An intelligent creation analysis method and system based on knowledge graph

Abstract

The present invention discloses an intelligent creation analysis method and system based on knowledge graph, which belongs to the field of electronic data processing. The present invention obtains historical creation content of creators and historical creation content of other creators of creation themes, and imports them into the creation similarity acquisition strategy of similar creators to obtain the creation similarity of similar creators, imports the creation similarity of similar creators and the creation content of related creation themes of similar creators into a second content acquisition strategy to obtain the extraction probability of second acquired content, analyzes the acquisition value of the acquired content according to the extraction probability of the first acquired content and the extraction probability of the second acquired content, arranges the acquired content on the side of the creation content in descending order according to the acquisition value, the creator selects the acquired content required, and accurately identifies and searches the acquired content required in the creation process based on the constructed knowledge graph network.

Description

Technical Field

[0001] The present invention belongs to the field of electronic data processing, and specifically relates to an intelligent creation analysis method and system based on knowledge graph. Background Art

[0002] Intelligent creation refers to the use of artificial intelligence technology to assist the creative process and improve the efficiency and quality of creation. This usually involves the application of natural language processing, machine learning, deep learning and other technologies. The development of intelligent creation is constantly advancing, and there may be more innovative applications and scenarios in the future. At the same time, we also need to pay attention to the challenges and problems of AI creation in ethics, copyright, creative autonomy, etc.

[0003] In the process of intelligent creation analysis, it is often necessary to use the knowledge graph network to generate reference materials for the subsequent creation content based on the previous creation content. In the process of making reference materials, the existing technology usually uses creations with high similarity to the previous content as reference materials, but this does not take into account the creator's historical creation habits, thereby ignoring the impact of the creator's historical creation habits on the creation content, which in turn leads to low creation efficiency and creation accuracy. Most of the existing technologies have the above problems;

[0004] For example, a Chinese patent with application publication number CN117216233A discloses a script outline creation system based on artificial intelligence, which includes: the information recognition module is a preliminary analysis of the character information, object information and background information and their attributes in the picture through a convolutional neural network; the comprehensive analysis module is an in-depth analysis of the story type, protagonist and supporting roles and their interests in the script outline; the result output module is to first encode the relevant information of the picture analysis into words through a recurrent neural network, and then decode the relevant words to output the script outline. The above method applies artificial intelligence technology to the field of script outline creation, thereby assisting creators in their creation or providing them with creative inspiration;

[0005] The above patents all have the problems raised by this background technology. In order to solve the problems raised by this background technology, this application designs an intelligent creation analysis method and system based on knowledge graph. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention proposes an intelligent creation analysis method and system based on knowledge graph.

[0007] To achieve the above object, the present invention provides the following technical solution: an intelligent creation analysis method based on knowledge graph, which comprises the following specific steps:

[0008] Obtain relevant knowledge content about the creative topic, and build a knowledge graph network about the creative topic through relevant knowledge content;

[0009] Obtain the creation content and the creation personnel's historical creation content and import it into the first content acquisition strategy to obtain the extraction probability of the first acquisition content;

[0010] Obtain the historical creative content of the creator and the historical creative content of other creators of the creative theme, and import them into the creative similarity acquisition strategy of similar creators to obtain the creative similarity of similar creators;

[0011] Importing the creation similarity of similar creators and the creation content of related creation themes of similar creators into the second content acquisition strategy to obtain the extraction probability of the second acquired content;

[0012] Analyzing the acquisition value of the acquired content according to the acquired extraction probability of the first acquired content and the acquired extraction probability of the second acquired content;

[0013] Arrange the acquired contents in descending order according to the acquired values ​​on the creative content side, and the creator selects the acquired contents they need.

