Cultural relic content information processing method and device, electronic equipment and storage medium

Abstract

The invention discloses a cultural relic content information processing method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the spatial-temporal feature extraction of a current cultural relic spatial-temporal diagram of a target user, and obtaining a node feature vector of each current target cultural relic content; for each target cultural relic content, combining the node feature vector of the current target cultural relic content with the real-time behavior feature vector of the target user to obtain a real-time feature vector corresponding to the target cultural relic content, and performing weighted fusion on the real-time feature vector and the feature vector of the cultural relic corresponding to the target cultural relic content in the cultural relic knowledge map to obtain a real-time feature vector of the target cultural relic content; obtaining an initial recommendation content feature corresponding to the target cultural relic content; combining the initial recommended content feature with a context feature of the currently browsed content in the cultural relic knowledge graph to obtain a final recommended content feature corresponding to the target cultural relic content; and based on the final recommended content features corresponding to the target cultural relic content, matching multi-modal current recommended cultural relic content and pushing the multi-modal current recommended cultural relic content.

Description

Technical Field

[0001] The present application relates to the technical field of content recommendation, and in particular to a method and device for processing cultural relics content information, an electronic device, and a storage medium. Background Art

[0002] Currently, in order to provide each user with content that meets their needs or preferences, many applications or web pages will recommend personalized content to each user. Therefore, in the digital human live broadcast platform, there is also a need for personalized content recommendation for cultural relics web pages.

[0003] Currently, personalized recommendations are mainly based on the user's recent historical data, through collaborative filtering and deep learning methods, to analyze the content that the user is interested in. Then, other content similar to the analyzed content of interest will be recommended to the user in the current and future period to meet the user's needs.

[0004] However, in the analysis process of the existing methods, the static behavior of users is captured, and there is a lack of analysis of spatiotemporal characteristics, that is, the changes of user behavior over time and space, such as the changes from weekdays to weekends, the changes from text content to image content, and other dynamic data. Therefore, the accuracy of the final analysis result is insufficient. In addition, although the existing methods will analyze the most recent historical data as much as possible to reduce the lag, there is still a certain lag because it cannot be adjusted in time according to the current situation, which will also affect the accuracy of the results. Moreover, the existing methods only recommend similar content, so the recommended content is concentrated in a single mode. Since it fails to fully consider the content connection between cultural relics, the depth of the recommended content is limited, so the richness of the recommended content is ineffective and fails to meet the diverse needs of users. Summary of the invention

[0005] Based on the above-mentioned deficiencies of the prior art, the present application provides a method and device for processing cultural relics content information, an electronic device, and a storage medium to solve the problem that the prior art cannot achieve accurate recommendations and the depth of recommended content is limited.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] The first aspect of the present application provides a method for processing cultural relics content information, comprising:

[0008] Extracting spatiotemporal features from the target user's current spatiotemporal graph of cultural relics to obtain node feature vectors of each current target cultural relic content; wherein the current spatiotemporal graph of cultural relics records the latest historical behavior data of the target user on each target cultural relic content and the attributes of each target cultural relic content;

[0009] For each target cultural relic content, the node feature vector of the current target cultural relic content is combined with the real-time behavior feature vector of the target user to obtain a real-time feature vector corresponding to the target cultural relic content;

[0010] Performing weighted fusion on the real-time feature vector corresponding to the target cultural relic content and the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-constructed cultural relic knowledge graph to obtain the initial recommended content feature corresponding to the target cultural relic content;

[0011] Combining the initial recommended content features corresponding to the target cultural relic content with the context features of the currently browsed content in the cultural relic knowledge graph to obtain the final recommended content features corresponding to the target cultural relic content;

[0012] Based on the final recommended content features corresponding to the target cultural relic content, multimodal current recommended cultural relic content is matched and pushed to the target user.

