CN116484835B

CN116484835B - Script item excavating method, device and equipment

Info

Publication number: CN116484835B
Application number: CN202310485351.5A
Authority: CN
Inventors: 阳林; 赵寅; 张�杰; 高�勋; 蔡晓岑; 钱凯
Original assignee: Beijing Youku Technology Co Ltd
Current assignee: Beijing Youku Technology Co Ltd
Priority date: 2023-04-28
Filing date: 2023-04-28
Publication date: 2023-11-28
Anticipated expiration: 2043-04-28
Also published as: CN116484835A

Abstract

The embodiment of the application provides a method, a device and equipment for excavating a scenario prop, wherein the method comprises the following steps: the electronic equipment acquires a script to be processed and extracts script elements in the script to be processed; determining target elements matched with the scenario elements in a preset item knowledge base according to the scenario elements; and then determining the target associated prop corresponding to the scenario to be processed according to the target element and a preset prop knowledge base. According to the embodiment of the application, the electronic equipment associates the props based on the preset prop knowledge base and the script elements, and can determine the target associated props in the script to be processed, so that the comprehensiveness of the excavation of the props can be improved, the operation of a user can be simplified, the time of the user is saved, and the efficiency of the excavation of the props is improved.

Description

Script item excavating method, device and equipment

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, and a device for excavating scenario items.

Background

In the shooting process of film and television works, such as movies, television shows and the like, the characteristics of long period, high investment and high uncertainty generally exist, in order to reduce cost and increase the scientificity of management, script analysis becomes a very important link in the shooting process of the film and television works, and script property mining is an important dimension of script analysis.

In the related art, when the play is excavated, a user usually manually reads the play and records the play used in the play, so that the operation is complex, the time and the labor are consumed, the efficiency of excavating the play is low, and the excavation of the play is not comprehensive.

Disclosure of Invention

The application provides a method, a device and equipment for excavating a script prop, which are used for simplifying the operation of a user, saving the time of the user and improving the efficiency and the comprehensiveness of excavating the script prop.

In a first aspect, an embodiment of the present application provides a scenario property mining method, including:

acquiring a scenario to be processed, and extracting scenario elements in the scenario to be processed;

determining target elements matched with the scenario elements in a preset item knowledge base according to the scenario elements;

and determining the target associated prop corresponding to the scenario to be processed according to the target element and the preset prop knowledge base.

In one possible implementation manner, determining, according to the scenario element, a target element matched with the scenario element in a preset prop knowledge base includes:

carrying out synonym rewriting on script elements, and determining a plurality of script elements with the same meaning as the same alternative element;

Determining matching scores of the candidate elements and each preset element in a preset prop knowledge base; the preset prop knowledge base comprises a plurality of preset elements and props corresponding to the preset elements;

and determining the preset element with the matching score meeting the preset condition as a target element.

In one possible embodiment, the method further comprises:

determining a target mention prop in the script to be processed based on the prop identification model;

and displaying the target mention props and the target association props.

In one possible embodiment, the method further comprises:

determining target categories corresponding to all props in the target mention props;

and classifying and fusing all the target mentioned props and all the target associated props according to the target category.

In one possible embodiment, displaying the target-mention props and the target-association props includes:

determining target evaluation parameters corresponding to all props in the target mention props; the target evaluation parameters are determined based on the correlation of the props and the to-be-processed script and the implantation scores of the props; the relevance and implantation scores are proportional to the target evaluation parameters;

and displaying the target mentioned props and the target associated props according to the order of the target evaluation parameters from large to small.

In one possible implementation, the scenario to be processed includes a plurality of shots, each shot corresponding to a scenario segment; displaying the target-mentioned props and the target-associated props, comprising:

determining the associated field times corresponding to the target-mentioned props and the associated field times corresponding to the target-associated props;

displaying the object-mentioned props and object-associated props, and displaying field links of associated fields corresponding to the props;

and responding to the touch operation for the scene link, and displaying the script fragment corresponding to the scene link selected by the touch operation.

In one possible embodiment, the method further comprises:

displaying a preset file generation control;

responding to touch operation of a control generated aiming at a preset file, and disassembling a scenario to be processed into scenario fragments corresponding to each occasion;

and generating a script dismantling file according to the script fragments corresponding to each occasion and the target mention props and target association props corresponding to each occasion.

In one possible embodiment, after categorizing and fusing the target-mentioned props and the target-associated props by target category, the method further comprises:

determining the number of props corresponding to each target category, and determining the total number of props corresponding to the scenario to be processed according to the number of props;

Determining the ratio of the number of props corresponding to each target class to the total number of props, and obtaining the corresponding prop ratio of each target class;

displaying the total number of props, the corresponding prop ratio of each target class and the corresponding prop number of each target class.

In one possible embodiment, the method further comprises:

displaying the labeling page; the labeling page comprises a search control; the search control comprises a text input control and a search dimension control;

responding to touch operation for a text input control and/or responding to touch operation for a search dimension control, and determining a target script segment corresponding to the touch operation from script segments corresponding to each scene in the script to be processed;

and displaying the target script fragment, and displaying the target mention props and the target association props corresponding to the field times of the target script fragment.

In one possible embodiment, the method further comprises:

displaying a preset remark control and a preset adding control;

responding to input operation for a preset remark control, determining remark information corresponding to the input operation, and associating the remark information with a target script fragment;

and responding to touch operation aiming at a preset adding control, and adding the target script fragment corresponding to the touch operation into the candidate fragment list.

In a second aspect, an embodiment of the present application provides a scenario prop excavating device, including:

the acquisition module is used for acquiring the scenario to be processed and extracting scenario elements in the scenario to be processed;

the first determining module is used for determining target elements matched with the script elements in a preset prop knowledge base according to the script elements;

and the second determining module is used for determining the target associated property corresponding to the scenario to be processed according to the target element and the preset property knowledge base.

In one possible implementation manner, the first determining module is specifically configured to:

In one possible embodiment, the apparatus further comprises:

the third determining module is used for determining a target mention prop in the scenario to be processed based on the prop identification model;

and the display module is used for displaying the target mentioned props and the target associated props.

