In the embodiment of the present invention, whether a preset interactive verb exists in the script content of the session may be detected, if the interactive verb is detected, whether at least two character nouns or character representatives exist within a preset character length range (for example, 5 characters on the left and right) near the interactive verb may be detected, and if the interactive verb exists, the interaction may be determined, for example, the interactive verb includes: clap, pull, push, listen, and speak, etc., for example: the script content is as follows: "I clap the shoulders of little brightness", because "I" and "little brightness" are detected near "clap", it can be determined that an interaction is detected; for another example: "i explain little" because "saying" detects "me" and "explain little" nearby, can confirm that detects an interaction too; for another example: "i zips up", since only one character noun or character pronoun of "i" is detected near "zips", it can be determined that no interaction is detected.

The number of core character interactions v4 can be calculated by:

wherein, the interactive _ count represents the number of times the core character (top10) in the local field interacts.

The total emotional intensity (i.e. the seven emotional intensities) of the characters appearing in the field is the sum of the emotional values of the characters appearing in the field, that is, for each field, the emotional value of each character can be calculated according to a preset algorithm for calculating the emotional value of the characters appearing in the field, and the emotional values of the characters appearing in the field are added to obtain the total emotional intensity;

the total emotional intensity v5 of the emerging character can be calculated by:

in the embodiment of the present invention, whether preset emotion words exist in a preset character length range (such as left and right 3 characters) near a target character in the scenario content of the scenario can be detected, each preset emotion word has a corresponding emotion score, based on each detected emotion word, an emotion score corresponding to the emotion word is searched, and the emotion scores corresponding to all emotion words of the target character are accumulated to obtain the emotion value of the target character.

For example: the emotional words comprise: smile, laugh, cry and \24696, cry and the like, wherein the emotion score corresponding to the smile is 2 points, the emotion score corresponding to the laugh is 4 points, the emotion score corresponding to the cry is 3 points, \24696, the emotion score corresponding to the cry is 5 points, and the hypothesis is that: the script content is as follows: "red little smiling," because "smile" is detected near "red little" of the target character, can determine that the emotional value adds 2 points; for another example: the target character is a little red and big smile, and because the target character is a little red and big smile, the emotional value can be determined to be added by 4 points; for another example: "Small red 24696;" cry ", because" 24696; "cry" is detected in the vicinity of "small red" of the target character, it is possible to determine the emotional value plus 5, etc.

The feature value of an episode point is the importance of the event in the episode node to which the episode belongs, the episode point in the composition term of a movie or a tv show specifies a change or event which is tightly woven into the story and turns the story to another direction, an episode node may contain at least one episode, and the calculation of the feature value of an episode point is described in detail later.

In this step, information such as the appearance characters, the interaction between the characters (such as behavior interaction and conversation interaction) and the emotional state of each character in the scenario text corresponding to each session can be extracted, important character information, core character information, interaction information between each character and other characters, and the like are extracted from the scenario-related file, and the analysis index corresponding to each session is calculated based on the extracted information.

Step S103, calculating the wonderful degree score of each field according to the analysis index corresponding to each field;

since the difference of the measure of each analysis index is large and each analysis index has different influence on the highlight of the scenario text, in this step, the analysis indexes of each scenario may be converted into the same measure, and a weight may be added to each analysis index to obtain the highlight score of each scenario.

And step S104, generating a wonderness change curve for representing the wonderness change condition of each field based on the wonderness score of each field.

In this step, the wonderness change curve may be generated with the wonderness score of each field as the Y-axis and the field as the X-axis.

In another embodiment of the present invention, the step S102 calculates an analysis index corresponding to each scenario according to the scenario text corresponding to each scenario, including:

step 201, obtaining the role of the session, the play data of each role, and the total number of the roles of the session in the scenario file.

In the embodiment of the invention, the play data is determined according to the behavior of the character in the field and the occurrence frequency of dialogue;

202, sequencing the play data of each role in the play file, and selecting a plurality of roles with the top play ranking to obtain a plurality of important roles in the play file;

in this step, the play data of each character in the play file may be sorted according to the number of plays, and several important characters ranked at the top in the sorting may be selected. For example, the characters in the drama file may be sorted in the order of the play from the most to the least, and the characters in the drama file may be sorted in the order of the play from the least to the most.

Step 203, counting the number of the roles matched with any important role in the roles of the scene, and obtaining the first number of the important roles of the scene;

and 204, calculating the ratio of the first quantity to the total quantity to obtain the field ratio of the important character.

In the embodiment of the invention, the ratio of the important character to the present can be calculated by the following formula:

v_1＝top_role/role_count

where top _ role refers to the first number of important characters present in the field, and role _ count represents the total number of characters present in the field.

In the embodiment of the present invention, the number of important characters with the largest play in the play file is calculated as follows:

where N represents the total number of characters present in the transcript file.

