Creation processing method, electronic device, and storage medium

Abstract

The invention provides a creation processing method, electronic equipment and a storage medium, and is suitable for the technical field of human-computer interaction. The creation processing method comprises the following steps: acquiring physiological feature information of a target object; determining emotional state information of the target object based on the physiological feature information; determining a target weight parameter based on the emotional state information; wherein the target weight parameter comprises a dominant weight of the target object and a cooperation weight of artificial intelligence; and performing man-machine collaborative creation based on the target weight parameter, and generating collaborative creation content. According to the embodiment of the invention, the target weight parameter can be determined through the emotional state information of the user so as to determine the dominant weight of the target object and the collaboration weight of artificial intelligence, dynamic distribution of the creation dominant right of man-machine collaboration creation is realized, the efficiency of man-machine collaboration creation can be improved, and thus the user experience is improved.

Description

(19) State Intellectual Property Office (12) Invention Patent Application (10) Application Publication Number (43) Application Publication Date (21) Application Number 202511086332.0 (22) Application Date 2025.08.04 (71) Applicant Sun Yuqian Address No. 1, Scenic Road, Huangwan Township, Emeishan City, Leshan City, Sichuan Province, 614200 (72) Inventor Sun Yuqian (74) Patent Agency Shenzhen Zhongyi United Intellectual Property Agency Co., Ltd. 44414 Patent Attorney Hu Juan (51) Int.Cl. G06F 18 / 26 (2023.01) G06F 18 / 213 (2023.01) (54) Invention Title Creation Processing Method, Electronic Device and Storage Medium (57) Abstract This application provides a creation processing method, electronic device and storage medium, applicable to the field of human-computer interaction technology. The creative processing method includes: acquiring physiological characteristic information of the target object; determining the emotional state information of the target object based on the physiological characteristic information; determining target weight parameters based on the emotional state information; wherein the target weight parameters include the dominant weight of the target object and the collaborative weight of artificial intelligence; and performing human-computer collaborative creation based on the target weight parameters to generate collaboratively created content. This embodiment of the application can determine the target weight parameters through the user's emotional state information, thereby determining the dominant weight of the target object and the collaborative weight of artificial intelligence, realizing the dynamic allocation of creative leadership in human-computer collaborative creation, improving the efficiency of human-computer collaborative creation, and thus enhancing the user experience. Claims (2 pages), Description (12 pages), Drawings (3 pages), CN 121093296 A, 2025.12.09, CN 1 21 09 32 96 A 1. A creative processing method, characterized in that it includes: acquiring physiological characteristic information of a target object; determining emotional state information of the target object based on the physiological characteristic information; determining target weight parameters based on the emotional state information; wherein the target weight parameters include the dominant weight of the target object and the collaborative weight of artificial intelligence; performing human-computer collaborative creation based on the target weight parameters to generate collaboratively created content. 2. The creative processing method according to claim 1, characterized in that determining the target weight parameters based on the emotional state information includes: determining a collaborative weight based on the emotional state information and a preset weight adjustment function; determining the dominant weight based on the collaborative weight; and determining the target weight parameters based on the collaborative weight and the dominant weight. 3. The creative processing method according to claim 2, characterized in that the physiological feature information includes physiological signals of the target object collected during the human-computer collaborative creation process, and feedback information when the target object reads the artificial intelligence-generated content, wherein the physiological signals include at least one of electroencephalogram (EEG), heart rate, and skin conductance response, and the feedback...The information includes at least one of voice signals and facial expression features, wherein the emotional state information includes a negative emotion index and an inspiration blockage index; determining the emotional state information of the target object based on the physiological feature information includes: performing emotion recognition on the physiological feature information based on a preset multimodal emotion recognition model to obtain the negative emotion index; determining the inspiration blockage index based on the physiological signal. 4. The creative processing method according to claim 3, wherein determining the collaboration weight based on the emotional state information and a preset weight adjustment function includes: obtaining the frequency of the target object's active behavior towards the artificial intelligence's creative content; wherein the frequency of active behavior is determined based on the number of times manual input information is entered, the number of times modification is undone, and the number of times suggestions are requested; determining the collaboration weight based on the negative emotion index, the inspiration blockage index, the frequency of active behavior, and the preset weight adjustment function. 5. The creative processing method according to claim 4, characterized in that, determining the collaboration weight based on the negative emotion index, the inspiration blockage index, the frequency of proactive behavior, and a preset weight adjustment function includes: inputting the negative emotion index, the inspiration blockage index, and the frequency of proactive behavior into the weight adjustment function, such that the weight adjustment function performs the following operations: taking the product of the first sensitivity coefficient and the negative emotion index, the product of the second sensitivity coefficient and the inspiration blockage index, and the product of the third sensitivity coefficient and the frequency of proactive behavior as the first adjustment weight, the second adjustment weight, and the third adjustment weight, respectively; subtracting the third adjustment weight from the sum of the first adjustment weight and the second adjustment weight to obtain the total adjustment weight; and taking the sum of the total adjustment weight and the base weight as the collaboration weight. 6. The creative processing method according to claim 5, characterized in that the basic weight is obtained by: determining the creative stage of human-computer collaborative creation; wherein the creative stage includes any one of the conception stage, generation stage, and polishing stage; if the creative stage is the conception stage, then the preset default value is increased by a first preset value to obtain the basic weight; if the creative stage is the generation stage, then the preset default value is used as the basic weight; if the creative stage is the polishing stage, then the preset default value is decreased by a second preset value to obtain the basic weight. 7. The creative processing method according to claim 5, characterized in that it further includes: acquiring the response behavior information of the target object to the creative content created by the artificial intelligence; wherein the response behavior information includes accepting or ignoring suggestions, the extent of modification, and subjective satisfaction rating; adjusting the sensitivity coefficient in the weight adjustment function based on the response behavior information and a preset algorithm;Wherein, the sensitivity coefficient includes at least one of a first sensitivity coefficient, a second sensitivity coefficient, and a third sensitivity coefficient. 8. The creative processing method according to any one of claims 1-7, characterized in that, the step of performing human-computer collaborative creation based on the target weight parameter to generate collaborative creative content includes: if the collaboration weight is greater than a third preset value, then automatically pushing creative suggestions through artificial intelligence to generate collaborative creative content; if the collaboration weight is less than a fourth preset value, then not automatically pushing creative suggestions through artificial intelligence, and pushing the creative suggestions in response to the calling operation of the target object to generate collaborative creative content; wherein, the third preset value is greater than the fourth preset value. 9. An electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 8. 10. A computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8. Claims 2 / 2 Page 3 CN 121093296 A Creative Processing Method, Electronic Device and Storage Medium Technical Field