[0014] It should be noted here that as a preferred technical solution for an intelligent creation analysis method based on a knowledge graph, the specific steps of obtaining relevant knowledge content of a creation theme and constructing a knowledge graph network about the creation theme through the relevant knowledge content are as follows:

[0015] S11, obtaining the creative theme determined by the creator, segmenting the creative theme to obtain a number of theme keywords, and importing the obtained theme keywords into the retrieval system to obtain relevant knowledge content related to the theme keywords;

[0016] S12, all relevant knowledge contents about the subject keywords are acquired to construct a knowledge graph network about the creation subject;

[0017] It should be noted here that, as a preferred technical solution of an intelligent creation analysis method based on a knowledge graph, the acquisition of creation content and the importation of the creation personnel's historical creation content into the first content acquisition strategy to obtain the extraction probability of the first acquired content includes the following specific steps:

[0018] S21. Obtain the real-time creative content during the creation process, obtain the historical creative content of the creator in the knowledge graph, import the historical creative content of the creator in the acquired knowledge graph into the historical creative content extraction probability calculation formula to calculate the historical creative content extraction probability, where the i-th historical creative content extraction probability calculation formula is: Wherein, m() is the number of elements in the set in brackets, zi is the keyword set of the i-th historical creation content, and z is the keyword set of the real-time creation content during the creation process;

[0019] S22, obtaining the extraction probability of all historical creation contents, and comparing them with the set extraction probability threshold. If the extraction probability of the corresponding historical creation contents is greater than or equal to the set extraction probability threshold, the corresponding historical creation contents are set as the first acquired contents. If the extraction probability of the corresponding historical creation contents is less than the set extraction probability threshold, the corresponding historical creation contents are not set as the first acquired contents.

[0020] S23: Obtain extraction probabilities of all first acquired contents.

[0021] It should be noted here that as a preferred technical solution of an intelligent creation analysis method based on knowledge graph, the acquisition of the historical creation content of the creator and the historical creation content of other creators of the creation theme and importing them into the creation similarity acquisition strategy of similar creators to obtain the creation similarity of similar creators includes the following specific steps:

[0022] S31, obtaining the historical creative content of the creator and the historical creative content of other creators of the creative theme;

[0023] S32, substituting the obtained historical creative content of the creator and the historical creative content of other creators of the creative theme into the creative similarity calculation formula to calculate the creative similarity of similar creators, wherein the creative similarity calculation formula of the g-th similar creator is: Among them, N is the number of historical creations of the creator, Mg is the number of historical creations of the g-th similar creator, kc is the keyword set of the c-th historical creation content of the creator, and Kj is the keyword set of the j-th historical creation content of the g-th similar creator.

[0024] It should be noted here that, as a preferred technical solution of an intelligent creation analysis method based on a knowledge graph, the extraction probability of obtaining the second acquired content by importing the creation similarity of similar creators and the creation content of related creation themes of similar creators into the second content acquisition strategy includes the following specific contents:

[0025] The calculated creative similarities of all similar creators are obtained, and at the same time, the creative contents of the relevant creative themes of the similar creators are obtained, wherein the relevant creative themes are the creative themes of the similar creators containing the keywords in the corresponding creative themes, and the creative similarities of all similar creators, the creative contents of the relevant creative themes of the similar creators, and the created contents of the creative themes are introduced into the second extraction probability calculation formula of the creative contents of the relevant creative themes to calculate the second extraction probability of the creative contents of the relevant creative themes, wherein the second extraction probability calculation formula of the creative contents of the xth relevant creative themes of the gth similar creators is: Among them, cgx is the keyword set of the creative content of the xth relevant creative theme of the gth similar creator. The calculated second extraction probability of the creative content of all relevant creative themes of all similar creators is compared with the set second extraction probability threshold. If the second extraction probability of the creative content of the corresponding relevant creative theme of the corresponding similar creator is greater than or equal to the set second extraction probability threshold, the creative content of the corresponding relevant creative theme of the corresponding similar creator is set as the second acquired content. If the second extraction probability of the creative content of the corresponding relevant creative theme of the corresponding similar creator is less than the set second extraction probability threshold, the creative content of the corresponding relevant creative theme of the corresponding similar creator is not set as the second acquired content.

[0026] It should be noted here that, as a preferred technical solution of the intelligent creation analysis method based on the knowledge graph, the analysis of the acquisition value of the acquired content according to the extraction probability of the first acquired content and the extraction probability of the second acquired content includes the following specific contents:

[0027] Obtain the extraction probabilities of all first acquired contents and all second acquired contents, substitute the obtained extraction probabilities of the first acquired contents and all second acquired contents into the acquired content acquisition value calculation formula to calculate the acquisition value of each acquired content, wherein the acquired content is any item in the set jointly constituted by the first acquired content and the second acquired content, wherein the acquisition value calculation formula of the vth acquired content is: Among them, Jv is the extraction probability of the vth acquired content, D is the number of the first acquired content, a is the proportion coefficient of the first acquired content, Td is the extraction probability of the dth first acquired content, S is the number of the second acquired content, and Bs is the extraction probability of the sth second acquired content.