In one possible embodiment, the apparatus is further for:

In one possible implementation, the display module is specifically configured to:

In one possible implementation, the scenario to be processed includes a plurality of shots, each shot corresponding to a scenario segment; the display module is specifically used for:

In one possible embodiment, the apparatus is further for:

displaying a preset file generation control;

In one possible embodiment, the apparatus is further for:

displaying a preset remark control and a preset adding control;

In a third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor;

the memory stores computer-executable instructions;

the processor executing computer-executable instructions stored in the memory, causes the processor to perform the scenario item mining method of any one of the first aspects.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored therein computer-executable instructions for implementing the scenario-item mining method of any one of the first aspects when the computer-executable instructions are executed by a processor.

In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which when executed by a processor implements a scenario item mining method according to any one of the first aspects.

In the embodiment of the application, the electronic equipment acquires the scenario to be processed and extracts scenario elements in the scenario to be processed; determining target elements matched with the scenario elements in a preset item knowledge base according to the scenario elements; and then determining the target associated prop corresponding to the scenario to be processed according to the target element and a preset prop knowledge base. According to the embodiment of the application, the electronic equipment associates the props based on the preset prop knowledge base and the script elements, and can determine the target associated props in the script to be processed, so that the comprehensiveness of the excavation of the props can be improved, the operation of a user can be simplified, the time of the user is saved, and the efficiency of the excavation of the props is improved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:

fig. 1 is a schematic diagram of an application scenario provided in an exemplary embodiment of the present application;

fig. 2 is a schematic flow chart of a scenario property excavation method according to an exemplary embodiment of the present application;

fig. 3 is a schematic flow chart of another scenario property excavation method provided in an exemplary embodiment of the present application;

FIG. 4 is a schematic diagram of a target associated prop matching strategy provided by an exemplary embodiment of the present application;

FIG. 5 is a schematic diagram of a prop summary page provided by an exemplary embodiment of the present application;

fig. 6 is a schematic diagram of a scenario information query page provided in an exemplary embodiment of the present application;

FIG. 7 is a schematic diagram of a markup page provided by an exemplary embodiment of the present application;

FIG. 8 is a schematic diagram of a scenario project management page provided in an exemplary embodiment of the present application;

fig. 9 is a schematic technical link diagram of a scenario property mining method according to an exemplary embodiment of the present application;

fig. 10 is a logic schematic diagram of a scenario property mining method according to an exemplary embodiment of the present application;

FIG. 11 is a schematic diagram of a merchant terminal script project page provided by an exemplary embodiment of the present application;

fig. 12 is a schematic structural view of a scenario property excavation apparatus provided in an exemplary embodiment of the present application;

fig. 13 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application. The user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of related data is required to comply with the relevant laws and regulations and standards of the relevant country and region, and is provided with corresponding operation entries for the user to select authorization or rejection.

The shooting process of film and television works such as movies and television shows has the characteristics of long script period, large investment and high uncertainty, script analysis is an important link in the film and television work shooting process, and script mining is an important dimension of script analysis in order to realize scientific management and risk assessment. The props are very important components for capturing the script, so that on one hand, the props can assist a user in analyzing the script making cost and assisting the user in deciding, scientific use and planning of the props can be realized, and cost reduction and efficiency improvement can be realized; on the other hand, the script property can be associated with the brand commodity, so that cooperation of the property and the brand merchant is realized, and the cost is further reduced.

In the related art, when the script is excavated, a user usually needs to manually read the script and manually record the script used in the script, so that the operation of the user is complicated, the time and the labor are consumed, and the efficiency of excavating the script is low.

Fig. 1 is a schematic diagram of an application scenario provided in an exemplary embodiment of the present application. As shown in fig. 1, includes a scenario 101, a user 102, and an electronic device 103. The electronic device 103 may be a cell phone, a computer, a wearable device, etc. As shown in fig. 1, in the related art, a user 102 manually reads a scenario 101, manually records various props included in the scenario 101, and the prop excavation efficiency is low. In the embodiment of the present application, the electronic device 103 may automatically determine and display the mentioned props and associated props corresponding to the scenario 101 based on the prop identification model and the preset prop knowledge base, so as to simplify the operation of the user and improve the prop excavation efficiency and comprehensiveness.

The technical scheme shown in the application is described in detail by specific examples. It should be noted that the following embodiments may exist alone or in combination with each other, and for the same or similar content, the description will not be repeated in different embodiments.

Fig. 2 is a schematic flow chart of a scenario property mining method according to an exemplary embodiment of the present application. Referring to fig. 2, the method may include:

s201, acquiring a scenario to be processed, and extracting scenario elements in the scenario to be processed.

The execution main body of the embodiment of the application can be electronic equipment or a script item excavating device arranged in the electronic equipment. The scenario property excavating device can be realized by software or by combination of software and hardware. For ease of understanding, hereinafter, an execution body will be described as an example of an electronic device.

In the embodiment of the application, the scenario to be processed can refer to a scenario requiring to be excavated for the property, and the scenario to be processed can be a scenario of various film and television works, such as a movie, a television play, a drama, an opera and the like. The scenario element may refer to various scenario information in the scenario to be processed, such as scenario scenes, personas, plot features, daily scenes, persona actions, etc. The scenario scene may refer to a scene corresponding to each session in the scenario, for example, "a forest cabin", "a hospital gate", and the like. Scenario features may refer to the degree of conflict of each scenario of a scenario, scenario emotion of each scenario, etc., e.g., scenarios in a scenario may be distinguished into "high-energy" (particularly important) scenarios, important scenarios, common (or bedding) scenarios, etc., based on the difference in conflict strength; the scenario emotion may include a negative emotion or a positive emotion, etc. Of course, the scenario elements may also include other types, and specifically may be flexibly set based on actual requirements, which is not limited by the embodiment of the present application.