[0001] This application relates to the field of human-computer interaction technology, and in particular to a creative processing method, electronic device and storage medium. Background Art

[0002] AI (Artificial Intelligence) collaboration refers to the interaction and cooperation between humans and artificial intelligence systems, aiming to improve work efficiency and decision-making quality through the complementary advantages of both parties.

[0003] At present, the application of human-computer collaborative creation has also made some progress. However, in the process of human-computer collaborative creation, it is difficult to adjust and allocate the creative leadership of humans and artificial intelligence, thereby reducing the efficiency of users through human-computer collaborative creation and reducing the user experience. Summary of the Invention

[0004] In view of this, the embodiments of this application provide a creative processing method, electronic device and storage medium to solve the problem of low efficiency or reduced user experience in human-computer collaborative creation in the prior art.

[0005] A first aspect of this application provides a creative processing method, including:

[0006] acquiring physiological characteristic information of a target object;

[0007] determining the emotional state information of the target object based on the physiological characteristic information;

[0008] determining target weight parameters based on the emotional state information; wherein the target weight parameters include the dominant weight of the target object and the collaborative weight of artificial intelligence;

[0009] performing human-computer collaborative creation based on the target weight parameters to generate collaboratively created content.

[0010] In one possible implementation, determining the target weight parameters based on the emotional state information includes:

[0011] Based on emotional state information and a preset weight adjustment function, determine the collaboration weight;

[0012] Based on the collaboration weight, determine the dominant weight;

[0013] Based on the collaboration weight and the dominant weight, determine the target weight parameter.

[0014] In one possible implementation, the physiological feature information includes the physiological signals of the target object collected during the human-computer collaborative creation process, and the feedback information when the target object reads the artificial intelligence's creative content. The physiological signals include at least one of electroencephalogram (EEG), heart rate, and skin conductance response. The feedback information includes at least one of voice signal and facial expression features. The emotional state information includes a negative emotion index and an inspiration blockage state index;

[0015] Based on the physiological feature information, determine the emotional state information of the target object, including:

[0016] Based on a preset multimodal emotion recognition model, perform emotion recognition on the physiological feature information to obtain a negative emotion index;

[0017] Based on the physiological signals, determine the inspiration blockage state index.

[0018] In one possible implementation, the collaboration weight is determined based on emotional state information and a preset weight adjustment function, including:

[0019] obtaining the frequency of the target object's proactive behavior towards the AI-generated content; wherein the frequency of proactive behavior is determined based on the number of times human input information is entered, the number of times modifications are undone, and the number of times suggestions are requested; Specification 1 / 12 page 4 CN 121093296 A

[0020] the collaboration weight is determined based on the negative emotion index, the inspiration blockage index, the frequency of proactive behavior, and the preset weight adjustment function.

[0021] In one possible implementation, the collaboration weight is determined based on the negative emotion index, the inspiration blockage index, the frequency of proactive behavior, and a preset weight adjustment function, including:

[0022] Inputting the negative emotion index, the inspiration blockage index, and the frequency of proactive behavior into the weight adjustment function, such that the weight adjustment function performs the following operations:

[0023] Using the product of the first sensitivity coefficient and the negative emotion index, the product of the second sensitivity coefficient and the inspiration blockage index, and the product of the third sensitivity coefficient and the frequency of proactive behavior as the first adjustment weight, the second adjustment weight, and the third adjustment weight, respectively;

[0024] Subtracting the sum of the first adjustment weight and the second adjustment weight from the third adjustment weight to obtain the total adjustment weight;

[0025] Using the sum of the total adjustment weight and the basic weight as the collaboration weight.

[0026] In one possible implementation, the basic weight is obtained as follows:

[0027] Determine the creation stage in which the human-computer collaborative creation takes place; wherein, the creation stage includes any one of the conception stage, generation stage, and polishing stage;

[0028] If the creation stage is the conception stage, then the preset default value is increased by a first preset value to obtain the basic weight;

[0029] If the creation stage is the generation stage, then the preset default value is used as the basic weight;

[0030] If the creation stage is the polishing stage, the default value is reduced by the second preset value to obtain the basic weight.

[0031] In one possible implementation, the creation processing method further includes:

[0032] Obtaining the response behavior information of the target object to the artificial intelligence creation content; wherein, the response behavior information includes accepting or ignoring suggestions, the extent of modification, and subjective satisfaction rating;

[0033] Adjusting the sensitivity coefficient in the weight adjustment function based on the response behavior information and the preset algorithm; wherein, the sensitivity coefficient includes at least one of the first sensitivity coefficient, the second sensitivity coefficient, and the third sensitivity coefficient.