[0028] It should be noted here that as a preferred technical solution for an intelligent creation analysis method based on a knowledge graph, the obtained content is arranged in descending order according to the obtained value on the creation content side, and the creator selects the required obtained content, including the following specific contents:

[0029] Obtain the calculated acquisition value of each acquisition content, compare the acquisition value of each acquisition content with the set acquisition threshold, obtain the acquisition content corresponding to the acquisition value greater than or equal to the set acquisition threshold, arrange the acquisition content corresponding to the acquisition value greater than or equal to the set acquisition threshold in descending order according to the acquisition value on the creative content side, and the creator selects the required acquisition content.

[0030] A knowledge graph-based intelligent creation analysis system, which is implemented based on the above-mentioned knowledge graph-based intelligent creation analysis method, and specifically includes a knowledge graph network construction module, a first content acquisition module, a creation similarity analysis module, a second content acquisition module, an acquisition value analysis module, a content selection module and a control module, wherein the knowledge graph network construction module is used to acquire relevant knowledge content of a creation theme, and construct a knowledge graph network about the creation theme through the relevant knowledge content;

[0031] The first content acquisition module is used to acquire the creation content and the creation personnel's historical creation content and import them into the first content acquisition strategy to obtain the extraction probability of the first acquired content;

[0032] The creation similarity analysis module is used to obtain the historical creation content of the creator and the historical creation content of other creators of the creation theme, and import them into the creation similarity acquisition strategy of similar creators to obtain the creation similarity of similar creators;

[0033] The second content acquisition module is used to import the creation similarity of similar creators and the creation content of related creation themes of similar creators into the second content acquisition strategy to obtain the extraction probability of the second acquired content;

[0034] The acquisition value analysis module is used to analyze the acquisition value of the acquisition content according to the acquired extraction probability of the first acquisition content and the extraction probability of the second acquisition content;

[0035] The content selection module is used to arrange the acquired content in descending order according to the acquired value on the side of the creative content, so that the creator can select the acquired content they need;

[0036] The control module is used to control the operation of the graph knowledge graph network construction module, the first content acquisition module, the creation similarity analysis module, the second content acquisition module, the acquisition value analysis module and the content selection module.

[0037] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0038] The processor executes the above-mentioned intelligent creation analysis method based on knowledge graph by calling the computer program stored in the memory.

[0039] A computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute an intelligent creation analysis method based on a knowledge graph as described above.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention obtains relevant knowledge content of a creative theme, constructs a knowledge graph network about the creative theme through the relevant knowledge content, obtains creative content and historical creative content of creators, and imports them into a first content acquisition strategy to obtain the extraction probability of a first acquired content, obtains historical creative content of creators and historical creative content of other creators of the creative theme, and imports them into a creative similarity acquisition strategy of similar creators to obtain the creative similarity of similar creators, imports the creative similarity of similar creators and creative content of related creative themes of similar creators into a second content acquisition strategy to obtain the extraction probability of a second acquired content, analyzes the acquisition value of the acquired content based on the acquired extraction probability of the first acquired content and the extraction probability of the second acquired content, arranges the acquired content on the side of the creative content in descending order according to the acquisition value, the creator selects the acquired content needed, and based on the constructed knowledge graph network, accurately identifies and searches the acquired content needed in the creative process, assists the creative process, and improves the creative efficiency and the accuracy of the creation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a schematic diagram of the overall process of an intelligent creation analysis method based on knowledge graph in the present invention;

[0043] Figure 2 This is a schematic diagram of step S2 of an intelligent creation analysis method based on knowledge graph of the present invention;

[0044] Figure 3 This is a schematic diagram of the overall framework of an intelligent creation analysis system based on knowledge graph in the present invention; DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present application and its application or use.