In the step, when prop excavation is required to be carried out on the scenario to be processed, the electronic equipment can acquire the scenario to be processed and carry out subsequent processing. The electronic device may then extract various script elements in the script to be processed based on the pre-configured algorithm model. For example, the electronic device may determine, through a scene recognition model, a scenario scene of each session in the scenario; the electronic equipment can also determine each persona in the script through the persona identification model; the electronic equipment can also determine the collision intensity and the like of each occasion in the play through a play collision intensity recognition model based on algorithms such as keyword recognition, emotion recognition and the like. It should be noted that, the algorithm model required in the scenario element extraction process may be flexibly configured based on actual requirements, which is not limited by the embodiment of the present application.

S202, determining target elements matched with the script elements in a preset prop knowledge base according to the script elements.

In the embodiment of the application, the prop can be the decoration and the articles, including physical articles, services, websites, application programs and the like, which are required in the performance process of drama and the like or the film and television work shooting process, and the embodiment of the application is not limited to the specific type of the prop.

The preset prop knowledge base may refer to a preset association prop knowledge base, which includes a plurality of preset elements, where each preset element corresponds to a plurality of props. For example, in the preset prop knowledge base, the props corresponding to the preset element of the scenario "meeting room" may include: projector, notebook computer, conference round table, office chair, notebook, microphone, etc. Aiming at the script to be processed, the electronic equipment can mine the props which are not directly mentioned in the script to be processed, but are needed in the shooting process. Such a scenario to be processed is not mentioned, but the prop required in the shooting process may be referred to as an implicit prop or an associative prop. The target element may refer to an element in the preset prop knowledge base that matches the scenario element.

The embodiment of the application constructs the preset prop knowledge base in advance, wherein the preset prop knowledge base comprises various script elements and props associated with the script elements. The preset prop knowledge base can be stored in the cloud, the electronic equipment can be accessed remotely, and the preset prop knowledge base can be directly stored in the local of the electronic equipment. Specifically, the preset prop knowledge base may include a scenario knowledge base and a filmed knowledge base, wherein the scenario knowledge base is a knowledge base constructed based on a large amount of scenario data; the film knowledge base is a knowledge base constructed based on film and television content or actual scenes, and the electronic device can obtain a large number of film and television videos or film and television images, and identify the props corresponding to different script elements through recognition algorithm models such as a visual scene recognition model, a target detection model, an action model and the like, and associate the script elements with the props corresponding to the script elements.

Specifically, after the electronic equipment extracts the scenario elements in the scenario to be processed in the step, the electronic equipment can determine target elements similar to the scenario elements of the scenario to be processed in a preset scenario knowledge base, and further can acquire target association items required by the scenario to be processed based on the target elements, so that rapid excavation of the association items is realized, and comprehensiveness and efficiency of excavation of the scenario items are improved.

S203, determining the target associated prop corresponding to the scenario to be processed according to the target element and the preset prop knowledge base.

In the embodiment of the application, the target associated prop can be the associated prop required in the scenario to be processed. After the electronic equipment determines the target element, the props corresponding to the target element can be read from a preset prop knowledge base based on the target element, and the props can be correspondingly used as target association props corresponding to the script to be processed.

On the basis of the above embodiment, fig. 3 is a schematic flow chart of another scenario property excavation method according to an exemplary embodiment of the present application. Referring to fig. 3, the method may include:

s301, acquiring a scenario to be processed, and extracting scenario elements in the scenario to be processed.

The specific implementation manner of step S301 may refer to step S201, and the embodiments of the present application are not described herein.

S302, determining target elements matched with the script elements in a preset prop knowledge base according to the script elements.

In the embodiment of the application, after determining the scenario elements, the electronic device can determine the target elements matched with the scenario elements in the preset prop knowledge base based on mapping matching. Specifically, when determining a target element matched with the scenario element, the electronic device may use a preset element with similarity to the scenario element larger than a preset threshold in a preset prop knowledge base as the target element, where the preset threshold may be 90% or 95%; the electronic device may also determine the element with the greatest similarity to the scenario element in the preset prop knowledge base, or may determine the target element in other manners, and the embodiment of the present application does not limit a specific determination manner of the target element.

In one possible embodiment, step S302 may include the following steps (1) to (3):

(1) And carrying out synonym rewriting on the script elements, and determining a plurality of script elements with the same meaning as the same candidate element.

In the embodiment of the application, the alternative elements can be elements obtained by unifying a plurality of script elements with the same actual meaning but similar names. Because the script writing method is various, different names may exist for the same script element, and the electronic device can unify script elements with different names but the same actual meaning into the same script element based on the synonym rewriting algorithm, so that the script element can be conveniently matched with preset elements in a preset prop knowledge base.

(2) Determining matching scores of the candidate elements and each preset element in a preset prop knowledge base; the preset prop knowledge base comprises a plurality of preset elements and props corresponding to the preset elements.

(3) And determining the preset element with the matching score meeting the preset condition as the target element.

In the embodiment of the application, the matching score may refer to the similarity degree between the candidate element and the preset element. The preset condition may be a preset matching score judgment condition, and specifically may be that the matching score is greater than a preset threshold value, etc. After determining the candidate elements, the electronic device can calculate the matching scores between the candidate elements and each preset element, and then determine the target elements corresponding to the candidate elements according to whether the matching scores meet preset conditions. Specifically, the electronic device may determine a preset element with a matching score greater than a preset threshold value as a target element, or rank the preset elements in order of the matching score from large to small, and use the preset element ranked in the first N bits as the target element, where the number N may be 1, 2, 3, and the like. Therefore, the electronic equipment combines a plurality of script elements with the same meaning into the same alternative element through synonym rewriting, calculates the matching score to determine the target element, so that the calculated amount can be reduced, and the accuracy of determining the target element can be improved.

It should be noted that, the electronic device may also use other matching strategies to determine the target element corresponding to the scenario element. Illustratively, FIG. 4 is a schematic diagram of a target associated prop matching strategy in accordance with an exemplary embodiment of the present application. As shown in fig. 4, the preset prop knowledge base is divided into a scenario knowledge base and a cost knowledge base, and the electronic device can adopt different preset matching strategies for scenario elements, namely scenario scenes, and for the scenario knowledge base and the cost knowledge base. For the scenario knowledge base, the electronic device may determine the longest matching tree node, and use the corresponding prop in the longest matching tree node as the target association prop. Specifically, for the scene "XX hospital gate", the electronic device can first find the longest matching tree node from the root node (root), that is, find two nodes of "gate" and "hospital", and then can determine the target associated prop corresponding to the longest matching tree node.