[0034] In one possible implementation, human-computer collaborative creation is performed based on the target weight parameter to generate collaborative creation content, including:

[0035] If the collaboration weight is greater than the third preset value, then creation suggestions are automatically pushed through artificial intelligence to generate collaborative creation content;

[0036] If the collaboration weight is less than the fourth preset value, then creation suggestions are not automatically pushed through artificial intelligence, but creation suggestions are pushed in response to the target object's call operation to generate collaborative creation content; wherein, the third preset value is greater than the fourth preset value.

[0037] A second aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method of the first aspect.

[0038] A third aspect of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of the method of the first aspect.

[0039] The beneficial effects of the embodiments of the present application compared with the prior art are:

[0040] The creative processing method of the first aspect of the present application can obtain the physiological characteristic information of the target object, determine the emotional state information of the target object based on the physiological characteristic information, and thus determine the target weight parameter based on the emotional state information. That is, the allocation of creative dominance between humans and artificial intelligence can be determined through the user's emotional state information. Then, based on the target weight parameter, human-computer collaborative creation is carried out to generate collaborative creation content. Since the embodiments of this application can determine the target weight parameters through the emotional state information of the user's instruction manual (page 2 / 12, CN 121093296 A), the dominant weight of the target object and the collaborative weight of artificial intelligence can be determined, thereby realizing the dynamic allocation of creative dominance in human-computer collaborative creation, which can improve the efficiency of human-computer collaborative creation and thus improve the user experience.

[0041] It is understood that the beneficial effects of the second to third aspects mentioned above can be referred to the relevant description in the first aspect mentioned above, and will not be repeated here. Brief Description of the Drawings

[0042] In order to more clearly illustrate the technical solutions in the embodiments of this application, the embodiments or the prior art will be described below.The accompanying drawings used in this application are briefly introduced. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 is a flowchart of a creative processing method provided by an embodiment of this application;

[0044] Figure 2 is a flowchart of a method for determining collaborative weights based on emotional state information and a preset weight adjustment function provided by an embodiment of this application;

[0045] Figure 3 is a flowchart of another creative processing method provided by an embodiment of this application;

[0046] Figure 4 is a structural schematic diagram of a creative processing system provided by an embodiment of this application;

[0047] Figure 5 is a structural schematic diagram of a creative processing device provided by an embodiment of this application;

[0048] Figure 6 is a structural schematic diagram of an electronic device provided by an embodiment of this application. Detailed Description

[0049] In the following description, specific details such as particular system structures and technologies are set forth for illustration rather than limitation in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art should understand that this application can also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted to avoid unnecessary detail that could obscure the description of this application.

[0050] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of a described feature, integral, step, operation, element, and / or component, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof.

[0051] It should also be understood that, as used in this specification and the appended claims, the term "and / or" refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0052] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases “if determined” or “if [the described condition or event] is detected” can be interpreted, depending on the context, as meaning “once determined” or “in response to determined” or “once [the described condition or event] is detected” or “in response to the detection of [the described condition or event]”.

[0053] Furthermore, in the description of this application and the appended claims, the terms “first,” “second,” “third,” etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0054] References to “one embodiment” or “some embodiments”, etc., described in this application mean that in this applicationOne or more embodiments include specific features, structures, or characteristics described in connection with the embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments of the specification", unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to", unless otherwise specifically emphasized.

[0055] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. It should be noted that the following embodiments can be referenced, borrowed, or combined with each other, and the same terms, similar features, and similar implementation steps in different embodiments will not be described again.

[0056] Referring to FIG1, an embodiment of this application provides a flowchart of a creative processing method. As shown in FIG1, the creative processing method of this application includes: steps S101 to S104.

[0057] S101, Obtain physiological characteristic information of the target object.

[0058] Optionally, physiological feature information is acquired through various hardware structures of the signal acquisition layer for the target object.

[0059] S102. Based on physiological feature information, determine the emotional state information of the target object.

[0060] In some embodiments, physiological feature information includes physiological signals of the target object acquired during human-computer collaborative creation, and feedback information when the target object reads the content created by artificial intelligence. Physiological signals include at least one of electroencephalogram (EEG), heart rate, and skin conductance response. Feedback information includes at least one of voice signal and facial expression features. Emotional state information includes a negative emotion index and an inspiration blockage index.

[0061] Optionally, determining the emotional state information of the target object based on physiological feature information includes: performing emotion recognition on physiological feature information based on a preset multimodal emotion recognition model to obtain a negative emotion index; and determining an inspiration blockage index based on physiological signals.

[0062] Optionally, the multimodal emotion recognition model can perform emotion recognition on multiple fused physiological feature information.

[0063] S103. Determine target weight parameters based on emotional state information; wherein, the target weight parameters include the dominant weight of the target object and the collaborative weight of the artificial intelligence.

[0064] In some embodiments, determining target weight parameters based on emotional state information includes: determining collaborative weight based on emotional state information and a preset weight adjustment function; determining dominant weight based on collaborative weight; and determining target weight parameters based on collaborative weight and dominant weight.

[0065] Optionally, the target weight parameters include collaboration weight and dominance weight.

[0066] This application embodiment defines two adjustable weight parameters: W_Human (dominance weight of human creator) and W_AI (collaboration weight of artificial intelligence), which satisfy the constraint: W_Human+W_AI=1. The system default state is: W_Human=0.7, W_AI=0.3, that is, AI plays the role of inspiration supplementation and suggestion generation.