[0013] Optionally, in the above-mentioned cultural relic content information processing method, before extracting spatiotemporal features from the target user's current spatiotemporal cultural relic graph to obtain node feature vectors of each current target cultural relic content, the method further includes:

[0014] Obtain the latest historical behavior data of the target user;

[0015] For the target cultural relic content that generates the behavior recorded in the historical behavior data of the target user, creating a node corresponding to the target cultural relic content based on the attributes of the target cultural relic content;

[0016] Initializing a node feature vector of the target cultural relic content according to the attributes of the target cultural relic content;

[0017] According to the behavior sequence in the historical behavior data of the target user, the nodes corresponding to the target cultural relic contents are connected, and the behavior time is recorded on the connected edges to obtain the current cultural relic spatiotemporal graph.

[0018] Optionally, in the above-mentioned cultural relic content information processing method, the extraction of spatiotemporal features of the target user's current spatiotemporal cultural relic graph to obtain node feature vectors of each current target cultural relic content includes:

[0019] For each target cultural relic content, determine each neighbor node of the target cultural relic content in the current cultural relic spatiotemporal graph;

[0020] Calculating the normalization coefficients of the target cultural relic content and each of the neighboring nodes;

[0021] Determining a current weight matrix corresponding to the target cultural relic content;

[0022] Based on the normalization coefficients of the target cultural relic content and each of the neighboring nodes, the node feature vector of the target cultural relic content, and the current weight matrix corresponding to the target cultural relic content, a current weighted sum of the target cultural relic content is obtained;

[0023] The latest node feature vector of the current target cultural relic content is obtained by calculating the current weight of the target cultural relic content, the preset bias term and the preset activation function.

[0024] Optionally, in the above-mentioned cultural relic content information processing method, for each of the target cultural relic contents, combining the node feature vector of the current target cultural relic content with the real-time behavior feature vector of the target user to obtain the real-time feature vector corresponding to the target cultural relic content includes:

[0025] Generating a real-time behavior feature vector of the target user based on the real-time behavior data of the target user;

[0026] For each target cultural relic content, a real-time feature vector corresponding to the target cultural relic content is obtained through the node feature vector of the current target cultural relic content and the real-time behavior feature vector of the target user.

[0027] Optionally, in the above cultural relics content information processing method, it also includes:

[0028] Define each cultural relic and each cultural relic category as an entity in the knowledge graph, and add detailed information for each of the entities;

[0029] The entities of each of the cultural relics are connected with the entities of the cultural relic category to which they belong, and with the entities of other cultural relics belonging to the same cultural relic category, to obtain a cultural relic knowledge graph.

[0030] Optionally, in the above-mentioned cultural relic content information processing method, the real-time feature vector corresponding to the target cultural relic content is weightedly fused with the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-constructed cultural relic knowledge graph to obtain the initial recommended content feature corresponding to the target cultural relic content, including:

[0031] The real-time feature vector corresponding to the target cultural relic content and the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-constructed cultural relic knowledge graph are weightedly calculated according to the fusion weight to obtain the initial recommended content features corresponding to the target cultural relic content.

[0032] Optionally, in the above-mentioned cultural relic content information processing method, the combining of the initial recommended content features corresponding to the target cultural relic content with the context features of the currently browsed content in the cultural relic knowledge graph to obtain the final recommended content features corresponding to the target cultural relic content includes:

[0033] The initial recommended content features corresponding to the target cultural relic content and the context features of the currently browsed content in the cultural relic knowledge graph are weighted according to the context weight to obtain the final recommended content features corresponding to the target cultural relic content; wherein the context weight is determined according to the type of the currently browsed content and / or the key information in the currently browsed content.

