Interaction method, system, device, medium and product

Abstract

The invention provides an interaction method, system and device, a medium and a product, and the method comprises the steps: obtaining a target monitoring range according to the similarity between a first digital person and each second digital person; detecting whether a third digital person exists in the target monitoring range or not; the third digital person is a digital person except the first digital person and the second digital person, and the distance between the third digital person and the first digital person is gradually reduced; and when it is detected that a third digital person exists in the target monitoring range, the received sound intensity of the third digital person is adjusted according to the current appearance attribute information of the third digital person, the similarity between the third digital person and the first digital person, and the similarity between the third digital person and each second digital person. According to the invention, in the interaction process of multiple digital persons, the sound intensity heard by the third-party digital person is dynamically adjusted to prevent the third-party digital person from obtaining the complete interaction content among the multiple digital persons, so that the leakage of interaction information is avoided, and the interaction security is ensured.

Description

Technical Field

[0001] The present invention relates to the field of virtual interaction technologies, and in particular, to an interaction method, system, device, medium and product. Background Art

[0002] The metaverse is a virtual world created by using technological means for connection and mapping and interacting with the real world. In the metaverse, as the carrier of users' virtual identities, the interaction between digital humans can not only simulate face-to-face communication in reality, but also break through the limitations of physical space, realizing interactions across regions and time, greatly expanding the interaction boundaries.

[0003] Currently, in the metaverse, no security measures are taken for the interaction between digital humans. When two digital humans are interacting, if a third digital human joins, and the joining third digital human has not undergone security verification, the interaction content between the two digital humans will be leaked by the third digital human, resulting in the lack of guarantee for interaction security.

[0004] Therefore, there is an urgent need for an interaction method, system, device, medium and product to solve the above problems. Summary of the Invention

[0005] The present invention provides an interaction method, system, device, medium and product to solve the defects in the prior art.

[0006] The present invention provides an interaction method, including: Obtaining a target monitoring range according to the similarity between a first digital human and each second digital human; the first digital human is the digital human sending a data interaction request, and the second digital human is the digital human receiving the data interaction request; Detecting whether there is a third digital human within the target monitoring range; the third digital human is a digital human other than the first digital human and the second digital human and whose distance from the first digital human is gradually decreasing; When it is detected that there is the third digital human within the target monitoring range, adjusting the received sound intensity of the third digital human according to the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans.

[0007] According to an interaction method provided by the present invention, the adjusting the received sound intensity of the third digital human according to the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans includes: Generate a first attribute summary of the third digital human according to the current appearance attribute information of the third digital human; the current appearance attribute information includes multiple items among skin color, hairstyle, clothing, and accessories; Obtain the latest attribute summary of the third digital human from multiple attribute summaries stored in the blockchain as the second attribute summary of the third digital human; When the first attribute summary is the same as the second attribute summary, adjust the received sound intensity of the third digital human according to the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans.

[0008] According to an interaction method provided by the present invention, the adjusting the received sound intensity of the third digital human according to the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans includes: Select the minimum similarity among the similarity between the third digital human and the first digital human and the similarity between the third digital human and multiple second digital humans; Select the maximum similarity among the similarities between the first digital human and multiple second digital humans; Adjust the received sound intensity of the third digital human according to the output sound energy of the target digital human, the distance between the third digital human and the target digital human, and the minimum similarity and the maximum similarity; the target digital human is the digital human currently outputting sound among the first digital human and multiple second digital humans.

[0009] According to an interaction method provided by the present invention, the adjusting the received sound intensity of the third digital human according to the output sound energy of the target digital human, the distance between the third digital human and the target digital human, and the minimum similarity and the maximum similarity includes: Calculate a target area according to the distance between the third digital human and the target digital human; Determine a target sound intensity according to the ratio between the output sound energy and the target area, and the ratio between the minimum similarity and the maximum similarity; Select the maximum sound intensity between the target sound intensity and a preset sound intensity, and adjust the received sound intensity of the third digital human according to the maximum sound intensity.

[0010] According to an interaction method provided by the present invention, the attribute summaries in the blockchain are stored based on the following steps: When the current appearance attribute information of any digital human is modified, the values of each attribute parameter in the current appearance attribute information of the any digital human are obtained, and according to the modification time corresponding to the value of each attribute parameter, an attribute list is constructed by applying all the attribute parameters and the values of all the attribute parameters in the current appearance attribute information of the any digital human; Calculate the hash value of the attribute list to obtain the attribute summary of the any digital human, and store the attribute summary of the any digital human in the blockchain.

[0011] According to an interaction method provided by the present invention, the obtaining of the target monitoring range according to the similarity between the first digital human and each second digital human includes: Calculate the standard deviation of the similarity between the first digital human and multiple second digital humans; Select the maximum similarity from the similarities between the first digital human and multiple second digital humans; Select the maximum distance from the distances between the first digital human and multiple second digital humans; Determine a first target distance according to the ratio between the standard deviation and the maximum similarity, and the maximum distance; Select the minimum distance from the first target distance and a second target distance, and determine the target monitoring range according to the minimum distance; the second target distance is determined according to the interaction environment corresponding to the data interaction request.

[0012] According to an interaction method provided by the present invention, the calculation steps of the similarity between the first digital human and each second digital human include: Calculate the similarity between the interaction influence attribute of the first digital human and the interaction influence attributes of each second digital human to obtain the similarity between the first digital human and each second digital human; Wherein, for the interaction influence attribute of each digital human among the first digital human and each second digital human, the interaction influence attribute includes multiple items such as preference data, age, and registration duration.