[0067] S104. Based on the target weight parameters, human-computer collaborative creation is carried out to generate collaborative creation content.

[0068] Based on the above steps S101 to S104, the creation processing method of this application embodiment can obtain the physiological characteristic information of the target object, determine the emotional state information of the target object based on the physiological characteristic information, and thus determine the target weight parameters based on the emotional state information. That is, the allocation of creative dominance between humans and artificial intelligence can be determined through the user's emotional state information. Then, based on the target weight parameters, human-computer collaborative creation is carried out to generate collaborative creation content. Since the embodiments of this application can determine the target weight parameters through the user's emotional state information, thereby determining the dominant weight of the target object and the collaborative weight of artificial intelligence, the dynamic allocation of creative dominance in human-computer collaborative creation can be realized, which can improve the efficiency of human-computer collaborative creation and thus improve the user experience.

[0069] As an example, this application provides a technical solution for obtaining physiological characteristic information of a target object and determining the emotional state information of the target object based on the physiological characteristic information. The specific content is as follows:

[0070] 1. Signal acquisition stage:

[0071] 1) The following three types of physiological signals are collected during the AI ​​collaborative creation process: Specification 4 / 12 pages 7 CN 121093296 A

[0072] Electroencephalogram (EEG): A head-mounted EEG device is used to collect alpha wave (8Hz–13Hz) and beta wave (13–30Hz) energy;

[0073] Heart rate (PPG): Pulse interval (IBI) and heart rate variability (HRV) are measured by a photoplethysmography sensor;

[0074] Skin conductance (GSR): Electrodes are attached to the fingertips to record the frequency, amplitude and response delay of skin conductance response (SCR).

[0075] Wherein, EEG (Electroencephalogram) represents electroencephalogram; PPG (Photoplethysmography) represents photoplethysmography; GSR (Galvanic Skin Response) represents electroskin response.

[0076] (2) After the AI ​​creation is completed, when the subject reads the creation result aloud, two types of behavioral signals are collected:

[0077] Speech signal: extract emotion-related parameters such as pitch, speech rate, loudness, spectral centroid, and formants;

[0078] Facial expression features: Action units are captured by a camera, and micro-expressions such as eyebrow raising, eyelid contraction, and changes in the corners of the mouth are analyzed.

[0079] 2. Feature extraction module:

[0080] EEG: Calculate the α / β power ratio and frequency band energy density of the frontoparietal lobe;

[0081] PPG: Extract the time domain and frequency domain features of HRV, such as SDNN, RMSSD, LF / HF, etc.;

[0082] GSR: Extract the occurrence frequency, average amplitude, recovery time, etc. of SCR;

[0083] Speech signal: Extract MFCC feature groups, F0 fundamental frequency, speech rate, energy changes, etc.;

[0084] Facial expression features: Use tools such as OpenFace to extract AU values ​​or calculate expression index (emotional activity, positive and negative emotion scores, etc.).

[0085] 3. Feature Fusion Strategy:

[0086] Early Fusion: Form a joint feature vector by splicing multimodal features;

[0087] Weight Mechanism Fusion: Introduce an attention mechanism to dynamically allocate the recognition weights of each modality in a specific time period, thereby improving the multimodal emotion recognition model's ability to perceive the dominant emotion source.

[0088] 4. Emotion Recognition and Classification:

[0089] Use classifiers such as Support Vector Machine (SVM), Multilayer Perceptron (MLP), or Long Short-Term Memory Network (LSTM);

[0090] Classification labels can be three-category (positive / neutral / negative) or six-category (joy, calm, tension, anger, disgust, sadness) emotion sets;

[0091] Can be extended to dimensionality methods (such as Russell's two-dimensional model) to support subsequent refined emotion modeling.

[0092] 5. Output and Judgment Mechanism:

[0093] During the AI ​​collaborative creation process, the system outputs the current dominant emotion trend every 10 seconds.

[0094] After the reading aloud session, the system integrates voice and facial expression signals to output an overall emotional state, which is used to assist in evaluating the psychological acceptance score and resonance quality of the AI ​​suggestions.

[0095] Optionally, this application embodiment supports the subsequent addition of other modal signal inputs (such as electromyography (EMG), skin temperature, motion capture, etc.), and can also connect to a deep emotion generation model (such as Diffusion-EmotionBridge) to further improve recognition accuracy and cross-modal interpretability.

[0096] Referring to Figure 2, this application embodiment provides a flowchart for determining collaboration weights based on emotional state information and a preset weight adjustment function. As shown in Figure 2, the method for determining collaboration weights based on emotional state information and a preset weight adjustment function includes steps S201 to S202.

[0097] S201: Obtain the frequency of proactive behavior of the target object towards the content created by artificial intelligence; wherein, the frequency of proactive behavior is determined based on the number of times manual input information is entered, the number of times modification is undone, and the number of times suggestions are requested;

[0098] S202. Based on the negative emotion index, the inspiration blockage index, the frequency of proactive behavior, and the preset weight adjustment function, determine the collaboration weight.

[0099] Optionally, the negative emotion index is obtained by acquiring emotion recognition from physiological feature information based on a preset multimodal emotion recognition model, and the inspiration blockage index is determined based on physiological signals.

[0100] In this application embodiment, when the creator is detected to be in a state of "low mood", "inspiration blockage", or "fatigue", the system can automatically adjust the weight structure to enhance the AI's dominance and reduce the user's load.