[0034] A second aspect of the present application provides a cultural relic content information processing device, comprising:

[0035] A node feature updating unit is used to extract the spatiotemporal features of the current spatiotemporal graph of cultural relics of the target user to obtain the node feature vectors of each current target cultural relic content; wherein the current spatiotemporal graph of cultural relics records the latest historical behavior data of the target user on each target cultural relic content and the attributes of each target cultural relic content;

[0036] A behavior feature combining unit is used to combine the node feature vector of the current target cultural relic content with the real-time behavior feature vector of the target user for each target cultural relic content, so as to obtain a real-time feature vector corresponding to the target cultural relic content;

[0037] A cultural relic feature fusion unit, used to perform weighted fusion on the real-time feature vector corresponding to the target cultural relic content and the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-constructed cultural relic knowledge graph, to obtain the initial recommended content feature corresponding to the target cultural relic content;

[0038] A context feature combining unit, used to combine the initial recommended content features corresponding to the target cultural relic content with the context features of the currently browsed content in the cultural relic knowledge graph to obtain the final recommended content features corresponding to the target cultural relic content;

[0039] The recommendation unit is used to match the multimodal current recommended cultural relic content based on the final recommended content features corresponding to the target cultural relic content and push it to the target user.

[0040] Optionally, in the above-mentioned cultural relics content information processing device, it also includes:

[0041] A data acquisition unit, used to acquire the latest historical behavior data of the target user;

[0042] A node creation unit, configured to create a node corresponding to the target cultural relic content based on the attributes of the target cultural relic content for the target cultural relic content that generates the behavior recorded in the historical behavior data of the target user;

[0043] A vector initialization unit, used to initialize the node feature vector of the target cultural relic content according to the attribute of the target cultural relic content;

[0044] The node connection unit is used to connect the nodes corresponding to the target cultural relic contents according to the behavior sequence in the historical behavior data of the target user, and record the behavior time on the connected edges to obtain the current cultural relic spatiotemporal graph.

[0045] Optionally, in the above-mentioned cultural relic content information processing device, the node feature updating unit includes:

[0046] A neighbor node determination unit, used to determine each neighbor node of the target cultural relic content in the current cultural relic spatiotemporal graph for each target cultural relic content;

[0047] A coefficient calculation unit, used to calculate the normalization coefficients of the target cultural relic content and each of the neighboring nodes;

[0048] A weight determination unit, used to determine a current weight matrix corresponding to the target cultural relic content;

[0049] An accumulation unit, configured to obtain a current weighted sum of the target cultural relic content based on the normalization coefficients of the target cultural relic content and each of the neighboring nodes, the node feature vector of the target cultural relic content, and the current weight matrix corresponding to the target cultural relic content;

[0050] The updating unit is used to calculate the latest node feature vector of the current target cultural relic content through the current weighting, preset bias term and preset activation function of the target cultural relic content.

[0051] Optionally, in the above-mentioned cultural relic content information processing device, the behavior feature combining unit includes:

[0052] A behavior feature generating unit, configured to generate a real-time behavior feature vector of the target user based on the real-time behavior data of the target user;

[0053] The node feature weighting unit is used to obtain the real-time feature vector corresponding to each target cultural relic content through the node feature vector of the current target cultural relic content and the real-time behavior feature vector of the target user.

[0054] Optionally, in the above-mentioned cultural relics content information processing device, it also includes:

[0055] An entity creation unit, used to define each cultural relic and each cultural relic category as an entity in the knowledge graph, and add detailed information of each of the entities;

[0056] The entity connection unit is used to connect the entity of each cultural relic with the entity of the cultural relic category to which it belongs, and with the entities of other cultural relics belonging to the same cultural relic category, so as to obtain a cultural relic knowledge graph.

[0057] Optionally, in the above-mentioned cultural relic content information processing device, the cultural relic feature fusion unit includes:

[0058] The cultural relic feature weighting unit performs weighted calculation according to the fusion weight on the real-time feature vector corresponding to the target cultural relic content and the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-constructed cultural relic knowledge graph to obtain the initial recommended content feature corresponding to the target cultural relic content.

[0059] Optionally, in the above-mentioned cultural relic content information processing device, the context feature combining unit includes:

[0060] The context feature combining subunit is used to weight the initial recommended content features corresponding to the target cultural relic content and the context features of the currently browsed content in the cultural relic knowledge graph according to the context weight to obtain the final recommended content features corresponding to the target cultural relic content; wherein the context weight is determined according to the type of the currently browsed content and / or the key information in the currently browsed content.