[0013] The present invention also provides an interaction system, including: A first processing unit, configured to obtain a target monitoring range according to the similarity between the first digital human and each second digital human; the first digital human is the digital human that sends a data interaction request, and the second digital human is the digital human that receives the data interaction request; A second processing unit, configured to detect whether there is a third digital human within the target monitoring range; the third digital human is a digital human other than the first digital human and the second digital human, and the distance between the third digital human and the first digital human gradually decreases; An interaction unit, configured to, when detecting the presence of the third digital human within the target monitoring range, adjust the received sound intensity of the third digital human according to the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarities between the third digital human and each of the second digital humans.

[0014] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the interaction method as described in any one of the above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the interaction method as described in any one of the above is implemented.

[0016] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the interaction method as described in any one of the above is implemented.

[0017] The interaction method, system, device, medium, and product provided by the present invention determine the monitoring range of interaction security protection according to the similarities between the first digital human participating in the interaction and each of the second digital humans, and monitor whether there is a third digital human whose distance from the first digital human is gradually decreasing and who does not participate in the interaction within this monitoring range. If there is a third digital human, then in combination with the current appearance attribute information of the third digital human, as well as the similarity between the third digital human and the first digital human and the similarities between the third digital human and each of the second digital humans, dynamically adjust the currently received sound intensity of the third digital human. Thereby, when the third digital human approaches, by adjusting the sound intensity it can hear, it is possible to prevent it from obtaining the complete interaction content, and further avoid the leakage of interaction information, ensuring the security of the interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 is a flowchart of the interaction method provided by the present invention.

[0020] Figure 2 is one of the schematic diagrams showing the appearance attributes of the digital human provided by the present invention.

[0021] Figure 3It is the second schematic diagram of the display of the appearance attributes of the digital human provided by the present invention.

[0022] Figure 4 It is the schematic diagram of the distribution of attribute summaries in the blockchain provided by the present invention.

[0023] Figure 5 It is the schematic structural diagram of the interaction system provided by the present invention.

[0024] Figure 6 It is the schematic structural diagram of the electronic device provided by the present invention. Detailed implementation manners

[0025] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts fall within the protection scope of the present invention.

[0026] The metaverse is a virtual world created by using technological means for linking and interacting with the real world in a mapped manner. In the metaverse, the operations of users can be presented through three-dimensional (3D) virtual digital human images to achieve virtual interaction.

[0027] Currently, in the metaverse, there are no security measures for the interaction between digital humans. That is, when two digital humans are interacting, if a third digital human joins, then the third digital human that joins will hear all the interaction content between these two digital humans. If the third digital human has not passed the security verification, the interaction content between the two digital humans will be leaked by the third digital human, resulting in the lack of guarantee of interaction security.

[0028] For this reason, the present application provides an interaction method. This method determines the monitoring range according to the similarity between the first digital human participating in the interaction and each second digital human, and monitors whether there is a third digital human whose distance is shrinking and not participating in the interaction within the monitoring range. If there is a third digital human, the current received sound intensity of the third digital human is dynamically adjusted according to the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each second digital human, so as to adjust the sound heard by the third digital human, so that when an abnormal third digital human approaches, the sound intensity heard by it is adjusted to avoid the leakage of interaction information and ensure interaction security.

[0029] Figure 1 It is the schematic flow diagram of the interaction method provided by the present invention, as Figure 1As shown, the method includes step 110, step 120, and step 130. This method can be applied to various interaction scenarios, such as party scenarios, work scenarios, etc., and this embodiment does not specifically limit this.

[0030] Step 110, obtain a target monitoring range according to the similarity between the first digital human and each second digital human; the first digital human is the digital human that sends a data interaction request, and the second digital human is the digital human that receives the data interaction request.

[0031] The first digital human here (described by digital human A in subsequent steps) is the digital human currently initiating an interaction in the metaverse, and the second digital human (described by digital human B or digital human C in subsequent steps) is the digital human interacting with the first digital human.

[0032] Optionally, during the interaction, the similarity between the first digital human and each second digital human can be calculated first based on their respective corresponding characteristic attributes (such as the relevant interaction influence attributes filled in by the user during registration, or the characteristic attributes formed by encoding the model parameters) to determine the similarity between the first digital human and each second digital human, so as to indicate the similarity degree between the first digital human initiating the interaction and each second digital human. Thus, through the similarity degree, the privacy of the interaction content between the first digital human initiating the interaction and each second digital human is characterized. For example, the higher the similarity degree, the more likely the first digital human and each second digital human will say some private content, that is, the higher the possibility of having words that they do not want other digital humans to hear. If the similarity degree is lower, there is no private content between the two, that is, the possibility of having words that they do not want other digital humans to hear in their interaction content is lower.

[0033] In a possible embodiment, the calculation step of the similarity between the first digital human and each second digital human includes: calculating the similarity between the interaction influence attribute of the first digital human and the interaction influence attributes of each second digital human to obtain the similarity between the first digital human and each second digital human; wherein, for the interaction influence attribute of each digital human among the first digital human and each second digital human, the interaction influence attribute includes multiple items such as preference data, age, and registration duration.