[0046] Example 1

[0047] In order to solve the technical problems raised in the background technology, the present invention provides a preferred embodiment: Figure 1-Figure 2 As shown, an intelligent creation analysis method based on knowledge graph includes the following specific steps:

[0048] Obtain relevant knowledge content about the creative topic, and build a knowledge graph network about the creative topic through relevant knowledge content;

[0049] Obtain the creation content and the creation personnel's historical creation content and import it into the first content acquisition strategy to obtain the extraction probability of the first acquisition content;

[0050] Obtain the historical creative content of the creator and the historical creative content of other creators of the creative theme, and import them into the creative similarity acquisition strategy of similar creators to obtain the creative similarity of similar creators;

[0051] Importing the creation similarity of similar creators and the creation content of related creation themes of similar creators into the second content acquisition strategy to obtain the extraction probability of the second acquired content;

[0052] Analyzing the acquisition value of the acquired content according to the acquired extraction probability of the first acquired content and the acquired extraction probability of the second acquired content;

[0053] Arrange the acquired contents in descending order according to the acquired values ​​on the side of the creative contents, and the creators select the acquired contents they need;

[0054] Among them, in this embodiment, the specific steps of obtaining relevant knowledge content of the creation theme and constructing a knowledge graph network about the creation theme through the relevant knowledge content are:

[0055] S11, obtaining the creative theme determined by the creator, segmenting the creative theme to obtain a number of theme keywords, and importing the obtained theme keywords into the retrieval system to obtain relevant knowledge content related to the theme keywords;

[0056] Segmenting creative topics and extracting keywords is a key step in creative analysis and answering questions. The following is a simplified process for extracting keywords from creative topics and answering questions:

[0057] 1. Determine the topic: First, you need to clarify the topic of your creation. For example, the topic may be "Application of artificial intelligence in the medical field";

[0058] 2. Word segmentation: Perform Chinese word segmentation on the subject sentence. Chinese word segmentation is to divide continuous text into meaningful phrases or single words. In Chinese, there is no space between words, so it is necessary to use word segmentation tools such as Jieba, HanLP, etc. The word segmentation results may be as follows:

[0059] Artificial Intelligence / Medical Field / Application;

[0060] 3. Extract keywords: Extract keywords from the word segmentation results. Keywords are usually words that express the core meaning of the topic. In the above example, the keywords may be:

[0061] AI

[0062] Medical field

[0063] application;

[0064] 4. Understand the meaning of keywords: Have an in-depth understanding of each keyword, including its definition, related concepts, application scenarios, etc.;

[0065] Through the above steps, keywords can be extracted from the creative theme, which can accurately and comprehensively reflect the meaning of the creative theme;

[0066] S12, all relevant knowledge contents about the subject keywords are acquired to construct a knowledge graph network about the creation subject;

[0067] Building a knowledge graph network about a creative topic follows these steps:

[0068] 1. Determine the scope of the topic: clarify what areas of knowledge the knowledge graph will cover. For example, if the topic is "Application of artificial intelligence in the medical field", then the knowledge graph should include knowledge in related fields such as artificial intelligence, medical care, disease diagnosis, and drug development.

[0069] 2. Data collection: Collect data related to the topic. This data can come from books, academic papers, websites, news reports, etc. Data collection should be comprehensive to ensure the breadth and accuracy of the knowledge graph.

[0070] 3. Data preprocessing: Clean and preprocess the collected data, including removing noise, unifying the format, eliminating duplication, etc.

[0071] 4. Entity recognition: Identify key entities from the data, such as people, places, organizations, events, etc. In the topic of "Application of artificial intelligence in the medical field", entities may include diseases, drugs, medical devices, research institutions, etc.

[0072] 5. Relationship extraction: Determine the relationships between entities. These relationships can be "belongs to", "treats", "studies", etc. In the knowledge graph, these relationships form a network between entities.

[0073] 6. Attribute extraction: Extract attributes for entities, such as the ingredients of drugs, specifications of medical equipment, etc.

[0074] 7. Build a knowledge graph: Use the extracted entities, relationships, and attributes to build a knowledge graph. Knowledge graphs are usually stored in the form of graphs, where nodes represent entities and edges represent relationships.