[0061] A third aspect of the present application provides an electronic device, including:

[0062] Memory and processor;

[0063] Wherein, the memory is used to store programs;

[0064] The processor is used to execute the program, and when the program is executed, it is specifically used to implement the cultural relics content information processing method as described in any one of the above.

[0065] A fourth aspect of the present application provides a computer storage medium for storing a computer program, which, when executed by a processor, is used to implement a method for processing cultural relics content information as described in any one of the above.

[0066] The embodiment of the present application provides a method for processing cultural relics content information, constructs a cultural relics spatiotemporal graph, records the latest target user's historical behavior data on each target cultural relics content and the attributes of each target cultural relics content. Then, the current cultural relics spatiotemporal graph of the target user is subjected to spatiotemporal feature extraction to obtain the node feature vectors of each current target cultural relics content, thereby extracting relevant features from the time dimension and the space dimension, and obtaining a more accurate reflection of the change of user interest over time and space, thereby improving the accuracy of the recommended content. For each target cultural relics content, the node feature vector of the current target cultural relics content is combined with the real-time behavior feature vector of the target user to obtain the real-time feature vector corresponding to the target cultural relics content, thereby fully considering the user's current behavior, so as to ensure that the obtained features reflect the user's current interests, thereby further improving the accuracy of the recommended content. Next, the real-time feature vector corresponding to the target cultural relics content is weightedly fused with the feature vector of the cultural relics corresponding to the target cultural relics content in the pre-constructed cultural relics knowledge graph, and the initial recommended content features corresponding to the target cultural relics content are obtained, thereby enriching the recommended content and increasing the depth of the recommended content by combining the features of the cultural relics in the knowledge graph. Then, the initial recommended content features corresponding to the target cultural relic content are combined with the context features of the current browsing content in the cultural relic knowledge graph to obtain the final recommended content features corresponding to the target cultural relic content, so that the provided content is consistent with the current browsing interest and the accuracy of the recommended content is improved. Finally, based on the final recommended content features corresponding to the target cultural relic content, the multimodal current recommended cultural relic content is matched and pushed to the target user, thus realizing a method for accurately providing multimodal content. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0068] Figure 1 A flowchart of a method for processing cultural relics content information provided in an embodiment of the present application;

[0069] Figure 2 A flowchart of a method for constructing a current cultural relic space-time map provided in an embodiment of the present application;

[0070] Figure 3 A flowchart of a method for updating a node feature vector provided in an embodiment of the present application;

[0071] Figure 4A schematic diagram of the architecture of a cultural relic content information processing device provided in an embodiment of the present application;

[0072] Figure 5 A schematic diagram of the architecture of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0073] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0074] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0075] The present application embodiment provides a method for processing cultural relics content information, such as Figure 1 As shown, the specific steps include:

[0076] S101, extracting spatiotemporal features from the current spatiotemporal graph of cultural relics of the target user to obtain node feature vectors of the current contents of each target cultural relic.

[0077] Among them, the current cultural relic space-time graph records the latest historical behavior data of the target user on each target cultural relic content and the attributes of each target cultural relic content. That is, the cultural relic space-time graph records the target cultural relic content on which the target user has recently implemented behavior, the type and time of the implemented behavior, and the order of behavior changes between each target cultural relic content, so as to reflect the relationship between the target user's behavior on the cultural relic content and the time dimension, and reflect the relationship between the cultural relic contents in the spatial dimension. For example, it records that the user browsed cultural relic A at time t1, and then jumped from browsing cultural relic content A to browsing cultural relic content B at time t2.

[0078] In order to analyze the target user's recent activities, the current cultural relic space-time map must at least record the latest historical behavior data of the target user on each target cultural relic content and the attributes of each target cultural relic content. Therefore, the cultural relic space-time map needs to be continuously updated according to the user's behavior data. It can be updated in real time or at a fixed time. When updating, new data is usually constructed in the original cultural relic space-time map, and of course, a new cultural relic space-time map can be reconstructed using the data.