[0034] Optionally, first determine the respective corresponding interaction influence attributes of digital human A and each second digital human interacting with digital human A. The interaction influence attribute here is an attribute that characterizes the internal interaction characteristics of the digital human, and can be multiple items among the attributes that characterize the internal interaction characteristics of the digital human, such as preference data, age, and registration duration in the metaverse. The interaction influence attribute here can specifically be filled in by the user during digital human registration and maintained by the metaverse based on the user's use of the digital human.

[0035] After obtaining the interaction influence attributes corresponding to Digital Human A and each second digital human interacting with Digital Human A, the interaction influence attributes of Digital Human A can be constructed into an attribute set, specifically A = {Preference Data A, Age A,...}. Similarly, the interaction influence attributes of each second digital human are constructed into an attribute set. For example, if a second digital human is Digital Human B, the corresponding attribute set is B = {Preference Data B, Age B,...}; if another second digital human is Digital Human C, the corresponding attribute set is C = {Preference Data C, Age C,...}.

[0036] Subsequently, calculate the similarity between the interaction influence attributes of the first digital human and those of each second digital human to obtain the similarity between the first digital human and each second digital human, thereby determining the privacy of the interaction content between digital humans, and then controlling the received sound intensity of other digital humans (other digital humans except the first digital human and the second digital human, such as Digital Human 1, Digital Human 2, etc.) based on the privacy, thereby enhancing the security of virtual interaction.

[0037] The similarity calculation here can be through cosine similarity or Jaccard similarity, etc., and this embodiment does not specifically limit this.

[0038] Taking a specific example below, the process of calculating the similarity between the first digital human and each second digital human will be described.

[0039] For example, calculate the similarity between Digital Human A and Digital Human B When calculating, it can be obtained through the following formula: ; Wherein, and are the attribute sets corresponding to Digital Human A and Digital Human B respectively.

[0040] Another example, when calculating the similarity between Digital Human A and Digital Human C When calculating, it can be obtained through the following formula: ; Wherein, and are the attribute sets corresponding to Digital Human A and Digital Human C respectively.

[0041] After obtaining the similarity between the first digital human and each second digital human through the above steps, the interaction monitoring range (also known as the target monitoring range) between the first digital human and each second digital human can be determined to monitor whether there are other abnormal digital humans eavesdropping on the interaction content between the first digital human and each second digital human. For example, when digital human A communicates with digital human B and digital human C at a party, at this time, it will be detected in real time whether there are other abnormal digital humans within the interaction monitoring range corresponding to digital human A. When an abnormal digital human is detected, the received sound intensity of the other abnormal digital human will be restricted, thereby preventing other abnormal digital humans from eavesdropping on the interaction content between the first digital human and each second digital human, and further ensuring the security of the interaction content between the first digital human and each second digital human.

[0042] The target monitoring range here can be obtained by training a neural network model (such as a convolutional neural network or a feedforward neural network, etc.) through the similarity between the sample second digital human interacting with the sample first digital human and the sample first digital human, as well as the monitoring distance label corresponding to the sample first digital human, to obtain an identification model, and inputting the similarity between the first digital human and each second digital human into the identification model, so that the identification model can identify the monitoring distance corresponding to the first digital human. Finally, with the position of the first digital human as the center and the monitoring distance corresponding to the first digital human as the radius, the target monitoring range is determined; for another example, the similarity between the first digital human and each second digital human is logically calculated jointly with other parameters (such as the distance between the first digital human and each second digital human, the interaction scenario, etc.) to obtain the monitoring distance corresponding to the first digital human, and the range determined with the position of the first digital human as the center and the monitoring distance corresponding to the first digital human as the radius is used as the target monitoring range, etc. This embodiment does not make specific limitations on this.

[0043] Step 120: Detect whether there is a third digital human within the target monitoring range; the third digital human is a digital human other than the first digital human and the second digital human and whose distance from the first digital human is gradually decreasing.

[0044] Optionally, after obtaining the target monitoring range, the distances between other digital humans (such as digital human 1, digital human 2, etc.) other than the first digital human and the second digital human within the target monitoring range and digital human A can be detected. If it is detected that there is a digital human among the other digital humans whose distance is gradually decreasing, it will be used as the third digital human, and all digital humans participating in the interaction (that is, the first digital human and the second digital human) will be reminded that there is another digital human approaching. At the same time, by adjusting the received sound intensity, the sound that the third digital human can hear is adjusted until the third digital human's normal receiving volume is restored after obtaining the authorization to join from the first digital human and the second digital human, so as to ensure the security and order of the interaction.

[0045] It should be noted that the third digital human here can be one or more, and this embodiment does not specifically limit this. For the sake of simplicity of description below, the third digital human is taken as digital human 1 as an example for description.

[0046] Step 130, when it is detected that the third digital human exists within the target monitoring range, adjust the received sound intensity of the third digital human according to the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans.

[0047] Optionally, when it is detected that a third digital human exists within the target monitoring range, obtain the current appearance attribute information of the third digital human.

[0048] For each digital human, its current appearance attribute information refers to the current attribute information representing the appearance of the digital human, such as multiple attributes among skin color, hairstyle, clothing, and accessories. The current appearance attribute information can be generated by the user's self-editing of the appearance of the digital human. For example, for a certain digital human model, if the user can only change the clothing and not the hairstyle, then the current appearance attribute information of this digital human only includes the clothing. If the user can change both the clothing and the hairstyle, then the current appearance attribute information of this digital human includes the clothing and the hairstyle.

