1, wherein the matching degree between a plurality of preset chords and each target segment is calculated based on the note sequence of each target segment, and for each target segment, the matching degree is the highest The preset chord of as the target chord of the corresponding target segment, including:

   Determine the target parameters based on the note sequence of each target segment and multiple preset chords;

   The Hidden Markov Model is used to calculate the matching degree between multiple preset chords and the respective target segments based on the target parameters, and the target chords corresponding to the respective target segments are obtained, and the target chords are matched with the corresponding target segments The preset chord with the highest degree.
4. The method according to claim 3, wherein the determining the target parameter based on the note sequence of each target segment and a plurality of preset chords comprises:

   Determining the collocation probabilities of multiple preset chords and each target segment based on the note sequence of each target segment;

   Determining the probability distribution of the multiple preset chords in each key signature based on the interval relationship between the multiple key signatures in the melody segment and each preset chord;

   Calculate the state transition probability of a combination of multiple preset chords and each key signature based on the preset change probability; wherein, the preset change probability includes the key signature change probability and the preset chord change probability;

   The target parameter is generated based on the note sequence, collocation probability, probability distribution, and state transition probability of each target segment.
5. The method according to claim 4, wherein the determining the collocation probability of a plurality of preset chords and the respective target fragments based on the note sequence of each target fragment comprises:

   Determining the duration vector of each note name in each target segment based on the note sequence of each target segment;

   The collocation probabilities of a plurality of preset chords and the respective target segments are determined based on the duration vector.
6. The method according to claim 3, wherein the calculating the matching degree between a plurality of preset chords and the respective target segments based on the target parameters, to obtain the target chords corresponding to the respective target segments, comprises:

   Respectively calculating the matching degree between a plurality of preset chords and the target segment ranked first in the melody segment based on the target parameter;

   If the currently calculated target segment is sorted after the first of the melody segment, it is determined that the currently calculated target segment is the first target segment, and the step of calculating the matching degree between a plurality of preset chords and the first target segment is performed: based on the target Parameters, and the matching degree between multiple preset chords and the previous target segment, respectively calculating the matching degree between multiple preset chords and the first target segment, and sorting the next target segment after the first target segment , As the first target segment; wherein the preamble target segment is the previous target segment sorted before the first target segment in the melody segment;

   Re-execute the step of calculating the matching degree between the multiple preset chords and the first target segment until the calculation of the matching degree between the multiple preset chords and the respective target segment is completed;

   The target segment that is at the end of the melody segment is automatically sorted forward and backward to determine the target chord corresponding to each of the target segments.
7. The method according to claim 1, wherein the melody segment is stored in a blockchain, and the generating a harmony segment matched with the melody segment based on the target chords respectively corresponding to the multiple target segments comprises:

   Determining that a section in the melody segment is divided into at least two or more target segments;

   Combining the time values of the same and adjacent target chords in the target chords respectively corresponding to at least two or more target segments constituting a measure of the melody segment;

   Based on the combined time value of the target chord, a harmony segment matched with the melody segment is generated.
8. A device with harmony, including:

   A dividing module for dividing the melody segment into multiple target segments based on the beat of the melody segment;

   The matching module is used to calculate the matching degree between multiple preset chords and each target segment based on the note sequence of each target segment, and for each target segment, use the preset chord with the highest matching degree as the corresponding target segment The target chord;

   The generating module is configured to generate a harmony segment matched with the melody segment based on the target chords respectively corresponding to the multiple target segments.
9. An electronic device, including: a memory and a processor;

   A computer program is stored in the memory;

   The processor is configured to execute the following method when running the computer program:

   Dividing the melody segment into multiple target segments based on the beat of the melody segment;

   Calculate the matching degree between a plurality of preset chords and each target segment based on the note sequence of each target segment, and for each target segment, use the preset chord with the highest matching degree as the target chord of the corresponding target segment;

   Based on the target chords respectively corresponding to the multiple target segments, a harmony segment matched with the melody segment is generated.
10. The electronic device according to claim 9, wherein the processor, when executing the melody segment-based beat to divide the melody segment into a plurality of target segments, specifically executes:

    Determining a variable parameter based on the beat of the melody segment; wherein the variable parameter is a preset value or a chord density set by the user based on the beat of the melody segment;

    The melody segment is divided into a plurality of target segments based on the variable parameter.
11. 9. The electronic device according to claim 9, wherein the processor respectively calculates the matching degree between a plurality of preset chords and the respective target segments in the note sequence based on each target segment, and for each target segment, When the preset chord with the highest matching degree is used as the target chord of the corresponding target segment, specifically execute:

    Determine the target parameters based on the note sequence of each target segment and multiple preset chords;

    The Hidden Markov Model is used to calculate the matching degree between multiple preset chords and the respective target segments based on the target parameters, and the target chords corresponding to the respective target segments are obtained, and the target chords are matched with the corresponding target segments The preset chord with the highest degree.
12. 11. The electronic device according to claim 11, wherein the processor specifically executes when the target parameter is determined based on the note sequence of each target segment and a plurality of preset chords:

    Determining the collocation probabilities of multiple preset chords and each target segment based on the note sequence of each target segment;

    Determining the probability distribution of the multiple preset chords in each key signature based on the interval relationship between the multiple key signatures in the melody segment and each preset chord;

    Calculate the state transition probability of a combination of multiple preset chords and each key signature based on the preset change probability; wherein, the preset change probability includes the key signature change probability and the preset chord change probability;