[0079] Optionally, another embodiment of the present application provides a method for constructing a current cultural relic time-space graph, such as Figure 2 As shown, including:

[0080] S201. Obtain the latest historical behavior data of the target user.

[0081] Among them, historical behavior data records the user's behavior on cultural relics content at various times, including data on user browsing, clicking and other interactive behaviors. For example, a user browsed the text description of Song Dynasty celadon in the morning and watched a video about Song Dynasty celadon in the afternoon.

[0082] S202 . For the target cultural relic content that generates the behavior recorded in the historical behavior data of the target user, create a node corresponding to the target cultural relic content based on the attributes of the target cultural relic content.

[0083] Among them, the attributes of the target cultural relic content are the attributes of the corresponding cultural relics, such as name, age, material, discovery location, etc. Therefore, in the embodiment of the present application, the text description, pictures, videos, interactive elements and other contents of the cultural relics are defined as nodes in the cultural relic space-time graph, and the attributes of the corresponding cultural relics are used as the attributes of the nodes. Node 1 represents a text description page of Song Dynasty celadon, and the attributes include: age = Song Dynasty, material = celadon, discovery location = Zhejiang. Node 2 represents a picture of Song Dynasty celadon, and the attributes include age = Song Dynasty, material = celadon, discovery location = Zhejiang.

[0084] S203: Initialize the node feature vector of the target cultural relic content according to the attributes of the target cultural relic content.

[0085] It should be noted that for the initially created nodes, since their features have not yet been extracted, they are not yet related to the user's behavior. Therefore, their attributes are initially used as the feature vectors of their corresponding nodes to facilitate subsequent updating of the feature vectors of the nodes on this basis.

[0086] S204, connecting the nodes corresponding to the target cultural relics content according to the behavior sequence in the historical behavior data of the target user, and recording the behavior time on the connected edges to obtain the current cultural relics spatiotemporal graph.

[0087] Specifically, in the embodiment of the present application, the century marks the interaction relationship between users of different cultural relics, including clicks, browsing time, scrolling behavior, etc. Moreover, the edge can further represent the association relationship between cultural relics, such as "belonging to the same dynasty" and "appearing in the same place".

[0088] In addition, in order to record the time when each behavior occurred, the behavior time is recorded on the edge. Therefore, each node can be connected to other nodes through edges to form a user behavior path. The relationship between the edge and the time dimension is: each edge has a timestamp, which records the time when the user jumps from one node to another. The relationship between the node and the time dimension is: the feature vector of each node can be updated over time.

[0089] After the current cultural relic space-time graph is updated, the node feature vector of the target cultural relic content is continuously updated by analyzing the current cultural relic space-time graph accordingly, so that the user's current interest can be reflected through the node feature vector of the target cultural relic content.

[0090] Specifically, in order to capture the temporal and spatial characteristics of user behavior, in the embodiment of the present application, a spatiotemporal convolutional layer is used to capture the temporal dependency and spatial dependency of user behavior.

[0091] Among them, time dependence refers to the change in users' interest in different types of cultural relics content at different times. For example, users pay more attention to academic research content during the day on weekdays, and pay more attention to entertainment and interactive content on weekend nights. For example, a user browsed the text description of Song Dynasty celadon at 10:00 am and watched a video of Song Dynasty celadon at 5:00 pm, indicating that users' interest in different types of content changes at different times.

[0092] Spatial dependency refers to the interaction between users browsing different cultural relics. For example, after viewing the text description of a cultural relic, a user may click on related pictures or videos. For example, after viewing the text description of Song Dynasty celadon, a user clicks on several pictures of Song Dynasty celadon, and then watches a video about the production process of Song Dynasty celadon.

[0093] Optionally, in another embodiment of the present application, a specific implementation of step S101 is as follows: Figure 3 As shown, including:

[0094] S301 . For each target cultural relic content, determine each neighbor node of the target cultural relic content in the current cultural relic space-time graph.