[0049] Figure 2 It is one of the schematic diagrams showing the appearance attributes of the digital human provided by the present invention. Figure 3 It is the second of the schematic diagrams showing the appearance attributes of the digital human provided by the present invention.

[0050] In a possible implementation manner, during the appearance editing process of the digital human, the attributes can be pre-made, and the user only performs attribute replacement to simplify the operation and ensure the overall style of the digital human is coordinated, thereby improving the quality and effect of the digital human appearance. For example, Figure 2 Schematically shows different pre-made hairstyles. For a certain digital human, the user can select one of them to replace the hairstyle of the digital human model, and then obtain the value corresponding to the hairstyle attribute parameter of the digital human. Among them, for this type of attribute, each hairstyle corresponds to a unique identifier in the background. Once the user selects a certain hairstyle to replace the hairstyle of the digital human model, the value corresponding to the hairstyle attribute parameter of the digital human is updated to the identifier of this hairstyle. That is to say, during the appearance editing process of the digital human, if any type of attribute is formed by selecting different pre-made attribute identifiers for appearance editing, then the value of this type of attribute is the identifier selected for editing.

[0051] In another possible implementation, during the appearance editing process of the digital human, the attributes can be created by the user for modeling to ensure the personalization, accuracy, and rich details of the digital human's appearance, enhancing the overall visual effect and realism of the digital human. For example, the user creates a corresponding hairstyle model for a certain digital human model. Specifically, as shown in Figure 3 then the value of the hairstyle attribute of this digital human is determined based on the area covered by the modeled hairstyle model and the color of the hairstyle. That is to say, during the appearance editing process of the digital human, if any type of attribute is created during modeling, the value of this type of attribute is determined by the parameters of the modeled attribute model.

[0052] After obtaining the current appearance attribute information of the third digital human based on the above steps, the received sound intensity of the third digital human can be dynamically adjusted by combining the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarities between the third digital human and each second digital human, so as to reduce the received sound intensity of the third digital human when the interaction content between the interacting digital humans is highly private, thereby ensuring interaction security.

[0053] During the adjustment process of the received sound intensity, the neural network model (such as a convolutional neural network or a feedforward neural network, etc.) can be trained through the sample appearance attribute information of the sample third digital human, the similarity between the sample third digital human and the sample first digital human, the similarities between the sample third digital human and each sample second digital human, and the received sound intensity label of the sample third digital human to obtain a prediction model, and the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarities between the third digital human and each second digital human are input into the prediction model to predict the received sound intensity of the third digital human; or, for example, the received sound intensity of the third digital human is obtained after multiple logical judgments and / or logical calculations by combining the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the third digital human and each second digital human. This embodiment does not make specific limitations on this.

[0054] The method provided in this embodiment determines the monitoring range of interactive security protection according to the similarity between the first digital human participating in the interaction and each second digital human, and monitors whether there is a third digital human with a reduced distance and not participating in the interaction within this monitoring range. If there is a third digital human, the current received sound intensity of the third digital human is dynamically adjusted by combining the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each second digital human. As a result, when the third digital human approaches, the sound intensity it can hear is adjusted to prevent it from obtaining complete interaction content, thereby avoiding the leakage of interaction information and ensuring interaction security.

[0055] In some embodiments, step 130 specifically includes: Step 131, generating a first attribute summary of the third digital human according to the current appearance attribute information of the third digital human; the current appearance attribute information includes multiple items among skin color, hairstyle, clothing, and accessories; Step 132, obtaining the latest attribute summary of the third digital human from multiple attribute summaries stored in the blockchain as the second attribute summary of the third digital human; Step 133, when the first attribute summary is the same as the second attribute summary, adjusting the received sound intensity of the third digital human according to the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans.

[0056] Optionally, when adjusting the received sound intensity, the current appearance attribute information of the third digital human can be obtained in real time, and this current appearance attribute information is the currently latest updated current appearance attribute information, which includes multiple items among skin color, hairstyle, clothing, and accessories.

[0057] After obtaining the values of all attribute parameters in the current appearance attribute information of the third digital human, an attribute list can be constructed by arranging all attribute parameters and the values of all attribute parameters in the current appearance attribute information of the third digital human in the order from the most recent modification time to the oldest. For example, if attribute 1 was modified today and attribute 2 was modified yesterday, the data format in the attribute list is attribute 1, the value of attribute 1, attribute 2, the value of attribute 2,....

[0058] Immediately afterwards, the attribute list of the third digital human is encoded, such as calculating a hash value, to obtain the first attribute summary of the third digital human.

[0059] It should be noted that for each digital human in the blockchain here, a corresponding block is pre-configured, and in the block of each digital human, there is stored an attribute digest generated when the appearance attribute information of each digital human changes at different time periods, and the attribute digests at each time period are arranged in sequence according to their corresponding change time periods.

[0060] In a possible implementation manner, the attribute digest in the blockchain is stored based on the following steps: when the current appearance attribute information of any digital human is modified, the values of each attribute parameter in the current appearance attribute information of the any digital human are obtained, and according to the modification time corresponding to the value of each attribute parameter, all the attribute parameters and the values of all the attribute parameters in the current appearance attribute information of the any digital human are used to construct an attribute list; calculate the hash value of the attribute list to obtain the attribute digest of the any digital human, and store the attribute digest of the any digital human into the blockchain.