Specifically, as shown in fig. 4, from the root node, two nodes of a gate and a hospital can be found in layer 2, other nodes are irrelevant nodes, but the gate node cannot be found by downward matching of the hospital, so that the electronic equipment can determine the gate node in layer 2, then continue downward matching, find the hospital node in layer 3, and the villa node is an irrelevant node, so that the longest matched tree node can be determined. In the matching process of tree nodes, the number of nodes in each layer is different, for example, layer 1 has only 1 root node, layer 2 has 1938 nodes, layer 3 has 2667 nodes, layer 4 has 376 nodes, and layers 5 and 5 have 111 nodes in total.

For the filmstrip knowledge base, the electronic device may perform similarity calculation (Sim) between the cut word of the scenario scene and the cut word of a certain scene in the filmstrip knowledge base. As shown in fig. 4, in determining the similarity of two scenario scenes, the electronic device may perform word segmentation processing on the scenario scenes, and then calculate the similarity between the scenario scene words in the scenario to be processed and the scenario scene words in the slicing knowledge base, respectively, according to the similarity matrix shown in fig. 4. In addition, in the scenario, the importance degree of the suffix is high, so that the weighting processing can be performed in the similarity calculation process. For example, for a scenario "XX hospital doorway", the importance of the "doorway" is significantly higher than that of "XX", and thus the weight of the term "doorway" may be set to 1, and the weight of other terms may be gradually decreased, for example, may be 0.9, 0.81, or the like. In addition, the electronic device can rewrite synonyms of scenario scenes with similar meanings in the scenario to be processed, the scenario scenes with similar meanings can be used as a synonym library, and the synonym library can be uniformly rewritten into the same alternative element to perform similarity calculation. Therefore, based on synonym rewriting and similarity matrix calculation, the electronic device can take the preset element with the maximum similarity as the target element, and then can determine the prop corresponding to the target element as the target association prop.

Of course, the matching policy shown in fig. 4 is only one way, and the electronic device may also use other matching policies to determine a target element similar to the scenario element, which is not limited by the embodiment of the present application.

S303, determining the target associated prop corresponding to the scenario to be processed according to the target element and a preset prop knowledge base.

In the embodiment of the application, after the electronic equipment determines the scenario elements of the scenario to be processed, the target elements matched with the scenario elements are determined in the preset scenario knowledge base, and then the scenario corresponding to the target elements is determined as the target associated scenario corresponding to the scenario to be processed, so that the depth of the excavation of the scenario can be increased, and the recall rate of the scenario is increased.

S304, determining the object mention prop in the scenario to be processed based on the prop identification model.

In the embodiment of the application, the prop identification model can be a pre-trained model for identifying the script-mentioned props. A variety of recognition algorithms may be included in the prop recognition model, such as named entity recognition algorithms (Named Entity Recognition, NER), and the like. The target mention props may refer to props that directly appear in the script to be processed or directly mention.

In addition to the target association prop, the electronic device may also determine a target mention prop that appears directly in the scenario to be processed. Specifically, after the electronic device acquires the scenario to be processed, the scenario to be processed may be input into the prop identification model, and it is determined that the object in the scenario to be processed refers to the prop.

S305, displaying the target mentioned props and the target associated props.

In the embodiment of the application, after the electronic equipment acquires the target-mentioned props and the target-associated props, the target-mentioned props and the target-associated props can be directly displayed, so that the user can conveniently carry out subsequent processing. Of course, the electronic device may also process the target-mentioned props and the target-associated props in a preset post-processing manner, for example, classification, summarization, proportion calculation, etc., so that the electronic device is convenient for a user to check.

In one possible implementation manner, when the electronic device displays the object-mentioned prop and the object-associated prop, a prop summary page may be displayed, where the prop summary page may be displayed according to the object-mentioned prop and the object-associated prop, that is, the object-mentioned prop and the object-associated prop are displayed using two sub pages, or may be displayed in a mixed summary manner, that is, summary data after the object-mentioned prop and the object-associated prop are mixed is displayed in the same page. Specifically, the scenario property excavation method may further include the following steps:

(4) And determining the target category corresponding to each prop in the target-mentioned props and the target-associated props.

In the embodiment of the application, the target category may refer to a category corresponding to the prop in the scenario to be processed. After determining the target mention props and the target association props corresponding to the scenario to be processed, the electronic equipment can determine the target category corresponding to each props from preset categories. The preset category may refer to a preset category of the mentioned props. The electronic device may store a pre-built scenario item category system, which includes possible preset types of various scenario items, where the preset types may be divided into multiple levels, for example, categories, subcategories, and so on. By way of example, the preset types may include 23 categories of bags, home appliances, automotive traffic, flower and bird lovely pets, food-drink, etc., each category may include a plurality of subcategories. According to the embodiment of the application, the electronic equipment can identify and classify the props by setting up a general script prop category system, so that the operation of a user can be simplified, and the efficiency is improved.

In the step, when the electronic equipment determines the object-mentioned props, the electronic equipment can simultaneously determine which object category each object-mentioned props belong to based on the prop identification model; when determining the target associated props, the target category corresponding to each target associated props can be determined based on the category fields in the preset prop knowledge base. Of course, the electronic device may also determine the target category corresponding to each prop based on the classification algorithm after determining the target-mentioned prop and the target-associated prop.

(5) Classifying and fusing all the target mentioned props and all the target associated props according to the target category.

In the embodiment of the application, after the target category to which each prop belongs is determined, the electronic equipment can classify and fuse the target reference prop and the target association prop in the script to be processed according to the target category, so that the similar props are normalized, the automatic classification processing of the props can be realized, and the viewing and analysis of users are facilitated.

(6) And determining the number of the props corresponding to each target category, and determining the total number of props corresponding to the scenario to be processed according to the number of the props.