[0095] Among them, the neighbor nodes of the target cultural relic content refer to other nodes directly connected to the node of the target cultural relic content, which reflects the situation where users flow from other nodes to the node of the target cultural relic content, or from the node of the target cultural relic content, from the node of the target cultural relic content to other nodes.

[0096] S302: Calculate the normalization coefficients of the target cultural relic content and each neighboring node.

[0097] In order to balance the contributions of different nodes and prevent some nodes from having too much influence on the results due to too many neighbors, the contribution of nodes is limited by calculating the normalization coefficient.

[0098] Specifically, for the node i of the target cultural relic content and a neighbor node j, that is, for each pair of nodes (i, j), the normalization coefficient is calculated as:

[0099]

[0100] Wherein, N(i) is the set of neighbor nodes of node i of the target cultural relic content, and N(j) is the set of neighbor nodes of a neighbor node j of the target cultural relic content node.

[0101] S303: Determine the current weight matrix corresponding to the target cultural relic content.

[0102] In order to consider the influence of different target cultural relic contents on the user's interest, it is necessary to determine the current weight matrix corresponding to the target cultural relic content. Optionally, the current weight matrix corresponding to the target cultural relic content is usually randomly initialized or obtained through a pre-trained model. The learning of the weight matrix can be optimized by a back propagation algorithm.

[0103] S304 , obtaining a current weighted sum of the target cultural relic content based on the normalization coefficients of the target cultural relic content and each neighboring node, the node feature vector of the target cultural relic content, and the current weight matrix corresponding to the target cultural relic content.

[0104] Specifically, the node feature vector of the current target cultural relic content is multiplied by the normalization coefficient of the target cultural relic content and each neighboring node and the corresponding current weight matrix W (l) , and then accumulate to obtain the current weighted sum of the target cultural relic content. Specifically, it can be expressed as:

[0105]

[0106] in, It is the node feature vector of the current target cultural relic content.

[0107] S305 , calculating through the current weighting of the target cultural relic content, the preset bias term and the preset activation function to obtain the latest node feature vector of the current target cultural relic content.

[0108] Specifically, the current weighted sum of the target cultural relic content is added with the preset bias term b (l) , we can get:

[0109]

[0110] Finally, by applying the preset activation function σ, we can get the new node feature vector of the current target cultural relic content:

[0111]

[0112] Optionally, feature extraction can be performed through a spatiotemporal convolutional network. Specifically, when the current spatiotemporal map of the target user is processed through the convolutional layer of the spatiotemporal convolutional network, the above processing process is realized. In addition, the spatiotemporal convolutional network may include multiple convolutional layers, that is, the above-mentioned process can be repeatedly performed through multiple convolutional layers.

[0113] Therefore, after the spatiotemporal graph convolution layer captures the temporal and spatial dependencies of user behavior, the updated feature vector adds the temporal and spatial information of the user's recent behavior compared to the original feature vector, and can more accurately reflect the user's interest changes. For example, if a user has browsed the text description page of Song Dynasty celadon many times in the past week and watched a teaching video a few days ago, then through spatiotemporal feature extraction, the system will generate a comprehensive feature vector, that is, the updated feature vector, which reflects the user's long-term interest in Song Dynasty celadon.

[0114] S102 . For each target cultural relic content, combine the node feature vector of the current target cultural relic content with the real-time behavior feature vector of the target user to obtain a real-time feature vector corresponding to the target cultural relic content.

[0115] Although the node feature vector of the current target cultural relic content is obtained based on recent data analysis, it is still based on historical behavior data. Therefore, in order to analyze the user's interests in real time based on the user's current behavior, it can more accurately reflect the current user's interests and make the final recommendation results more accurate. Therefore, the user's latest behavior data is captured in real time, and its corresponding feature vector is combined with the node feature vector of the current target cultural relic content, and the feature vector is adjusted in real time to ensure that the recommended content based on the adjusted feature vector is closer to the user's current interests.