[0061] Optionally, for any digital human, it is monitored in real time whether its current appearance attribute information is modified. If it is modified, the current appearance attribute information is obtained to generate a corresponding attribute digest. The specific generation steps can refer to the generation steps of the first attribute digest and will not be elaborated here. And the generated digest is stored into the blockchain. During the storage process, in the blockchain, a block is allocated for each digital human, and the attribute digests generated each time a change occurs will be connected behind the corresponding block in the order of the change time, specifically as Figure 4 shown. Thus, by storing the attribute digest of the digital human appearance attribute information in the blockchain and utilizing the immutable and traceable characteristics of the blockchain, the integrity and traceability of the digital human appearance attribute information are ensured, thereby improving the security and reliability of digital human interaction.

[0062] In summary, when obtaining the second attribute digest, the block corresponding to the third digital human can be located in the blockchain first, and according to the storage time of the attribute digest, the most recently stored (the latest stored) attribute digest in the block is selected as the second attribute digest of the third digital human.

[0063] Subsequently, compare whether the calculated first attribute digest is the same as the second attribute digest stored in the blockchain. If the first attribute digest is not the same as the second attribute digest, this means that the appearance attribute information of the third digital human may be tampered with or there is a situation where an update is not synchronized. At this time, it is characterized that the third digital human is an abnormal digital human, and the sound that the third digital human can receive is turned off, that is, the sound reception intensity of the third digital human is set to 0, so that the third digital human cannot hear the interaction content between the interacting digital humans, thereby avoiding the failure of the interaction security protection mechanism due to incorrect or tampered appearance attribute information, and further avoiding the leakage of interaction information and ensuring the security of digital human interaction.

[0064] If the first attribute summary is the same as the second attribute summary, it indicates that the appearance attribute information of the currently obtained third digital human is consistent with the appearance attribute information corresponding to the latest attribute summary recorded in the blockchain and has not been tampered with or modified. At this time, the received sound intensity of the third digital human can be dynamically adjusted according to the similarity between the third digital human and the first digital human, as well as the similarity between the third digital human and each second digital human, so as to reduce the received sound intensity of the third digital human when the interaction content between the interacting digital humans is highly private, thereby ensuring interaction security.

[0065] It should be noted that the calculation steps of the similarity between the third digital human and the first digital human, as well as the similarity between the third digital human and each second digital human, are similar to the calculation steps of the similarity between the first digital human and each second digital human. That is, the similarity between the third digital human and the first digital human can be calculated based on the interaction influence attributes of the third digital human and the first digital human, and the similarity between the third digital human and the second digital human can be calculated based on the interaction influence attributes of the third digital human and the second digital human. Details are not elaborated here.

[0066] The method provided in this embodiment compares the attribute summary generated from the current appearance attribute information of the third digital human with the latest attribute summary obtained from the blockchain. When the two are the same, the received sound intensity of the third digital human is adjusted according to the similarity between the third digital human and the first digital human and each second digital human, so as to utilize the immutable characteristic of the blockchain to prevent the risk of information tampering, ensure the authenticity and integrity of the appearance attribute information of the third digital human, and thus be able to perform corresponding operations based on accurate appearance attribute information and similarity when adjusting the sound intensity, effectively avoiding the leakage of interaction information and ensuring the security and reliability of digital human interaction.

[0067] In some embodiments, step 133 specifically includes: Step 133-1, select the minimum similarity among the similarity between the third digital human and the first digital human and the similarity between the third digital human and multiple second digital humans; Step 133-2, select the maximum similarity among the similarity between the first digital human and multiple second digital humans; Step 133-3, adjust the received sound intensity of the third digital human according to the output sound energy of the target digital human, the distance between the third digital human and the target digital human, and the minimum similarity and the maximum similarity; the target digital human is the digital human currently outputting sound among the first digital human and multiple second digital humans.

[0068] Optionally, when adjusting the received sound intensity, if it is determined that the current appearance attribute information of the third digital human is normal (that is, the first attribute summary of the third digital human is the same as the second attribute summary), the minimum similarity can be selected first from the first similarity set (that is, the set including the similarity between the third digital human and the first digital human, and the similarities between the third digital human and multiple second digital humans) to obtain the minimum similarity. , which indicates the least similar degree between the third digital human and the first digital human and all second digital humans.

[0069] In addition, the maximum similarity is selected from the second similarity set (that is, the set including the similarities between the first digital human and multiple second digital humans) to obtain the maximum similarity. , the larger this value is, the more similar the digital humans are, the stronger the interaction privacy is, that is, the greater the possibility of not wanting to be heard.

[0070] Moreover, determine the output sound energy of the target digital human (that is, the digital human that outputs sound currently among the first digital human and multiple second digital humans, such as the first digital human or any second digital human). . For example, if the current digital human A is speaking, then digital human A is taken as the target digital human. Correspondingly, the output sound energy of the target digital human is the output sound energy of digital human A.

[0071] Immediately, combine the output sound energy of the target digital human , the distance between the third digital human and the target digital human , the minimum similarity and the maximum similarity to dynamically adjust the received sound intensity of the third digital human, so as to reduce the received sound intensity of the third digital human when the interaction content privacy between the interacting digital humans is relatively strong, thereby ensuring interaction security.