In the embodiment of the application, the number of props may refer to the number of all props in a target class. The total number of props may refer to the total number of all props within the scenario to be processed. After classifying and fusing the object-mentioned props and the object-associated props, the electronic device can count the props in each object category, and can sum the props in all object categories to obtain the total number of props corresponding to the scenario to be processed.

(7) And determining the ratio of the number of props corresponding to each target class to the total number of props, and obtaining the prop ratio corresponding to each target class.

In the embodiment of the application, the prop duty ratio may refer to a ratio of the number of props of a target class to the total number of props. After determining the total number of props corresponding to the scenario to be processed and the number of props corresponding to each target category, the electronic device can determine the prop occupation ratio corresponding to each target category.

(8) And displaying the total number of props, the prop occupation ratio corresponding to each target class and the number of props corresponding to each target class.

In the embodiment of the application, the electronic equipment can display the total number of the props corresponding to the script to be processed in the prop summarization page, can display the number of the props corresponding to each target category, and can display the prop occupation ratio corresponding to each target category in a column diagram, a pie diagram and other modes. Of course, the electronic device may also determine the frequency of occurrence or the number of times of mention of the object with respect to the prop, and display various statistics of the prop in multiple dimensions. Therefore, the electronic equipment is visual and visual in image and can be convenient for a user to check by displaying summarized data such as the total number of props in the script to be processed and the prop ratio of each category, and further the operation efficiency of the user can be improved.

In another possible implementation manner, the electronic device may also display the props in the scenario to be processed in a sorted manner, and specifically, the prop mining method may further include the following steps (9) to (10):

(9) Determining target evaluation parameters corresponding to all props in the target mention props; the target evaluation parameters are determined based on the correlation of the props and the to-be-processed script and the implantation scores of the props; the correlation and implantation scores are proportional to the target evaluation parameter.

In the embodiment of the present application, the target evaluation parameter may refer to an evaluation parameter value corresponding to the prop, for example, may be a grading value. The relevance may refer to the degree of relevance of the prop to the scenario to be processed, and the implantation score may refer to implantation score or implantation value corresponding to the prop. The electronic equipment can determine the target evaluation parameters based on the correlation degree of the props and the script to be processed and simultaneously combining the implantation scores of the props. The higher the correlation degree of the props and the script to be processed is, the higher the implantation score of the props is, and the higher the target evaluation parameters are. Specifically, when determining the target evaluation parameter, the electronic device may use a weighted summation manner, or may introduce other parameters, for example, calculating the target evaluation parameter such as prop cost, which is not limited in the embodiment of the present application.

(10) And displaying the target mentioned props and the target associated props according to the order of the target evaluation parameters from large to small.

In the embodiment of the application, after the target evaluation parameters of all the props are determined, the electronic equipment can display the props mentioned by the targets and the props associated with the targets in a sequence from big to small according to the target evaluation parameters. Therefore, a user can conveniently and intuitively check related props with higher implantation values in the script to be processed, and further the working efficiency of the user is improved.

In one possible implementation manner, the electronic device can also provide a script segment link jump function in the prop summary page, that is, after the user clicks the link corresponding to the prop, the electronic device can directly jump to the script segment corresponding to the prop, so that the user can conveniently check the script segment. Specifically, the scenario property excavation method may further include the following steps:

(11) Determining the associated field times corresponding to the target-mentioned props and the associated field times corresponding to the target-associated props; the scenario to be processed comprises a plurality of occasions, and each occasion corresponds to one scenario segment.

In the embodiment of the application, the scenario to be processed can be divided into a plurality of fields, for example, the scenario to be processed can comprise a first screen third field, a second screen fourth field and the like, and each field can correspond to a scenario segment. Associated shots may refer to shots in which the target-mentioned prop is directly present or to shots in which the target-associated prop is directly associated. After determining that the object mentioned props are associated with the object, the electronic device can further determine the associated field times corresponding to the props.

(12) And displaying the object-mentioned props and the object-associated props, and displaying field links of associated fields corresponding to the props.

In the embodiment of the application, the session link may refer to a jump link corresponding to the associated session. When the electronic equipment displays the target mentioned props and the target associated props, field links of at least one associated field corresponding to each props can be displayed at the same time.

(13) And responding to the touch operation for the scene link, and displaying the script fragment corresponding to the scene link selected by the touch operation.

In the embodiment of the application, when a user needs to check the occurrence of the prop or the associated script fragment original text, the corresponding scene links of the prop can be controlled in the prop summarization page; the electronic equipment responds to the touch operation, can display the script fragment corresponding to the scene link determined by the touch operation, is convenient for viewing, can simplify the operation of a user, does not need the user to search manually, and can improve the use experience of the user.

Illustratively, FIG. 5 is a schematic diagram of a prop summary page provided by an exemplary embodiment of the present application. As shown in fig. 5, in the prop summary page, the electronic device respectively classifies and displays the target-mentioned props and the target-associated props (two sub-pages are adopted for display), and in fig. 5, prop summary data of the target-mentioned props is shown. When the user needs to switch to the target association, the interactable control corresponding to the target association in the collection page of the target association can be touched, and the electronic equipment can display the collection total data sub page of the target association.

As shown in fig. 5, in the total data sub-page of the object-mentioned props, the electronic device displays all object categories of the object-mentioned props, the total number of the object-mentioned props, and the total number of the object-mentioned props in the scenario to be processed, and also displays the prop ratios of the respective object categories, for example, the prop ratio of the "oven" is 23.9%, the prop ratio of the "bookshelf" is 16.5%, the prop ratio of the "cabinet" is 12.9%, and so on. The electronic equipment displays a search control in the prop summarizing page, so that a user can directly input a prop name to search and select prop categories to screen, and the operation of the user is facilitated.

After the user selects to display the target mention props, the electronic device displays the target mention props selected by the user one by one in the prop summary page, and the user can click a cancel selection control to cancel the display of the target mention props. When displaying the object-mention prop, the electronic device displays the object category and the frequency of occurrence to which the object-mention prop belongs, and also displays the number of times the object-mention prop appears and the links of the object shots (mention shots 1-5, 2-30, etc. as shown in fig. 6). When a user needs to check script corresponding to the target-mentioned prop, the user can touch the target scene link, and the electronic equipment responds to the touch operation, can display script fragments corresponding to the target scene link, and is convenient for the user to check.