[0101] Referring to Figure 3, this application embodiment provides a flowchart of another creative processing method. As shown in Figure 3, the creative processing method of this application embodiment includes: steps S301 to S307.

[0102] S301. Obtain the physiological feature information of the target object; wherein, the physiological feature information includes the physiological signals of the target object collected during the human-computer collaborative creation process, and the feedback information when the target object reads the artificial intelligence's creative content.

[0103] Physiological signals include at least one of electroencephalogram (EEG), heart rate, and skin conductance response; feedback information includes at least one of speech signals and facial expression features.

[0104] Emotional state information includes a negative emotion index and an inspiration blockage index.

[0105] S302. Based on a preset multimodal emotion recognition model, perform emotion recognition on the physiological feature information to obtain a negative emotion index.

[0106] S303. Based on the physiological signals, determine the inspiration blockage index.

[0107] S304. Obtain the frequency of proactive behavior of the target object towards the content created by artificial intelligence; wherein, the frequency of proactive behavior is determined based on the number of times human input information is entered, the number of times modification is undone, and the number of times suggestions are requested.

[0108] S305. Based on the negative emotion index, the inspiration blockage index, the frequency of proactive behavior, and a preset weight adjustment function, determine the collaboration weight.

[0109] In some embodiments, the collaboration weight is determined based on the negative emotion index, the inspiration blockage index, the frequency of proactive behavior, and a preset weight adjustment function, including:

[0110] Inputting the negative emotion index, the inspiration blockage index, and the frequency of proactive behavior into the weight adjustment function, causing the weight adjustment function to perform the following operations:

[0111] Using the product of the first sensitivity coefficient and the negative emotion index, the product of the second sensitivity coefficient and the inspiration blockage index, and the product of the third sensitivity coefficient and the frequency of proactive behavior as the first adjustment weight, the second adjustment weight, and the third adjustment weight, respectively;

[0112] Subtracting the third adjustment weight from the sum of the first and second adjustment weights to obtain the total adjustment weight;

[0113] Using the sum of the total adjustment weight and the base weight as the collaboration weight.

[0114] As an example, the weight adjustment function is: W_AI(t)=base+α1·E(t)+α2·F(t)-α3·A(t);

[0115] Where: E(t): the negative emotion index at the current moment, calculated by the multimodal emotion recognition model;

[0116] F(t): the inspiration blockage state index, such as the decrease of α waves in EEG, the convergence of PPG changes, the increase of GSR, etc.;

[0117] A(t): the frequency of user active behavior, such as the number of times of keyboard input, undoing modification, and actively requesting suggestions;

[0118] α1, α2, α3 are the adjustment sensitivity coefficients set by the system, corresponding to the first sensitivity coefficient, the second sensitivity coefficient, and the third sensitivity coefficient, respectively.

[0119] base: the basic weight, with a preset default value of 0.3.

[0120] Optionally, E(t) is based on the following multimodal feature fusion: (1) Electroencephalogram (EEG): α / β ratio, prefrontal activation level; (2) Heart rate variability (HRV): SDNN, LF / HF index; (3) Skin conductance (GSR): SCR peak frequency, average amplitude; (4) Speech signal: fundamental frequency jitter, intensity fluctuation, speech rate change; (5) Facial expression features: facial action unit activity, emotion bias score.

[0121] In some embodiments, the basic weight is obtained in the following way:

[0122] Determine the creation stage of human-computer collaborative creation; wherein, the creation stage includes any one of the conception stage, generation stage and polishing stage;

[0123] If the creation stage is the conception stage, the preset default value is increased by a first preset value to obtain the basic weight;

[0124] If the creation stage is the generation stage, the preset default value is used as the basic weight;

[0125] If the creation stage is the polishing stage, the preset default value is decreased by a second preset value to obtain the basic weight.

[0126] This application embodiment provides a multi-stage adaptation strategy. In order to match the non-linear rhythm of creation, the collaborative process is divided into three major stages, and different weight biases are set, as follows:

[0127] Conception stage: Increase W_AI, AI takes the lead in triggering inspiration and proposals;

[0128] Generation stage: Balance W_Human and W_AI, and collaboratively promote the creation content;

[0129] Polishing stage: Increase W_Human, and emphasize human language style and logical control.

[0130] S306. Based on the collaboration weight, determine the dominant weight, and use the collaboration weight and the dominant weight as the target weight parameter.

[0131] S307. Based on the target weight parameter, perform human-computer collaborative creation to generate collaborative creation content.

[0132] In some embodiments, performing human-computer collaborative creation to generate collaborative creation content based on the target weight parameter includes:

[0133] If the collaboration weight is greater than the third preset value, then creative suggestions are automatically pushed through artificial intelligence to generate collaborative content;

[0134] If the collaboration weight is less than the fourth preset value, then creative suggestions are not automatically pushed through artificial intelligence, but in response to the call operation of the target object, creative suggestions are pushed to generate collaborative content; wherein, the third preset value is greater than the fourth preset value.

[0135] Optionally, the third preset value is 0.5 and the fourth preset value is 0.3.

[0136] As an example, when W_AI>0.5, creative suggestions can be automatically triggered without waiting for a user's explicit request; when W_AI<0.3, AI enters a waiting mode and provides creative suggestions when the user calls.

[0137] The output behavior of this application embodiment includes suggestion frequency, active recommendation form, suggestion language style, etc.

[0138] In some embodiments, the creative processing method further includes:

[0139] acquiring response behavior information of the target object to the creative content created by artificial intelligence; wherein, the response behavior information includes accepting or ignoring suggestions, the extent of modification, and subjective satisfaction rating;

[0140] adjusting the sensitivity coefficients in the weight adjustment function based on the response behavior information and a preset algorithm; wherein, the sensitivity coefficients include at least one of a first sensitivity coefficient, a second sensitivity coefficient, and a third sensitivity coefficient.