[0072] Here, the step of jointly adjusting the received sound intensity can be realized by performing associated mapping on the output sound energy of the target digital human , the distance between the third digital human and the target digital human , the minimum similarity and the maximum similarity according to a pre-trained neural network model (such as a convolutional network, a feedforward network, etc.), or it can be realized by performing multiple non-linear calculations on the output sound energy of the target digital human , the distance between the third digital human and the target digital human , the minimum similarity and the maximum similarity . This embodiment does not make specific limitations on this.

[0073] In a possible implementation, the step of adjusting the received sound intensity of the third digital person according to the output sound energy of the target digital person, the distance between the third digital person and the target digital person, and the minimum similarity and the maximum similarity specifically includes: calculating the target area according to the distance between the third digital person and the target digital person; determining the target sound intensity according to the ratio between the output sound energy and the target area, and the ratio between the minimum similarity and the maximum similarity; selecting the maximum sound intensity from the target sound intensity and the preset sound intensity, and adjusting the received sound intensity of the third digital person according to the maximum sound intensity.

[0074] Optionally, the initial sound intensity can be determined by calculating the ratio between the output sound energy of the target digital person and the target area, and the minimum similarity can be calculated by and the maximum similarity The ratio between them can determine the attenuation coefficient of the sound, specifically the minimum similarity With the maximum similarity The larger the gap is, the more it means that the third digital person and all the digital persons currently interacting (that is, the first digital person and the second digital person) do not belong to the same interaction circle, and the data needs to be kept confidential, so it is necessary to accelerate the attenuation of the receiving sound intensity of the third digital person.

[0075] Therefore, by comparing the ratio between the output sound energy of the target digital person and the target area with the minimum similarity and the maximum similarity The target sound intensity can be obtained by multiplying the ratio between the target sound intensity and the preset sound intensity, and the maximum sound intensity can be determined by comparing the target sound intensity with the preset sound intensity to obtain the received sound intensity of the third digital person, thereby adjusting the sound that the third digital person can hear according to the received sound intensity of the third digital person. The preset sound intensity is the preset minimum sound intensity that the third digital person can receive, such as 0.

[0076] The following assumes that the sound intensity is set to 0 and the receiving sound intensity of the third digital person is The specific calculation formula is described as follows: .

[0077] The method provided in this embodiment dynamically adjusts the received sound intensity of the third digital human by comprehensively considering the output sound energy of the target digital human, the distance between the third digital human and the target digital human, as well as the minimum similarity and the maximum similarity. Thereby, while ensuring the privacy of the digital human interaction content, the risk of the interaction information being obtained by an unauthorized third party is effectively reduced, and the security and reliability of the digital human interaction in the metaverse are significantly improved.

[0078] In some embodiments, step 110 specifically includes: Calculating the standard deviation of the similarities between the first digital human and multiple second digital humans; Selecting the maximum similarity among the similarities between the first digital human and multiple second digital humans; Selecting the maximum distance among the distances between the first digital human and multiple second digital humans; Determining a first target distance according to the ratio between the standard deviation and the maximum similarity, and the maximum distance; Selecting the minimum distance between the first target distance and the second target distance, and determining the target monitoring range according to the minimum distance; the second target distance is determined according to the interaction environment corresponding to the data interaction request.

[0079] Optionally, when determining the target monitoring range, the standard deviation of the similarities between the first digital human and multiple second digital humans can be calculated to obtain the standard deviation . This standard deviation indicates the degree of deviation of the similarities. The smaller the standard deviation, the more similar all the interacting digital humans (i.e., the first digital human and the second digital humans) are, the higher the privacy of the interaction content, that is, the higher the possibility of words that the interaction content does not want to be heard by a third party, and the greater the monitoring distance. Therefore, it is inversely proportional to the monitoring distance . The larger the standard deviation, the greater the difference in similarities among all the interacting digital humans, the lower the privacy of the interaction content, that is, the lower the possibility of words that the interaction content does not want to be heard by outsiders.

[0080] Moreover, the maximum distance is selected among the distances between the first digital human and multiple second digital humans , and the maximum similarity is selected among the similarities between the first digital human and multiple second digital humans . The larger this maximum similarity , the more similar the interacting digital humans are, the higher the privacy of the interaction content, that is, the greater the possibility of words that do not want to be heard, and the greater the interaction monitoring distance. Therefore, it is directly proportional to the monitoring distance .

[0081] Therefore, after adding the ratio between the standard deviation and the maximum similarity to 1 and multiplying the result by the maximum distance, the first target distance can be obtained. Then, the maximum distance threshold, that is, the second target distance, can be adaptively determined according to the interaction distance threshold associated with the interaction environment corresponding to the data interaction request. For example, if the interaction environment is a bounded environment (such as having a party in a room), the second target distance is the distance between the first digital human and the boundary. If the interaction environment is an unbounded environment (such as having a party on an open grassland), the second target distance is a preset distance threshold.

[0082] Subsequently, the minimum distance is selected as the monitoring distance from the first target distance and the second target distance , and a target monitoring range is constructed with the monitoring distance as the radius and the position of the first digital human as the center. Among them, the specific calculation formula of the monitoring distance is as follows: .

[0083] The method provided in the present embodiment comprehensively considers the similarity standard deviation, maximum similarity, and maximum distance between the first digital human and multiple second digital humans, and combines the characteristics of the interaction environment to dynamically determine the target monitoring range, effectively balancing the privacy of the interaction content and the adaptability of the monitoring range, and ensuring the security and flexibility of the digital human interaction in the metaverse.

[0084] Next, the interaction system provided by the present invention will be described. The interaction system described below can be correspondingly referred to the interaction method described above.