In another possible implementation, the electronic device may also display a scenario information query page (or scenario element summary page) that may be used to present summary data of scenario elements in the scenario to be processed. Specifically, the scenario property excavation method may further include the following steps:

(14) And displaying a preset file generation control.

(15) And responding to touch operation of a control generated for a preset file, and disassembling the scenario to be processed into scenario fragments corresponding to each occasion.

(16) And generating a script dismantling file according to the script fragments corresponding to each occasion and the target mention props and target association props corresponding to each occasion.

In the embodiment of the present application, the preset file generation control may refer to a preset touch button for generating a scenario disassembly file. The scenario dismantling file may refer to a file formed after the scenario is dismantled according to the number of occasions, and specifically may refer to a scenario dismantling table and the like. The scenario dismantling file can comprise each session in the scenario to be processed, and the target mention props and target association props corresponding to each session.

In this step, the electronic device may display a preset file generation control in the scenario element summary page. When a user needs to generate or export a script dismantling file, the preset file generation control can be touched; the electronic equipment responds to touch operation of a control generated aiming at a preset file, the scenario to be processed can be split according to the scenes, meanwhile, the target mention props and target association props corresponding to all the scenes are determined, and then scenario dismantling files comprising all the scenes of the scenario to be processed can be generated and displayed, so that a user can conveniently carry out subsequent processing. Thus, in the embodiment of the application, the user can export the script dismantling file by one key, so that the operation of the user is simplified, and the operation efficiency of the user is improved.

Fig. 6 is a schematic diagram of a scenario information query page according to an exemplary embodiment of the present application. As shown in fig. 6, the electronic device may display summary data of different scenario elements through a plurality of sub-pages in the scenario information query page (scenario scene distribution sub-page and character sub-page in fig. 6). In the sub-page of the scenario distribution, the electronic device displays the total set number of the scenario to be processed, the total number of occasions, the day-to-night-play (day Jing Yejing) duty ratio, the inside-field-to-outside-field duty ratio, and the like. The electronic device also displays the proportion of each scenario, for example, the proportion corresponding to the XX bar is 40%, the proportion corresponding to the XX pub is 25%, and the like, and meanwhile, the electronic device also displays the number of scenes of more small scenes in each scenario, for example, the number of scenes outside the XX bar, the number of scenes in the XX bar open-air area, and the like in the scenario information inquiry page. In addition, the electronic equipment also displays a preset file generation control in the script element summary page, when a user needs to acquire a script dismantling file, the preset file generation control can be touched, the electronic equipment can generate the script dismantling file, and the operation of the user is convenient.

In another possible implementation manner, the electronic device may also display a labeling page, so that the user may screen and locate the scenario to be processed according to a specific dimension, jump to a corresponding scenario segment, and facilitate the user to view. The script item mining method can further comprise the following steps:

(17) Displaying the labeling page; the labeling page comprises a search control; the search controls include a text input control and a search dimension control.

In the embodiment of the application, the labeling page can refer to a page used for labeling by a user. The search control may refer to a preset interactable control for conducting a search. The search controls may include a text input control and a search dimension control. The text input control can be a text input box, and a user can directly input text to search; the search dimension control may display multiple dimensions, where a user may select at least one dimension to screen a scenario to be processed, and the multiple dimensions may specifically include scenario scenes, personas, plot features, keywords, and the embodiment of the present application is not limited thereto.

(18) And determining a target script fragment corresponding to the touch operation from script fragments corresponding to each scene in the script to be processed in response to the touch operation for the text input control and/or in response to the touch operation for the search dimension control.

(19) And displaying the target script fragment, and displaying the target mention props and the target association props corresponding to the field times of the target script fragment.

In the embodiment of the application, the target scenario segment may refer to a scenario segment determined by the electronic device based on a touch operation of a user. The electronic device responds to touch operation of a user, and can determine the target script fragment from the script to be processed based on search text input by the user and/or search dimension selected by the user. And then the electronic equipment can display the target script fragment, and display the target mention props and the target association props associated with the scene where the target script fragment is positioned, so that the user can conveniently view and analyze the target script fragment.

In analyzing a scenario, a user typically needs to determine a scenario section capable of merchandise implantation, which may be referred to as open, in addition to the analysis of the prop. In the related art, a user can only determine the opening in the scenario to be processed in a manual reading mode, which is time-consuming and labor-consuming.

In the embodiment of the application, the user can realize automatic screening analysis on the script by inputting the search text or selecting the search dimension and other touch operations based on the search control in the annotation page, the electronic equipment responds to the touch operations and can rapidly screen out the target script fragment based on the search text or the search dimension, and the user can further determine whether to take the target script fragment as an opening, so that the user does not need to carefully read the script to be processed, and the processing efficiency is improved.

(20) And displaying a preset remark control and a preset adding control.

(21) And responding to the input operation of the preset remark control, determining remark information corresponding to the input operation, and associating the remark information with the target script fragment.

(22) And responding to touch operation aiming at a preset adding control, and adding the target script fragment corresponding to the touch operation to the candidate fragment list.

In the embodiment of the application, after the electronic device displays the target script fragment in the annotation page, the electronic device can also display a preset remark control and a preset adding control. The preset remark control can be used for acquiring remark information input by a user; the preset add control may be used to add the target scenario segment to an alternative segment list, which may refer to an alternative scenario segment list for open implantation.

In this step, after the electronic device determines the target scenario segment based on the input operation of the user on the search control, the target scenario segment may be displayed, and simultaneously, the preset notes control and the preset add control may be displayed. The electronic device may obtain remark information input by the user in response to an input operation of the preset remark control by the user, and correlate the remark information with the target scenario segment. The electronic device can also respond to the touch operation of the user on the preset adding control to quickly add the target script fragment to the alternative fragment list, so that the efficiency of determining the opening by the user can be improved.