[0075] In this embodiment, obtaining the creation content and the creation personnel's historical creation content into the first content acquisition strategy to obtain the extraction probability of the first acquisition content includes the following specific steps:

[0076] S21. Obtain the real-time creative content during the creation process, obtain the historical creative content of the creator in the knowledge graph, import the historical creative content of the creator in the acquired knowledge graph into the historical creative content extraction probability calculation formula to calculate the historical creative content extraction probability, where the i-th historical creative content extraction probability calculation formula is: Wherein, m() is the number of elements in the set in brackets, zi is the keyword set of the i-th historical creation content, and z is the keyword set of the real-time creation content during the creation process;

[0077] S22, obtaining the extraction probability of all historical creation contents, and comparing them with the set extraction probability threshold. If the extraction probability of the corresponding historical creation contents is greater than or equal to the set extraction probability threshold, the corresponding historical creation contents are set as the first acquired contents. If the extraction probability of the corresponding historical creation contents is less than the set extraction probability threshold, the corresponding historical creation contents are not set as the first acquired contents.

[0078] S23: Obtain extraction probabilities of all first acquired contents.

[0079] In this embodiment, obtaining the historical creation content of the creator and the historical creation content of other creators of the creation theme and importing them into the creation similarity acquisition strategy of similar creators to obtain the creation similarity of similar creators includes the following specific steps:

[0080] S31, obtaining the historical creative content of the creator and the historical creative content of other creators of the creative theme;

[0081] S32, substituting the obtained historical creative content of the creator and the historical creative content of other creators of the creative theme into the creative similarity calculation formula to calculate the creative similarity of similar creators, wherein the creative similarity calculation formula of the g-th similar creator is: Among them, N is the number of historical creations of the creator, Mg is the number of historical creations of the g-th similar creator, kc is the keyword set of the c-th historical creation content of the creator, and Kj is the keyword set of the j-th historical creation content of the g-th similar creator.

[0082] In this embodiment, the creation similarity of similar creators and the creation content of related creation themes of similar creators are imported into the second content acquisition strategy to obtain the extraction probability of the second acquired content, including the following specific contents:

[0083] The calculated creative similarities of all similar creators are obtained, and at the same time, the creative contents of the relevant creative themes of the similar creators are obtained. The relevant creative themes are the creative themes of similar creators containing the keywords in the corresponding creative themes. The obtained creative similarities of all similar creators, the creative contents of the relevant creative themes of similar creators, and the created contents of the creative themes are introduced into the second extraction probability calculation formula of the creative contents of the relevant creative themes to calculate the second extraction probability of the creative contents of the relevant creative themes. Among them, the second extraction probability calculation formula of the creative contents of the xth relevant creative themes of the gth similar creator is: Among them, cgx is the keyword set of the creative content of the xth relevant creative theme of the gth similar creator. The calculated second extraction probability of the creative content of all relevant creative themes of all similar creators is compared with the set second extraction probability threshold. If the second extraction probability of the creative content of the corresponding relevant creative theme of the corresponding similar creator is greater than or equal to the set second extraction probability threshold, the creative content of the corresponding relevant creative theme of the corresponding similar creator is set as the second acquired content. If the second extraction probability of the creative content of the corresponding relevant creative theme of the corresponding similar creator is less than the set second extraction probability threshold, the creative content of the corresponding relevant creative theme of the corresponding similar creator is not set as the second acquired content.

[0084] In this embodiment, the analysis of the acquisition value of the acquired content according to the acquired extraction probability of the first acquired content and the acquired extraction probability of the second acquired content includes the following specific contents:

[0085] Obtain the extraction probabilities of all first acquired contents and all second acquired contents, substitute the obtained extraction probabilities of the first acquired contents and all second acquired contents into the acquired content acquisition value calculation formula to calculate the acquisition value of each acquired content, wherein the acquired content is any item in the set jointly constituted by the first acquired content and the second acquired content, wherein the acquisition value calculation formula of the vth acquired content is: Among them, Jv is the extraction probability of the vth acquired content, D is the number of the first acquired content, a is the proportion coefficient of the first acquired content, Td is the extraction probability of the dth first acquired content, S is the number of the second acquired content, and Bs is the extraction probability of the sth second acquired content.