The embodiment of the invention can automatically calculate the analysis index of the ratio of the important characters to the scene, realizes the quantification of the characteristic information in the scenario text, is convenient for calculating the wonderful degree score based on the analysis index subsequently, is further convenient for automatically generating the wonderful degree change curve based on the wonderful degree score, and improves the generation efficiency and the accuracy of the wonderful degree change curve.

In another embodiment of the present invention, calculating an analysis index corresponding to each scenario according to the scenario text corresponding to each scenario includes:

step 303, obtaining the plot information of the plot belonging to the field, the field contained in the plot information and the arrangement sequence of the field;

and 304, calculating the characteristic value of the situation node according to the field arrangement sequence and the position of the field in the field arrangement sequence.

The plot characteristic value v6 may be calculated by the following equation:

v₆＝f(plot_num)

where plot _ num is a field identifier, illustratively, the f () function represents: and sorting the scenes belonging to the same situation node according to the sequence of the scenes, setting the scene point characteristic values of the scenes at two ends to be 0.5, and sequentially adding 0.5 to the middle scene to be used as the scene point characteristic value of the corresponding scene, wherein the scenes do not belong to any situation node and the scene point characteristic value is 0.

For example: if 7 scenes belong to the same scene node, the scene node feature values of the 7 scenes are [0.5,1,1.5,2,1.5,1,0.5]) in sequence.

The embodiment of the invention can automatically calculate the analysis index of the plot characteristic value, realizes the quantification of the characteristic information in the plot text, is convenient for calculating the wonderful degree score based on the analysis index subsequently, is further convenient for automatically generating the wonderful degree change curve based on the wonderful degree score, and improves the generation efficiency and the accuracy of the wonderful degree change curve.

In another embodiment of the present invention, for each session, calculating the highlight score of each session based on the analysis index corresponding to the session includes:

step 401, converting each analysis index into a feature score for the analysis index corresponding to each session;

in practical application, for each analysis index, the analysis index is constructed in n fieldsSet F of corresponding numerical values in the next₁＝{v₁₁,v₁₂,…,v_1n}; each analytical index can then be converted to a characteristic score using the Z-core normalization method of the following formula:

wherein, mean () function and std () function represent mean value and standard deviation respectively, and other analysis indexes adopt the above-mentioned mode in turn, convert the analysis index into characteristic score.

And step 402, multiplying the characteristic score of each field by the corresponding weight coefficient to obtain the wonderful score of each field.

The formula for calculating the chroma score is as follows:

where t is the field, i represents the ith feature, w_i＝[0.6,1.0,0.8,1.0,1.2,0.5]The corresponding weight coefficient is assigned to each feature.

Based on the above equation, a set S ═ S of the highlight score for each field can be calculated₁,s₂,…,s_n-s 1 is the highlight score of the first field, -s 2 is the highlight score of the second field, and sn is the highlight score of the nth field.

The embodiment of the invention can automatically calculate the wonderness score of each field, is convenient for automatically generating the wonderness change curve based on the wonderness score, and improves the generation efficiency and the accuracy of the wonderness change curve.

In a further embodiment of the present invention, generating a highlight variation curve for characterizing a highlight variation of each field based on the highlight score of each field comprises:

step 501, performing exponential smoothing processing on the wonderness score of each field to obtain a first intermediate score of each field;

the highlight scores of each field may be exponentially smoothed as follows

s_i＝α×s_i+(1-α)×s_i-1,i∈{2,3,…,n}

Wherein a is a preset natural number.

Step 502, performing outlier detection in the first intermediate score of each field to obtain a head outlier set, a tail outlier set and a normal point set;

in this step, a first intermediate score greater than a first preset threshold may be determined as a head outlier, and a head outlier set including the head outlier is constructed; determining a first intermediate score smaller than a second preset threshold value as a tail outlier, and constructing a tail outlier set comprising the tail outlier, wherein the first preset threshold value is larger than the second preset threshold value; determining first intermediate scores except for the head outlier and the tail outlier among the first intermediate scores of all the fields as normal points, and constructing a normal point set including the normal points.

Illustratively, assuming q1 and q3 are 0.25 quantile and 0.75 quantile of s, respectively, for each si, si is defined as head outliers if si < q1-3 × (q3-q1), and as tail outliers if si > q3+3 (q3-q1), with the remaining points being normal points. Wherein, the quantile number refers to arranging a group of numbers from small to large, the number at the position of 1/4 is 0.25 quantile, and the number at the position of 3/4 is 0.75 quantile.

Step 503, normalizing the head outlier set to a first interval, normalizing the tail outlier set to a second interval, and normalizing the normal point set to a third interval to obtain a second intermediate score of each session.