[0141] Optionally, the preset algorithm may employ reinforcement learning or heuristic algorithms, etc.

[0142] This application embodiment has a weight update and self-learning mechanism, recording each human response behavior to AI suggestions, including: accepting or ignoring suggestions, the extent of modification, and subjective satisfaction rating of the final work, etc. By continuously optimizing the three sensitivity coefficients α1, α2, and α3 through reinforcement learning or heuristic algorithms, personalized adjustment of the weight adjustment function is achieved.

[0143] This application embodiment realizes the leap from the "tool-operator" model to the "symbiotic-co-structure" model in human-machine relationship, so that AI is no longer just an assistant that passively executes commands, but a co-creation partner that actively adjusts its role and behavior strategy according to human state.

[0144] This application embodiment can be extended to various creative scenarios such as script creation, novel writing and psychological writing training. Specification 7 / 12 pages 10 CN 121093296 A

[0145] This application embodiment is applicable to the following multimodal creation types: (1) Literary writing: optimize paragraph tone and character emotion consistency; (2) Illustration design: adjust character dynamics and background style to fit the narrative emotion; (3) Video script: rewrite the rhythm of lines and the order of scenes to match emotional tension; (4) Music creation: adjust the rhythm of lyrics and the degree of melody resonance to achieve high emotional connectivity.

[0146] The creative processing method provided by this application embodiment can be applied to mobile phones, tablets, wearable devices, in-vehicle devices, augmented reality (AR) devices, etc.On electronic devices such as AR / VR devices, laptops, ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs), this application embodiment does not impose any restrictions on the specific type of electronic device.

[0147] It should be understood that the order of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of this application embodiment.

[0148] Referring to Figure 4, this application embodiment provides a schematic diagram of the structure of a creative processing system. As shown in Figure 4, the creative processing system of this application embodiment includes a signal acquisition layer 41, a preprocessing and fusion node 42, a main control computing module 43, and a user interface module 44.

[0149] The signal acquisition layer 41 includes an EEG collector 411, a heart rate sensor 412, a skin conductance probe 413, a camera 414, and a microphone 415.

[0150] Specifically, the EEG acquisition device 411 acquires electroencephalogram (EEG), the heart rate sensor 412 acquires heart rate PPG, the skin conductance probe 413 acquires GSR, the camera 414 acquires facial expressions, and the microphone 415 acquires speech signals.

[0151] Optionally, the creation processing system of this application embodiment has a Bluetooth or Wi-Fi wireless transmission interface, supports low-power continuous acquisition, and all acquisition devices support a unified driver protocol and timestamp synchronization.

[0152] Optionally, the preprocessing and fusion node 42 can be equipped with an edge processor (such as NVIDIA Jetson Nano or Raspberry Pi 5) to perform preliminary data cleaning, feature extraction, and standardization processing; at the same time, the preprocessing and fusion node 42 has a built-in small data caching mechanism to ensure data integrity in offline scenarios; the preprocessing and fusion node 42 supports low-latency feature fusion.

[0153] Optionally, the main control computing module 43 is equipped with a host server or a local high-computing-power device, integrating an emotion recognition model (SVM, LSTM, Transformer, etc.), a resonance determiner, and a suggestion generation engine. Cross-platform compatibility can be achieved by deploying the model.

[0154] Optionally, the user interface module 44 includes a terminal display, a touch interface, or a mobile app, used to display suggested content, created content, collect user feedback (clicks, expressions, voice, etc.), and send it to the core module to optimize model weights.

[0155] The creation processing system of this application embodiment mainly demonstrates a modular signal acquisition and computing system architecture and a standardized API interface design. It proposes to adopt a modular structure at the hardware level to achieve high scalability and adaptability to various applications.The creative processing system of this application embodiment has plug-and-play, hot-swap recognition, edge computing and remote communication capabilities.

[0156] The creative processing system of this application embodiment is a human-machine symbiotic creative system, which designs a "dynamic dominance allocation mechanism" to dynamically adjust the participation and dominance of AI and humans in the creative process according to the creator's real-time emotional state, cognitive load and interactive behavior characteristics, thereby optimizing creative efficiency and experience.

[0157] In order to further improve the performance of the creative processing system of this application embodiment in terms of emotion recognition accuracy and response sensitivity, the creative processing system of this application embodiment supports compatibility and adaptation with brain-computer interface devices (BCI).

[0158] BCI technology can achieve more refined modeling of psychological variables such as user cognitive state, emotional fluctuations and inspiration bursts through high-precision electroencephalogram (EEG) acquisition and processing. Typical devices include, but are not limited to, non-invasive BCI systems that support multi-channel high-density sampling (such as OpenBCI, NextMind, Emotiv, etc.).

[0159] In the signal acquisition layer 41 of the creative processing system of this application embodiment, a standard interface for accessing BCI devices (such as BLE, USB, SDK / API protocol layer) is reserved, which can realize the following functions: (1) dynamic monitoring and time synchronization of EEG frequency bands (α / β / θ / γ); (2) joint modeling of inspiration activation index and emotional stability; (3) coupling analysis of brain region activity map and suggestion adoption behavior; (4) real-time resonance feedback mechanism under high sampling rate.