Illustratively, fig. 7 is a schematic diagram of a labeling page according to an exemplary embodiment of the present application. As shown in fig. 7, the electronic device displays a search control in the annotation page that includes a search text input control 701 and a search dimension control 702. The user may input search text in search text input control 701 to search, or may determine the dimensions to be screened in search dimension control 702. The electronic equipment determines and displays the target script fragment based on the touch operation of the user on the search control, and simultaneously displays the target mention props and the target association props corresponding to the target script fragment.

In addition, the electronic equipment also displays a preset remark control and a preset addition control in the annotation page. When the user needs to annotate the target script fragment, the remark information can be input by touching the preset remark control, and the electronic equipment can acquire the remark information and associate the remark information with the target script fragment based on the input operation of the user. When the user needs to add the target scenario segment to the alternative segment list (alternative proposal in fig. 7), a preset adding control may be touched, the electronic device may add the target scenario segment to the alternative segment list in response to the touch operation, and the user may click on the alternative segment list to view the target scenario segment that has been selected. Therefore, the electronic equipment automatically locates to the corresponding target script fragment based on the search operation of the user by displaying the labeling page, and meanwhile, the one-key addition of the alternative proposal can be realized, so that the operation of the user can be simplified, and the working efficiency of the user can be improved.

It should be understood that, in the embodiments of the present application, the sequence number of each step does not mean the sequence of execution, and the execution sequence of each step should be determined by the function and the internal logic of each step, and should not limit the implementation process of the embodiments of the present application in any way.

Based on the above embodiment, in one possible implementation manner, the electronic device may further display a project management page of the scenario to be processed, so that a user may manage each scenario to be processed in a unified manner. Fig. 8 is a schematic diagram of a scenario project management page according to an exemplary embodiment of the present application. As shown in fig. 8, the electronic device may display a plurality of processing items of the scenario to be processed in the item management page. The project management page comprises a plurality of interactable controls, wherein the script information controls are used for jumping to a script information inquiry page; the prop summarization control is used for jumping to a script prop summarization page; the annotation page can be used to jump to the annotation page; rights management may be used to set the operational rights of the script to be processed, etc. In addition, the user can also touch and control to create project controls, and new to-be-processed scripts are added to excavate props; when the number of the items is large, the user can input names of the to-be-processed script through the search control to search the items. Therefore, through the project management page displayed by the electronic equipment, a user can uniformly manage a plurality of processing projects of the script to be processed, so that the operation of the user is simplified, and the operation efficiency of the user is improved.

On the basis of the above embodiment, fig. 9 is a schematic technical link diagram of a scenario property mining method according to an exemplary embodiment of the present application. As shown in fig. 9, the electronic device first acquires a scenario to be processed; the electronic equipment extracts the mentioned props in the to-be-processed script based on the script content of the to-be-processed script through the prop identification model on one hand, and obtains the target mentioned props; on the other hand, the electronic equipment extracts the script elements in the script to be processed, performs mapping matching on the script elements based on a matching strategy, determines target elements in a preset prop knowledge base, and can further take props corresponding to the target elements as target association props. After the target mention props and the target association props are obtained, the electronic equipment can carry out post-treatment on the target mention props and the target association props, for example, classification fusion can be carried out, and sorting can be carried out based on target evaluation parameters; finally, the electronic device can display the target mentioned props and the target associated props, and particularly can display a prop summarizing page, a labeling page, a script information inquiring page and the like.

In the embodiment of the application, the electronic equipment excavates the target associated prop by combining the association matching based on the script elements with the preset prop knowledge base, thereby improving recall of the implicit prop; when the preset prop knowledge base is established, mediums such as scripts, tablets and the like are analyzed, the preset prop knowledge base is established based on event, character and scene knowledge of a plurality of content sources such as scripts, tablets and the like, the comprehensiveness and richness of the knowledge base can be improved, and then the comprehensiveness of the script prop excavation can be improved.

On the basis of the above embodiment, fig. 10 is a logic schematic diagram of a scenario property mining method according to an exemplary embodiment of the present application. As shown in fig. 10, for scenario content of a scenario to be processed, the electronic device may determine, based on the item identification model, that an object in the scenario to be processed refers to an item. The electronic device may further extract scenario elements in the scenario to be processed based on an information identification model, where the information identification model may be a preset scenario element extraction model, and may specifically include a scene identification model, a scenario collision intensity identification model, and the like, and in a possible implementation manner, the information identification model may also include a prop identification model. After determining the script element, the electronic device may determine the target association based on the script element and a preset prop knowledge base. The preset prop knowledge base may include a script knowledge base and a filmed knowledge base. The film knowledge base can be from two kinds of maps, one is a film and television content element map, wherein the film and television content element map can comprise the placement props appearing in various scene environments in the broadcasted film and television theatre, and the other map can be other maps, such as which props are included in various common actual scenes. The knowledge base can establish the corresponding relation between preset elements and props based on algorithm models such as visual scene recognition, target detection, action recognition and the like. After the electronic equipment determines the object-mentioned props and the object-associated props, a script dismantling file (a script dismantling table in fig. 10) can be generated, and finally summarized data of the object-mentioned props and the object-associated props can be displayed, so that suggestions are provided for prop implantation and open implantation of users, and the operation of the users is simplified.

In a possible implementation manner, the scenario item mining method in the embodiment of the present application may be implemented based on electronic device platform software, and specifically may include a platform end, an intermediate end and a merchant end. The platform end can be used for creating and executing processing projects of the to-be-processed script and performing project management and task allocation; the intermediate end specifically refers to an agent end and can perform operations such as checking and inquiring of the scenario to be processed; the platform end and the middle end are an internal and external co-operating system. The merchant terminal can check and inquire prop, determine implantable item information, commodity type and the like.

Fig. 11 is a schematic diagram of a scenario project page of a merchant end, where each scenario project issued by a platform end may be displayed in an electronic device, and at the same time, a property category corresponding to each scenario project is displayed, as shown in fig. 11. The script project page may be a 5 th generation internet hypertext markup language page (Hyper Text Markup Language, HTML 5). After clicking a scenario item, the electronic device can display detailed information of the scenario item, such as scenario introduction (e.g., scenario introduction, shooting time, etc.), item category, specific item, etc., and the user can quickly acquire relevant information.