Wherein the smaller boundary threshold for the first interval is greater than or equal to the larger boundary threshold for the third interval, which is greater than or equal to the larger boundary threshold for the second interval;

since the data point values have positive or negative values and the difference of the numerical range obtained by each scenario is large, the data point values are normalized to be between 0 and 100, and the data point values are more normative, for example: there is a set of data: [ -100, -99, -1,0,1,2,3,2,1,3, 99,100], the set of numbers being calculated in terms of outliers, -100, -99 being tail outliers, 99 and 100 being head outliers (i.e., too different from the overall data, direct plotting will cause these individual outlier data to press the intermediate curves very gently, showing no fluctuations), thus normalizing tail outliers [ -100, -99] to between 3-7, head outliers [99,100] to between 93-100, normal points [ -1,0,1,2,3,2,1,3] to between 11-85.

In this step, the head outlier set Sh, the normal point set Sn, and the tail outlier set St may be normalized according to the following equations:

wherein h is_min＝3,h_max＝7,n_min＝11,n_max＝85,t_min＝93,t_max＝100。

And step 504, generating a wonderful degree change curve based on the second intermediate scores of the fields.

The embodiment of the invention can automatically carry out exponential smoothing processing, outlier detection and normalization processing on the wonderness scores of all the fields, and is convenient for smoothing the generated wonderness change curve.

For easy understanding, the present invention further provides an embodiment in practical application, as shown in fig. 2, assuming that the scenario file includes n scenes,scene 1, scene 2, and scene … …, six analysis indexes, i.e., the exposure percentage of the important character, the number of the exposure characters, the total drama of the exposure characters, the number of times of interaction of the core character, the total emotional intensity of the exposure characters, and the feature value of the plot, may be first calculated, then each analysis index is converted into a feature score to obtain v1, v2, and … … v6, then v1, v2, and … … v6 are weighted and averaged to obtain a highlight score of each scene, then the highlight score of each scene is subjected to index smoothing, outlier detection, and normalization processing, and finally a highlight change curve is generated based on the processed data.

In still another embodiment of the present invention, as shown in fig. 3, there is also provided a scenario information processing apparatus including:

the obtaining module 11 is configured to obtain a scenario text corresponding to each scenario in the scenario file;

the first calculating module 12 is configured to calculate an analysis index corresponding to each scenario according to the scenario text corresponding to each scenario, where the analysis index is used to analyze the highlight information of each scenario in the scenario file;

a second calculating module 13, configured to calculate, for each session, a highlight score of each session based on an analysis index corresponding to the session;

and the generating module 14 is used for generating a wonderness change curve for representing the wonderness change condition of each field based on the wonderness score of each field.

In another embodiment of the present invention, an electronic device is further provided, which includes a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;

a memory for storing a computer program;

and the processor is used for realizing the script information processing method of any one of the method embodiments when executing the program stored in the memory.

In the electronic device provided by the embodiment of the invention, the processor executes the program stored in the memory to realize that the scenario text corresponding to each scenario in the scenario file is firstly obtained, then the analysis index corresponding to each scenario is calculated according to the scenario text corresponding to each scenario, then the highlight score of each scenario is calculated based on the analysis index corresponding to each scenario aiming at each scenario, and finally the highlight change curve for representing the highlight change condition of each scenario can be generated based on the highlight score of each scenario.

Thecommunication bus 1140 mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. Thecommunication bus 1140 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 4, but this does not indicate only one bus or one type of bus.

Thecommunication interface 1120 is used for communication between the electronic device and other devices.

Thememory 1130 may include a Random Access Memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

Theprocessor 1110 may be a general-purpose processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the integrated circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components.

In still another embodiment of the present invention, there is also provided a computer-readable storage medium having stored thereon a program of a scenario information processing method, which when executed by a processor, implements the steps of the scenario information processing method described in any one of the method embodiments described above.

It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A scenario information processing method, comprising:

acquiring a scenario text corresponding to each field in the scenario file;

2. The scenario information processing method according to claim 1, wherein the analysis index includes: one or more of the important role appearance ratio, the appearance role number, the total drama of the appearance role, the interaction times of the core character, the total emotional intensity of the appearance role and the feature value of the plot point;

3. The scenario information processing method of claim 2, wherein calculating the analysis index corresponding to each scenario according to the scenario text corresponding to each scenario comprises:

4. The scenario information processing method of claim 2, wherein calculating the analysis index corresponding to each scenario according to the scenario text corresponding to each scenario comprises:

5. The scenario information processing method according to claim 1, wherein calculating, for each session, a highlight score for each session based on an analysis index corresponding to the session includes:

6. The scenario information processing method according to claim 1, wherein generating a highlight variation curve for representing a highlight variation of each of the fields based on the highlight score of each of the fields comprises:

7. The scenario information processing method of claim 6, wherein performing outlier detection in the first middle score of each session to obtain a head outlier set, a tail outlier set, and a normal point set comprises:

8. A scenario information processing apparatus comprising:

9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;

a memory for storing a computer program;

a processor for implementing the scenario information processing method according to any one of claims 1 to 7 when executing the program stored in the memory.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a program of a scenario information processing method, which when executed by a processor, realizes the steps of the scenario information processing method of any one of claims 1 to 7.