[0160] The core innovation of the creative processing system of this application embodiment includes the suggestion generation mechanism and personalized resonance optimization algorithm constructed based on high-precision emotional state parameters. As one of the optional acquisition entry points of the creative processing system of this application embodiment, the introduction of the brain-computer interface device can further expand the applicability and industrial depth of the system in high-demand scenarios such as clinical psychology, neuro-art, and trauma intervention.

[0161] Referring to Figure 5, this application embodiment provides a schematic diagram of the structure of a creative processing device 50. As shown in Figure 5, the creation processing device 50 includes: an acquisition module 501, a first determination module 502, a second determination module 503, and a creation module 504.

[0162] The acquisition module 501 is used to acquire physiological characteristic information of the target object.

[0163] The first determination module 502 is used to determine the emotional state information of the target object based on the physiological characteristic information.

[0164] The second determination module 503 is used to determine target weight parameters based on the emotional state information; wherein, the target weight parameters include the dominant weight of the target object and the collaborative weight of artificial intelligence.

[0165] The creation module 504 is used to perform human-computer collaborative creation based on the target weight parameters to generate collaborative creation content.

[0166] Optionally, the second determining module 503 is used to determine the collaboration weight based on emotional state information and a preset weight adjustment function; determine the dominant weight based on the collaboration weight; and use the collaboration weight and the dominant weight as the target weight parameters.

[0167] Optionally, the first determining module 502 is used to perform emotion recognition on physiological feature information based on a preset multimodal emotion recognition model to obtain a negative emotion index; and determine the inspiration blockage state index based on physiological signals.

[0168] Optionally, the second determining module 503 is used to obtain the frequency of the target object's active behavior towards the artificial intelligence creation content; wherein, the frequency of active behavior is determined based on the number of times human input information is entered, the number of times modification is undone, and the number of times suggestions are requested; and the collaboration weight is determined based on the negative emotion index, the inspiration blockage state index, the frequency of active behavior, and the preset weight adjustment function.

[0169] Optionally, the second determining module 503 is used to input the negative emotion index, the inspiration blockage index, and the frequency of proactive behavior into the weight adjustment function, so that the weight adjustment function performs the following operations: the product of the first sensitivity coefficient and the negative emotion index, the product of the second sensitivity coefficient and the inspiration blockage index, and the product of the third sensitivity coefficient and the frequency of proactive behavior are respectively used as the first adjustment weight, the second adjustment weight, and the third adjustment weight; the sum of the first adjustment weight and the second adjustment weight is subtracted from the third adjustment weight to obtain the total adjustment weight; the sum of the total adjustment weight and the basic weight is used as the collaboration weight.

[0170] Optionally, the second determining module 503 is used to obtain the response behavior information of the target object to the content created by artificial intelligence; wherein, the response behavior information includes accepting or ignoring suggestions, the extent of modification, and subjective satisfaction rating; based on the response behavior information and a preset algorithm, the sensitivity coefficient in the weight adjustment function is adjusted; wherein, the sensitivity coefficient includes at least one of the first sensitivity coefficient, the second sensitivity coefficient, and the third sensitivity coefficient.

[0171] Optionally, the creation module 504 is used to automatically push creation suggestions through artificial intelligence if the collaboration weight is greater than a third preset value, so as to generate collaborative creation content; if the collaboration weight is less than a fourth preset value, it does not automatically push creation suggestions through artificial intelligence, but pushes creation suggestions in response to the call operation of the target object to generate collaborative creation content; wherein, the third preset value is greater than the fourth preset value.

[0172] The device of the embodiments of this application can execute the method provided in the embodiments of this application, and its implementation principle is similar. The actions performed by each module in the device of each embodiment of this application are corresponding to the steps in the method of each embodiment of this application. For detailed functional descriptions of each module of the device, please refer to the descriptions in the corresponding methods shown above, which will not be repeated here.

[0173] Referring to FIG6, an embodiment of this application provides a schematic diagram of the structure of an electronic device 6. As shown in FIG6, the electronic device 6 of this application embodiment includes: a memory 61, a processor 60, and a computer program 62 stored in the memory 61 and executable on the processor 60. When the processor 60 executes the computer program, it implements the steps of the methods of the various embodiments of this application.

[0174] The electronic device 6 may be a desktop computer, a laptop, a handheld computer, or a cloud server, etc. The electronic device 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that FIG6 is merely an example of the electronic device 6 and does not constitute a limitation on the electronic device 6. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0175] The processor 60 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0176] In some embodiments, the memory 61 may be an internal storage unit, such as a hard disk or RAM. The memory 61 may be a removable / non-removable, volatile / non-volatile computer system storage medium, for example: the memory 61 is a non-volatile memory used for reading and writing non-volatile magnetic media. In other embodiments, the memory 61 may also be an external storage device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 6. The memory 61 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of a computer program. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0177] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. Their specific functions and technical effects can be found in the method embodiments section, and will not be repeated here.

[0178] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in software functional units. In addition, the specific names of each functional unit and module are only for easy differentiation and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, which will not be repeated here. Specification 10 / 12 pages 13 CN 121093296 A

[0179] The embodiments of this application also provide a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the steps in the above-described method embodiments.

[0180] If the integrated unit described above is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program described above can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the various method embodiments described above. The computer program described above includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium described above can at least include: any entity or device capable of carrying computer program code to a device / electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk.

[0181] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).The storage medium may include RAM, flash memory, hard disk drive (HDD), or solid-state drive (SSD), and may also include combinations of the above types of memory.

[0182] This application provides a computer program product that, when run on a processor, enables the processor to implement the steps in the above-described method embodiments.

[0183] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0184] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0185] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For example, the division of the above modules or units is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of the apparatus or units may be electrical, mechanical, or other forms.