    The target parameter is generated based on the note sequence, collocation probability, probability distribution, and state transition probability of each target segment.
13. The electronic device according to claim 11, wherein the processor calculates the matching degree between a plurality of preset chords and the respective target segments based on the target parameters, and obtains the corresponding corresponding to the respective target segments. When the target chord, the specific implementation:

    Respectively calculating the matching degree between a plurality of preset chords and the target segment ranked first in the melody segment based on the target parameter;

    If the currently calculated target segment is sorted after the first of the melody segment, it is determined that the currently calculated target segment is the first target segment, and the step of calculating the matching degree between a plurality of preset chords and the first target segment is performed: based on the target Parameters, and the matching degree between multiple preset chords and the previous target segment, respectively calculating the matching degree between multiple preset chords and the first target segment, and sorting the next target segment after the first target segment , As the first target segment; wherein the preamble target segment is the previous target segment sorted before the first target segment in the melody segment;

    Re-execute the step of calculating the matching degree between the multiple preset chords and the first target segment until the calculation of the matching degree between the multiple preset chords and the respective target segment is completed;

    The target segment that is at the end of the melody segment is automatically sorted forward and backward to determine the target chord corresponding to each of the target segments.
14. The electronic device according to claim 9, wherein the melody segment is stored in a blockchain, and the processor generates a matching chord matching the melody segment based on the target chords corresponding to the multiple target segments. When harmonizing segments, the specific implementation:

    Determining that a section in the melody segment is divided into at least two or more target segments;

    Combining the time values of the same and adjacent target chords in the target chords respectively corresponding to at least two or more target segments constituting a measure of the melody segment;

    Based on the combined time value of the target chord, a harmony segment matched with the melody segment is generated.
15. A computer-readable medium having a computer program stored thereon, wherein the computer program implements the following method when executed by a processor:

    Dividing the melody segment into multiple target segments based on the beat of the melody segment;

    Calculate the matching degree between a plurality of preset chords and each target segment based on the note sequence of each target segment, and for each target segment, use the preset chord with the highest matching degree as the target chord of the corresponding target segment;

    Based on the target chords respectively corresponding to the multiple target segments, a harmony segment matched with the melody segment is generated.
16. The computer-readable medium according to claim 15, wherein when the melody segment is divided into a plurality of target segments based on the beat of the melody segment, the specific realization is achieved:

    Determining a variable parameter based on the beat of the melody segment; wherein the variable parameter is a preset value or a chord density set by the user based on the beat of the melody segment;

    The melody segment is divided into a plurality of target segments based on the variable parameter.
17. The computer-readable medium according to claim 15, wherein the matching degree between a plurality of preset chords and the respective target segments is calculated based on the note sequence of each target segment, and for each target segment, the When the preset chord with the highest matching degree is used as the target chord of the corresponding target segment, the specific realization is as follows:

    Determine the target parameters based on the note sequence of each target segment and multiple preset chords;

    The Hidden Markov Model is used to calculate the matching degree between multiple preset chords and the respective target segments based on the target parameters, and the target chords corresponding to the respective target segments are obtained, and the target chords are matched with the corresponding target segments The preset chord with the highest degree.
18. 18. The computer-readable medium according to claim 17, wherein when the target parameter is determined based on the note sequence of each target segment and a plurality of preset chords, the specific realization is achieved:

    Determining the collocation probabilities of multiple preset chords and each target segment based on the note sequence of each target segment;

    Determining the probability distribution of the multiple preset chords in each key signature based on the interval relationship between the multiple key signatures in the melody segment and each preset chord;

    Calculate the state transition probability of a combination of multiple preset chords and each key signature based on the preset change probability; wherein, the preset change probability includes the key signature change probability and the preset chord change probability;

    The target parameter is generated based on the note sequence, collocation probability, probability distribution, and state transition probability of each target segment.
19. The computer-readable medium according to claim 17, wherein the matching degree between a plurality of preset chords and the respective target segments is calculated based on the target parameters, and the target chord time corresponding to the respective target segments is obtained. ,Implementation:

    Respectively calculating the matching degree between a plurality of preset chords and the target segment ranked first in the melody segment based on the target parameter;

    If the currently calculated target segment is sorted after the first of the melody segment, it is determined that the currently calculated target segment is the first target segment, and the step of calculating the matching degree between a plurality of preset chords and the first target segment is performed: based on the target Parameters, and the matching degree between multiple preset chords and the previous target segment, respectively calculating the matching degree between multiple preset chords and the first target segment, and sorting the next target segment after the first target segment , As the first target segment; wherein the preamble target segment is the previous target segment sorted before the first target segment in the melody segment;

    Re-execute the step of calculating the matching degree between the multiple preset chords and the first target segment until the calculation of the matching degree between the multiple preset chords and the respective target segment is completed;

    The target segment at the end of the self-sorting melody segment goes backward to determine the target chord corresponding to each target segment.
20. The computer-readable medium according to claim 15, wherein the melody segment is stored in a blockchain, and the harmony segment matched with the melody segment is generated based on the target chords respectively corresponding to the plurality of target segments When, the specific realization:

    Determining that a section in the melody segment is divided into at least two or more target segments;

    Combining the time values of the same and adjacent target chords in the target chords respectively corresponding to at least two or more target segments constituting a measure of the melody segment;

    Based on the combined time value of the target chord, a harmony segment matched with the melody segment is generated.

Images