[0086] In this embodiment, the acquired contents are arranged in descending order according to the acquired values ​​on the creative content side, and the creator selects the acquired contents required, including the following specific contents:

[0087] Obtain the calculated acquisition value of each acquisition content, compare the acquisition value of each acquisition content with the set acquisition threshold, obtain the acquisition content corresponding to the acquisition value greater than or equal to the set acquisition threshold, arrange the acquisition content corresponding to the acquisition value greater than or equal to the set acquisition threshold in descending order according to the acquisition value on the creative content side, and the creator selects the required acquisition content.

[0088] It should be noted here that the value-taking method of the set extraction probability threshold, the second extraction probability threshold, the proportion coefficient of the first acquired content and the set acquisition threshold in this embodiment is: obtained by technical personnel in this field based on experiments, and the preferred experimental acquisition method is: obtain 5000 sets of creative data, import the creative data into the acquisition value calculation formula for acquiring the content, calculate the acquisition value of the acquired content, and substitute it into the fitting software to obtain the set extraction probability threshold, the second extraction probability threshold, the proportion coefficient of the first acquired content and the set acquisition threshold with the highest selection accuracy.

[0089] It should be noted in this embodiment that the advantages of this embodiment over the prior art are: obtaining relevant knowledge content of the creative theme, constructing a knowledge graph network about the creative theme through the relevant knowledge content, obtaining the creative content and the creator's historical creative content and importing them into the first content acquisition strategy to obtain the extraction probability of the first acquired content, obtaining the creator's historical creative content and the historical creative content of other creators of the creative theme and importing them into the creative similarity acquisition strategy of similar creators to obtain the creative similarity of similar creators, importing the creative similarity of similar creators and the creative content of related creative themes of similar creators into the second content acquisition strategy to obtain the extraction probability of the second acquired content, analyzing the acquisition value of the acquired content based on the acquired extraction probability of the first acquired content and the extraction probability of the second acquired content, arranging the acquired content on the side of the creative content in descending order according to the acquisition value, the creator selects the required acquired content, and accurately identifies and searches the acquired content required in the creative process based on the constructed knowledge graph network, thereby assisting the creative process and improving the creative efficiency and accuracy.

[0090] Example 2

[0091] like Figure 3 As shown, a knowledge graph-based intelligent creation analysis system is implemented based on the above-mentioned knowledge graph-based intelligent creation analysis method, which specifically includes a knowledge graph network construction module, a first content acquisition module, a creation similarity analysis module, a second content acquisition module, an acquisition value analysis module, a content selection module and a control module, wherein the knowledge graph network construction module is used to acquire relevant knowledge content of the creation theme, and construct a knowledge graph network about the creation theme through the relevant knowledge content;

[0092] A first content acquisition module is used to acquire the creation content and the creation personnel's historical creation content and import them into the first content acquisition strategy to obtain the extraction probability of the first acquisition content;

[0093] A creative similarity analysis module is used to obtain the historical creative content of the creator and the historical creative content of other creators of the creative theme, and import them into the creative similarity acquisition strategy of similar creators to obtain the creative similarity of similar creators;

[0094] A second content acquisition module, used for importing the creation similarity of similar creators and the creation content of related creation themes of similar creators into a second content acquisition strategy to obtain an extraction probability of the second acquired content;

[0095] An acquisition value analysis module, used to analyze the acquisition value of the acquisition content according to the acquired extraction probability of the first acquisition content and the extraction probability of the second acquisition content;

[0096] The content selection module is used to arrange the acquired content in descending order according to the acquired value on the side of the creative content, so that the creator can select the acquired content they need;

[0097] The control module is used to control the operation of the graph knowledge graph network construction module, the first content acquisition module, the creation similarity analysis module, the second content acquisition module, the acquisition value analysis module and the content selection module.

[0098] Example 3

[0099] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0100] The processor executes the above-mentioned intelligent creation analysis method based on knowledge graph by calling the computer program stored in the memory.

[0101] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement an intelligent creation analysis method based on a knowledge graph provided in the above method embodiment. The electronic device may also include other components for implementing the functions of the device. For example, the electronic device may also have components such as a wired or wireless network interface and an input / output interface to input and output data. This embodiment will not be described in detail here.