[0186] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of this embodiment.

[0187] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it; although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.Book Page 12 / 12, Page 15 of CN 121093296 A, Figure 1, Figure 2, Attached Drawings of the Specification, Page 1 / 3, Page 16 of CN 121093296 A, Figure 3, Figure 4, Attached Drawings of the Specification, Page 2 / 3, Page 17 of CN 121093296 A, Figure 5, Figure 6, Attached Drawings of the Specification, Page 3 / 3, Page 18 of CN 121093296 A, CREATION PROCESSING METHOD, ELECTRONIC DEVICE, AND STORAGE MEDIUM, ABSTRACT, The present application provides a creation processing method, an electronic device, and a storage medium, applicable to the field of human-computer interaction technology. The creation processing method includes: acquiring physiological characteristic information of a target object; determining emotional state information of the target object based on the physiological characteristic information; determining target weight parameters based on the emotional state information; wherein the target weight parameters include a dominant weight of the target object and a collaborative weight of artificial intelligence; and performing human-computer collaborative creation based on the target weight parameters to generate collaborative creation content. The embodiments of thepresent application can determine target weight parameters through the emotional state information of the user, so as to determine the dominant weight of the target object and the collaborative weight of artificial intelligence, achieve dynamic allocation of creative dominance in human-computer collaborative creation, improve the efficiency of human-computer collaborative creation, and thus enhance user experience.

Claims

1. A creative processing method, characterized in that, include: Obtain physiological characteristic information of the target object; Based on the physiological characteristics, the emotional state information of the target object is determined; Based on the emotional state information, target weight parameters are determined; wherein, the target weight parameters include the dominant weight of the target object and the collaborative weight of artificial intelligence; Based on the target weight parameters, human-computer collaborative creation is carried out to generate collaborative content.

2. The creative processing method according to claim 1, characterized in that, The step of determining the target weight parameters based on the emotional state information includes: Based on the emotional state information and the preset weight adjustment function, the cooperation weight is determined; Based on the cooperation weight, the dominant weight is determined; Based on the collaboration weight and the dominant weight, the target weight parameter is determined.

3. The creative processing method according to claim 2, characterized in that, The physiological characteristic information includes physiological signals of the target object collected during the human-computer collaborative creation process, and feedback information when the target object reads the AI-generated content. The physiological signals include at least one of electroencephalogram (EEG), heart rate, and skin conductance. The feedback information includes at least one of voice signals and facial expression features. The emotional state information includes a negative emotion index and an inspiration blockage index. Determining the emotional state information of the target object based on the physiological characteristic information includes: Based on a preset multimodal emotion recognition model, emotion recognition is performed on the physiological feature information to obtain the negative emotion index; Based on the physiological signals, the inspiration blockage index is determined.

4. The creative processing method according to claim 3, characterized in that, The determination of cooperation weights based on the emotional state information and a preset weight adjustment function includes: The frequency of proactive actions of the target object in response to the content created by the artificial intelligence is obtained; wherein, the frequency of proactive actions is determined based on the number of times information is manually input, the number of times modifications are undone, and the number of times suggestions are requested; The collaboration weight is determined based on the negative emotion index, the inspiration blockage index, the frequency of proactive behavior, and a preset weight adjustment function.

5. The creative processing method according to claim 4, characterized in that, The determination of collaboration weights based on the negative emotion index, the inspiration blockage index, the frequency of proactive behavior, and a preset weight adjustment function includes: The negative emotion index, the inspiration blockage index, and the frequency of proactive behavior are input into the weight adjustment function, causing the weight adjustment function to perform the following operations: The product of the first sensitivity coefficient and the negative emotion index, the product of the second sensitivity coefficient and the inspiration blockage index, and the product of the third sensitivity coefficient and the frequency of proactive behavior are respectively used as the first adjustment weight, the second adjustment weight, and the third adjustment weight. Subtract the third adjustment weight from the sum of the first and second adjustment weights to obtain the total adjustment weight; The sum of the total adjustment weight and the basic weight is taken as the cooperation weight.

6. The creative processing method according to claim 5, characterized in that, The basic weights are obtained in the following way: Determine the creation stage in which human-computer collaborative creation takes place; wherein, the creation stage includes any one of the conception stage, generation stage, and polishing stage; If the creation stage is the conception stage, then the default value is increased by the first default value to obtain the basic weight; If the creation stage is the generation stage, then the preset default value will be used as the basic weight; If the creation stage is a polishing stage, then the default value is reduced by the second default value to obtain the basic weight.

7. The creative processing method according to claim 5, characterized in that, Also includes: Obtain the response behavior information of the target object to the content created by the artificial intelligence; wherein, the response behavior information includes accepting or ignoring suggestions, the extent of modification, and subjective satisfaction rating; Based on the response behavior information and the preset algorithm, the sensitivity coefficient in the weight adjustment function is adjusted; wherein, the sensitivity coefficient includes at least one of a first sensitivity coefficient, a second sensitivity coefficient, and a third sensitivity coefficient.

8. The creative processing method according to any one of claims 1-7, characterized in that, The process of generating collaborative content based on the target weight parameters includes: If the collaboration weight is greater than the third preset value, then creative suggestions will be automatically pushed through artificial intelligence to generate collaborative content; If the collaboration weight is less than the fourth preset value, then the creation suggestion will not be automatically pushed through artificial intelligence, but the creation suggestion will be pushed in response to the call operation of the target object to generate collaborative creation content; wherein, the third preset value is greater than the fourth preset value.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 8.

Images