According to the script property mining method, script dismantling capability is high, and success rate of script element identification is high. Specifically, the dismantling success rate can reach 85.2%, the scene accuracy can reach 100%, the name recognition accuracy can reach 99%, and the character recognition accuracy in the scene can reach 90.7%. In addition, the electronic equipment in the embodiment of the application can automatically excavate the script and the property without manual reading and manual recording of the script by a user, thereby improving the efficiency of excavating the script and the property and saving the time of the user.

Fig. 12 is a schematic structural diagram of a scenario prop excavating device according to an exemplary embodiment of the present application, please refer to fig. 12, wherein scenario prop excavating device 120 includes:

an obtaining module 121, configured to obtain a scenario to be processed, and extract scenario elements in the scenario to be processed;

a first determining module 122, configured to determine, according to the scenario element, a target element that matches the scenario element in a preset prop knowledge base;

the second determining module 123 is configured to determine, according to the target element and the preset prop knowledge base, a target associated prop corresponding to the scenario to be processed.

In one possible implementation, the first determining module 122 is specifically configured to:

In one possible implementation, the apparatus 120 further includes:

In one possible implementation, the apparatus 120 is further configured to:

displaying a preset file generation control;

In one possible implementation, the apparatus 120 is further configured to:

displaying a preset remark control and a preset adding control;

The scenario property excavating device 120 provided in the embodiment of the present application may execute the technical scheme shown in the above method embodiment, and its implementation principle and beneficial effects are similar, and will not be described herein.

Fig. 13 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application, referring to fig. 13, the electronic device 130 may include a processor 131 and a memory 132. The processor 131 and the memory 132 are illustratively interconnected by a bus 133.

Memory 132 stores computer-executable instructions;

processor 131 executes computer-executable instructions stored in memory 132, causing processor 131 to perform the scenario item mining method as described in the method embodiments above.

Accordingly, an embodiment of the present application provides a computer readable storage medium, in which computer executable instructions are stored, for implementing the scenario item mining method of the above method embodiment when the computer executable instructions are executed by a processor.

Correspondingly, the embodiment of the application also provides a computer program product, comprising a computer program, wherein the computer program can realize the scenario item mining method shown in the embodiment of the method when being executed by a processor.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors, input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that 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 one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims

1. The script item excavating method is characterized by comprising the following steps of:

determining target elements matched with the script elements in a preset prop knowledge base according to the script elements;

determining a target association prop corresponding to the scenario to be processed according to the target element and the preset prop knowledge base;

and determining target elements matched with the script elements in a preset prop knowledge base according to the script elements, wherein the method comprises the following steps:

carrying out synonym rewriting on the script elements, and determining a plurality of script elements with the same meaning as the same alternative element;

determining the matching scores of the candidate elements and each preset element in a preset prop knowledge base; the preset prop knowledge base comprises a plurality of preset elements and props corresponding to the preset elements, and is a preset association prop knowledge base;

And determining the preset element with the matching score meeting the preset condition as the target element.

2. The method according to claim 1, wherein the method further comprises:

determining a target mention prop in the script to be processed based on a prop identification model;

and displaying the target mentioned props and the target associated props.

3. The method according to claim 2, wherein the method further comprises:

determining target categories corresponding to all props in the target mentioned props;

4. The method of claim 2, wherein the presenting the target-mentioned prop and the target-associated prop comprises:

determining target evaluation parameters corresponding to all props in the target mentioned props; the target evaluation parameters are determined based on the correlation of the props and the script to be processed and the implantation scores of the props; the correlation and the implantation score are in direct proportion to the target evaluation parameter, the correlation refers to the degree of correlation between the prop and the script to be processed, and the implantation score refers to implantation score or implantation value corresponding to the prop;

And displaying the target mentioned props and the target associated props according to the order of the target evaluation parameters from big to small.

5. The method of claim 2, wherein the scenario to be processed includes a plurality of shots, each shot corresponding to a scenario segment; the displaying the target-mentioned props and the target-associated props includes:

displaying the target mentioned props and the target associated props, and displaying field links of associated fields corresponding to each props;

6. The method of claim 5, wherein the method further comprises:

displaying a preset file generation control;

responding to touch operation of a control generated for the preset file, and disassembling the scenario to be processed into scenario fragments corresponding to each occasion;

and generating a script dismantling file according to the script fragments corresponding to each occasion and the target mention props and the target association props corresponding to each occasion.

7. The method of claim 4, wherein after said categorizing and fusing said target-mentioned props and said target-associated props according to said target category, said method further comprises:

determining the ratio of the number of props corresponding to each target class to the total number of props to obtain the corresponding prop ratio of each target class;

and displaying the total number of the props, the prop ratio corresponding to each target class and the number of props corresponding to each target class.

8. The method of claim 5, wherein the method further comprises:

displaying the labeling page; the annotation page comprises a search control; the search control comprises a text input control and a search dimension control;

responding to the touch operation of the text input control and/or responding to the touch operation of the search dimension control, and determining a target script fragment corresponding to the touch operation from script fragments corresponding to each scene in the script to be processed;

And displaying the target script fragment, and displaying the target mention props and the target association props corresponding to the scenes of the target script fragment.

9. The method of claim 8, wherein after the displaying the target scenario segment, the method further comprises:

displaying a preset remark control and a preset adding control;

responding to input operation of the preset remark control, determining remark information corresponding to the input operation, and associating the remark information with the target scenario segment;

and responding to the touch operation of the preset adding control, and adding the target script fragment corresponding to the touch operation into an alternative fragment list.

10. A scenario prop excavation device, comprising:

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a scenario to be processed and extracting scenario elements in the scenario to be processed;

the second determining module is used for determining a target association prop corresponding to the scenario to be processed according to the target element and the preset prop knowledge base;

The first determining module is specifically configured to:

11. An electronic device, comprising: a memory and a processor;

the memory stores computer-executable instructions;

the processor executing computer-executable instructions stored in the memory, causing the processor to perform the scenario item mining method of any one of claims 1 to 9.

12. A computer readable storage medium having stored therein computer executable instructions for implementing the scenario feature mining method of any one of claims 1 to 9 when the computer executable instructions are executed by a processor.