[0085] Figure 5 is a schematic structural diagram of the interaction system provided by the present invention. As Figure 5 shown, the system includes: The first processing unit 510 is used to obtain a target monitoring range according to the similarity between the first digital human and each second digital human; the first digital human is the digital human that sends a data interaction request, and the second digital human is the digital human that receives the data interaction request; The second processing unit 520 is used to detect whether there is a third digital human within the target monitoring range; the third digital human is a digital human other than the first digital human and the second digital human and whose distance from the first digital human is gradually decreasing; The interaction unit 530 is used to adjust the received sound intensity of the third digital human according to the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans when it is detected that the third digital human exists within the target monitoring range.

[0086] The system provided in this embodiment determines the monitoring range of interactive security protection according to the similarity between the first digital human participating in the interaction and each of the second digital humans, and monitors whether there is a third digital human whose distance from the first digital human is gradually decreasing and who is not participating in the interaction within this monitoring range. If there is a third digital human, the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans are combined to dynamically adjust the currently received sound intensity of the third digital human. Thus, when the third digital human approaches, by adjusting the sound intensity it can hear, it is possible to prevent it from obtaining the complete interaction content, thereby avoiding the leakage of interaction information and ensuring the security of the interaction.

[0087] In some embodiments, the interaction unit 530 is specifically used for: Generate a first attribute summary of the third digital human according to the current appearance attribute information of the third digital human; the current appearance attribute information includes multiple items such as skin color, hairstyle, clothing, and accessories; Obtain the latest attribute summary of the third digital human from multiple attribute summaries stored in the blockchain as the second attribute summary of the third digital human; When the first attribute summary is the same as the second attribute summary, adjust the received sound intensity of the third digital human according to the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans.

[0088] In some embodiments, the interaction unit 530 is further used for: Select the minimum similarity among the similarity between the third digital human and the first digital human and the similarity between the third digital human and multiple second digital humans; Select the maximum similarity among the similarities between the first digital human and multiple second digital humans; Adjust the received sound intensity of the third digital human according to the output sound energy of the target digital human, the distance between the third digital human and the target digital human, and the minimum similarity and the maximum similarity; the target digital human is the digital human currently outputting sound among the first digital human and multiple second digital humans.

[0089] In some embodiments, the interaction unit 530 is further used for: Calculate a target area based on the distance between the third digital human and the target digital human; Determine a target sound intensity based on the ratio between the output sound energy and the target area, and the ratio between the minimum similarity and the maximum similarity; Select the maximum sound intensity from the target sound intensity and a preset sound intensity, and adjust the received sound intensity of the third digital human according to the maximum sound intensity.

[0090] In some embodiments, the attribute digest in the blockchain is stored based on the following steps: When the current appearance attribute information of any digital human is modified, obtain the values of each attribute parameter in the current appearance attribute information of the any digital human, and construct an attribute list by applying all the attribute parameters and the values of all the attribute parameters in the current appearance attribute information of the any digital human according to the modification time corresponding to the value of each attribute parameter; Calculate the hash value of the attribute list to obtain the attribute digest of the any digital human, and store the attribute digest of the any digital human in the blockchain.

[0091] In some embodiments, the first processing unit 510 is specifically configured to: Calculate the standard deviation of the similarities between the first digital human and multiple second digital humans; Select the maximum similarity from the similarities between the first digital human and multiple second digital humans; Select the maximum distance from the distances between the first digital human and multiple second digital humans; Determine a first target distance based on the ratio between the standard deviation and the maximum similarity, and the maximum distance; Select the minimum distance from the first target distance and a second target distance, and determine the target monitoring range according to the minimum distance; the second target distance is determined according to the interaction environment corresponding to the data interaction request.

[0092] In some embodiments, the calculation steps of the similarities between the first digital human and each second digital human include: Calculate the similarity between the interaction influence attribute of the first digital human and the interaction influence attributes of each second digital human to obtain the similarities between the first digital human and each second digital human; Among them, for the interaction influence attributes of the first digital human and each of the second digital humans, the interaction influence attributes include multiple items among preference data, age, and registration duration. The system provided by the present invention is used to execute the above-mentioned method embodiments. For the specific process and detailed content, please refer to the above embodiments and will not be elaborated here.

[0093] Figure 6 An entity structure diagram of an electronic device is exemplified, as Figure 6 shown. The electronic device may include: a processor 610, a communication interface 620, a memory 630, and a communication bus 640. Among them, the processor 610, the communication interface 620, and the memory 630 communicate with each other through the communication bus 640. The processor 610 can call the logical instructions in the memory 630 to execute an interaction method, and the method includes: obtaining a target monitoring range according to the similarity between the first digital human and each second digital human; the first digital human is the digital human that sends a data interaction request, and the second digital human is the digital human that receives the data interaction request; detecting whether there is a third digital human within the target monitoring range; the third digital human is a digital human other than the first digital human and the second digital human and whose distance from the first digital human is gradually decreasing; when it is detected that there is the third digital human within the target monitoring range, adjusting the received sound intensity of the third digital human according to the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans.

[0094] In addition, when the logical instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc that can store program codes.