[0102] Example 4

[0103] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0104] When the computer program runs on a computer device, the computer device executes the above-mentioned intelligent creation analysis method based on the knowledge graph.

[0105] For example, the computer readable storage medium can be a read-only memory, a random access memory, a read-only CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0106] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

Claims

1. An intelligent creation analysis method based on knowledge graph, characterized in that: It includes the following specific steps: Obtain relevant knowledge content about the creative topic, and build a knowledge graph network about the creative topic through relevant knowledge content; Obtain the creation content and the creation personnel's historical creation content and import it into the first content acquisition strategy to obtain the extraction probability of the first acquisition content; Obtain the historical creative content of the creator and the historical creative content of other creators of the creative theme, and import them into the creative similarity acquisition strategy of similar creators to obtain the creative similarity of similar creators; Importing the creation similarity of similar creators and the creation content of related creation themes of similar creators into the second content acquisition strategy to obtain the extraction probability of the second acquired content; Analyzing the acquisition value of the acquired content according to the acquired extraction probability of the first acquired content and the acquired extraction probability of the second acquired content; Arrange the acquired contents in descending order according to the acquired values ​​on the side of the creative contents, and the creators select the acquired contents they need; The analysis of the acquisition value of the acquired content according to the acquired extraction probability of the first acquired content and the acquired extraction probability of the second acquired content includes the following specific contents: Obtain the extraction probabilities of all first acquired contents and all second acquired contents, substitute the obtained extraction probabilities of the first acquired contents and all second acquired contents into the acquired content acquisition value calculation formula to calculate the acquisition value of each acquired content, wherein the acquired content is any item in the set jointly constituted by the first acquired content and the second acquired content, wherein the acquisition value calculation formula of the vth acquired content is: Among them, Jv is the extraction probability of the vth acquired content, D is the number of the first acquired content, a is the proportion coefficient of the first acquired content, Td is the extraction probability of the dth first acquired content, S is the number of the second acquired content, and Bs is the extraction probability of the sth second acquired content.

2. The intelligent creation analysis method based on knowledge graph according to claim 1, characterized in that: The method of acquiring the creation content and the creation personnel's historical creation content and importing it into the first content acquisition strategy to obtain the extraction probability of the first acquired content includes the following specific steps: Obtain the real-time creative content during the creation process, obtain the historical creative content of the creator in the knowledge graph, import the historical creative content of the creator in the acquired knowledge graph into the historical creative content extraction probability calculation formula to calculate the historical creative content extraction probability, where the calculation formula for the i-th historical creative content extraction probability is: Wherein, m() is the number of elements in the set in brackets, zi is the keyword set of the i-th historical creation content, and z is the keyword set of the real-time creation content during the creation process; Obtain the extraction probability of all historical creation contents, and compare them with the set extraction probability threshold. If the extraction probability of the corresponding historical creation contents is greater than or equal to the set extraction probability threshold, the corresponding historical creation contents are set as the first acquired contents. If the extraction probability of the corresponding historical creation contents is less than the set extraction probability threshold, the corresponding historical creation contents are not set as the first acquired contents. The extraction probabilities of all first-acquired contents are obtained.

3. The intelligent creation analysis method based on knowledge graph according to claim 2, characterized in that: The method of obtaining the historical creative content of the creator and the historical creative content of other creators of the creative theme and importing them into the creative similarity acquisition strategy of similar creators to obtain the creative similarity of similar creators includes the following specific steps: Obtain the historical creative content of the creator and the historical creative content of other creators of the creative subject; Substitute the obtained historical creation content of the creator and the historical creation content of other creators of the creation theme into the creation similarity calculation formula to calculate the creation similarity of similar creators, where the creation similarity calculation formula of the g-th similar creator is: Among them, N is the number of historical creations of the creator, Mg is the number of historical creations of the g-th similar creator, kc is the keyword set of the c-th historical creation content of the creator, and Kj is the keyword set of the j-th historical creation content of the g-th similar creator.