[0095] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the interaction method provided by each of the above methods. The method includes: obtaining a target monitoring range according to the similarity between the first digital human and each second digital human; the first digital human is the digital human that sends a data interaction request, and the second digital human is the digital human that receives the data interaction request; detecting whether there is a third digital human within the target monitoring range; the third digital human is a digital human other than the first digital human and the second digital human, and the distance between the third digital human and the first digital human is gradually decreasing; when it is detected that there is a third digital human within the target monitoring range, adjusting the received sound intensity of the third digital human according to the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans.

[0096] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the interaction method provided by each of the above methods. The method includes: obtaining a target monitoring range according to the similarity between the first digital human and each second digital human; the first digital human is the digital human that sends a data interaction request, and the second digital human is the digital human that receives the data interaction request; detecting whether there is a third digital human within the target monitoring range; the third digital human is a digital human other than the first digital human and the second digital human, and the distance between the third digital human and the first digital human is gradually decreasing; when it is detected that there is a third digital human within the target monitoring range, adjusting the received sound intensity of the third digital human according to the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans.

[0097] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0098] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An interaction method, characterized in that, Including: Obtain a target monitoring range according to the similarity between the first digital human and each second digital human; the first digital human is the digital human that sends a data interaction request, and the second digital human is the digital human that receives the data interaction request; Detect whether there is a third digital human within the target monitoring range; The third digital human is a digital human other than the first digital human and the second digital human, and the distance between the third digital human and the first digital human is gradually decreasing; When it is detected that there is the third digital human within the target monitoring range, adjust the received sound intensity of the third digital human according to the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans.

2. The interactive method according to claim 1, wherein The adjusting the received sound intensity of the third digital human according to the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans includes: Generate a first attribute summary of the third digital human according to the current appearance attribute information of the third digital human; the current appearance attribute information includes multiple items such as skin color, hairstyle, clothing, and accessories; Obtain the latest attribute summary of the third digital human from multiple attribute summaries stored in the blockchain as the second attribute summary of the third digital human; When the first attribute summary is the same as the second attribute summary, adjust the received sound intensity of the third digital human according to the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans.

3. The interactive method according to claim 2, wherein The adjusting the received sound intensity of the third digital human according to the similarity between the third digital human and the first digital human, and the similarity between the third digital human and each of the second digital humans includes: Select the minimum similarity among the similarity between the third digital human and the first digital human and the similarity between the third digital human and multiple second digital humans; Select the maximum similarity among the similarity between the first digital human and multiple second digital humans; Adjust the received sound intensity of the third digital human according to the output sound energy of the target digital human, the distance between the third digital human and the target digital human, and the minimum similarity and the maximum similarity; the target digital human is the digital human that currently outputs sound among the first digital human and multiple second digital humans.

4. The interactive method according to claim 3, wherein The adjusting the received sound intensity of the third digital human according to the output sound energy of the target digital human, the distance between the third digital human and the target digital human, and the minimum similarity and the maximum similarity includes: Calculate a target area according to the distance between the third digital human and the target digital human; Determine the target sound intensity according to the ratio between the output sound energy and the target area, and the ratio between the minimum similarity and the maximum similarity. Select the maximum sound intensity from the target sound intensity and the preset sound intensity, and adjust the received sound intensity of the third digital human according to the maximum sound intensity.

5. The interactive method according to claim 2, wherein The attribute digest in the blockchain is stored based on the following steps: When the current appearance attribute information of any digital human is modified, obtain the values of the attribute parameters in the current appearance attribute information of the any digital human, and construct an attribute list by applying all the attribute parameters and the values of all the attribute parameters in the current appearance attribute information of the any digital human according to the modification time corresponding to the values of the attribute parameters; Calculate the hash value of the attribute list to obtain the attribute digest of the any digital human, and store the attribute digest of the any digital human in the blockchain.

6. The interactive method according to any one of claims 1-5, characterized in that The obtaining of the target monitoring range according to the similarity between the first digital human and each second digital human includes: Calculate the standard deviation of the similarity between the first digital human and multiple second digital humans; Select the maximum similarity from the similarities between the first digital human and multiple second digital humans; Select the maximum distance from the distances between the first digital human and multiple second digital humans; Determine the first target distance according to the ratio between the standard deviation and the maximum similarity and the maximum distance; Select the minimum distance from the first target distance and the second target distance, and determine the target monitoring range according to the minimum distance; the second target distance is determined according to the interaction environment corresponding to the data interaction request.

7. The interactive method according to any one of claims 1-5, characterized in that, The calculation steps of the similarity between the first digital human and each second digital human include: Calculate the similarity between the interaction influence attribute of the first digital human and the interaction influence attributes of each second digital human to obtain the similarity between the first digital human and each second digital human; Among them, for the interaction influence attribute of each digital human among the first digital human and each second digital human, the interaction influence attribute includes multiple items such as preference data, age, and registration duration.

8. An interactive system, characterized in that, Include: A first processing unit for obtaining a target monitoring range according to the similarity between the first digital human and each second digital human; The first digital human is the digital human that sends the data interaction request, and the second digital human is the digital human that receives the data interaction request; A second processing unit for detecting whether there is a third digital human within the target monitoring range; The third digital human is a digital human other than the first digital human and the second digital human and whose distance from the first digital human is gradually decreasing; An interaction unit for, when detecting that there is a third digital human within the target monitoring range, adjusting the received sound intensity of the third digital human according to the current appearance attribute information of the third digital human, the similarity between the third digital human and the first digital human, and the similarities between the third digital human and each second digital human.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the interaction method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the interaction method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the interaction method according to any one of claims 1 to 7.

Images