4. The method for intelligent creation analysis based on knowledge graph according to claim 3, characterized in that: The method of importing the creation similarity of similar creators and the creation content of related creation themes of similar creators into the second content acquisition strategy to obtain the extraction probability of the second acquired content includes the following specific contents: The calculated creative similarities of all similar creators are obtained, and at the same time, the creative contents of the relevant creative themes of the similar creators are obtained, wherein the relevant creative themes are the creative themes of the similar creators containing the keywords in the corresponding creative themes, and the creative similarities of all similar creators, the creative contents of the relevant creative themes of the similar creators, and the created contents of the creative themes are introduced into the second extraction probability calculation formula of the creative contents of the relevant creative themes to calculate the second extraction probability of the creative contents of the relevant creative themes, wherein the second extraction probability calculation formula of the creative contents of the xth relevant creative themes of the gth similar creators is: Among them, cgx is the keyword set of the creative content of the xth relevant creative theme of the gth similar creator. The calculated second extraction probability of the creative content of all relevant creative themes of all similar creators is compared with the set second extraction probability threshold. If the second extraction probability of the creative content of the corresponding relevant creative theme of the corresponding similar creator is greater than or equal to the set second extraction probability threshold, the creative content of the corresponding relevant creative theme of the corresponding similar creator is set as the second acquired content. If the second extraction probability of the creative content of the corresponding relevant creative theme of the corresponding similar creator is less than the set second extraction probability threshold, the creative content of the corresponding relevant creative theme of the corresponding similar creator is not set as the second acquired content.

5. The method for intelligent creation analysis based on knowledge graph according to claim 1, characterized in that: The obtained contents are arranged in descending order according to the obtained values ​​on the side of the creative contents, and the creator selects the required obtained contents, including the following specific contents: Obtain the calculated acquisition value of each acquisition content, compare the acquisition value of each acquisition content with the set acquisition threshold, obtain the acquisition content corresponding to the acquisition value greater than or equal to the set acquisition threshold, arrange the acquisition content corresponding to the acquisition value greater than or equal to the set acquisition threshold in descending order according to the acquisition value on the creative content side, and the creator selects the required acquisition content.

6. The method for intelligent creation analysis based on knowledge graph according to claim 5, characterized in that: The specific steps of obtaining the relevant knowledge content of the creative theme and constructing the knowledge graph network about the creative theme through the relevant knowledge content are as follows: Obtain the creative theme determined by the creator, segment the creative theme to obtain a number of theme keywords, and import the obtained theme keywords into the retrieval system to obtain relevant knowledge content related to the theme keywords; Acquire all relevant knowledge content about the subject keywords to build a knowledge graph network about the creative topic.

7. An intelligent creation analysis system based on knowledge graph, which is implemented based on the intelligent creation analysis method based on knowledge graph according to any one of claims 1 to 6, characterized in that: It specifically includes a knowledge graph network construction module, a first content acquisition module, a creation similarity analysis module, a second content acquisition module, an acquisition value analysis module, a content selection module and a control module, wherein the knowledge graph network construction module is used to acquire relevant knowledge content of the creation theme, and construct a knowledge graph network about the creation theme through the relevant knowledge content; The first content acquisition module is used to acquire the creation content and the creation personnel's historical creation content and import them into the first content acquisition strategy to obtain the extraction probability of the first acquired content; The creation similarity analysis module is used to obtain the historical creation content of the creator and the historical creation content of other creators of the creation theme, and import them into the creation similarity acquisition strategy of similar creators to obtain the creation similarity of similar creators; The second content acquisition module is used to import the creation similarity of similar creators and the creation content of related creation themes of similar creators into the second content acquisition strategy to obtain the extraction probability of the second acquired content; The acquisition value analysis module is used to analyze the acquisition value of the acquisition content according to the acquired extraction probability of the first acquisition content and the extraction probability of the second acquisition content; The content selection module is used to arrange the acquired content in descending order according to the acquired value on the side of the creative content, so that the creator can select the acquired content they need; The control module is used to control the operation of the graph knowledge graph network construction module, the first content acquisition module, the creation similarity analysis module, the second content acquisition module, the acquisition value analysis module and the content selection module.

8. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes an intelligent creation analysis method based on a knowledge graph as described in any one of claims 1 to 6 by calling a computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes an intelligent creation analysis method based on a knowledge graph as described in any one of claims 1 to 6.

Images