[0116] Optionally, in another embodiment of the present application, a specific implementation of step S102 includes:

[0117] A real-time behavior feature vector of the target user is generated based on the real-time behavior data of the target user, and then for each target cultural relic content, the real-time feature vector corresponding to the target cultural relic content is obtained through the node feature vector of the current target cultural relic content and the real-time behavior feature vector of the target user.

[0118] Specifically, a real-time behavior feature vector of the target user is generated based on the real-time behavior data of the target user, and then for each target cultural relic content, the difference between the node feature vector of the current target cultural relic content and the real-time behavior feature vector of the target user is multiplied by the learning rate, and the resulting product is added to the node feature vector of the current target cultural relic content to obtain the real-time feature vector corresponding to the target cultural relic content.

[0119] So specifically, when the target user has a new behavior, the system immediately updates the corresponding node feature vector in the following way to obtain the real-time feature vector corresponding to the target cultural relic content:

[0120]

[0121] in, represents the real-time feature vector corresponding to the target cultural relic content, that is, the updated node feature vector finally obtained. r is the real-time behavior feature vector of the target user generated based on the real-time behavior data. η is the learning rate, which controls the speed of the update.

[0122] And "x r -h i "This operation is actually calculating the feature vector x of the behavior data r and the existing feature vector h i This difference can be understood as a change in user interest or a transfer vector from the current state to the new state. In other words, the result of this operation is the incremental information brought by real-time behavior. r -h i ) represents the degree to which the existing feature vector is adjusted according to the user's latest behavior data, and the learning rate η determines the extent to which the new observation x is trusted. r , and adjust the existing feature vector accordingly, multiplying this difference by the learning rate η and adding it to the original feature vector h i We get the updated feature vector , which represents a state that is closer to the user’s current interests after combining the latest user behavior.

[0123] Because the feature vector h generated by spatiotemporal feature extraction iIt is based on the user's historical behavior data and reflects the user's comprehensive interests over a period of time. The subsequent dynamic feature update is to capture the user's latest behavior and ensure that the recommended content is closer to the user's current interests. That is, the final feature vector is generated by combining the user's real-time behavior data. . So the two complement each other, allowing the recommendation system to more intelligently understand the user's behavior patterns and interest changes, and provide more accurate and personalized recommendations. In short, dynamic feature updates are to ensure the immediacy and relevance of the recommendation system, further improve the user experience, and adapt to various changes in user interests.

[0124] For example, in the scenario where the original recommendation is completely retained: the user has mainly browsed content about Song Dynasty celadon in the past month, including text descriptions, pictures, and videos. In recent days, the user's behavior has not changed significantly, and he continues to pay attention to Song Dynasty celadon. Therefore, the user's initial interest feature vector h i Indicates a high level of interest in Song Dynasty celadon. The system generates a new real-time feature vector x based on the user's latest behavior r , capturing the user's continued interest in Song Dynasty celadon. Calculate x r and the existing feature vector h i The system takes into account the small differences between the two and updates them with a moderate learning rate η. Therefore, when recommending results, the system continues to recommend content related to Song Dynasty celadon, such as the latest discovered celadon objects, expert interpretation articles, etc., to ensure that the recommended content is highly consistent with the user's current interests.

[0125] For the scenario of completely switching to new recommendations: the user has mainly browsed various contents about Song Dynasty celadon in the past month, including text descriptions, pictures, and videos. However, in recent days, the user's behavior has changed significantly. He has become very interested in Tang Dynasty pottery figurines and has viewed several articles about Tang Dynasty pottery figurines, watched related archaeological excavation videos, and even participated in an online discussion forum. Therefore, the user's initial interest feature vector h i This reflects the high level of interest in Song Dynasty celadon. The system generates a new real-time feature vector x based on the user's latest behavior. r , capturing the user's new interest in Tang Dynasty pottery figurines. Calculate x r and the existing feature vector h i The system uses a higher learning rate η to update the recommended content to quickly adapt to changes in user interests. Therefore, when recommending results, the system quickly adjusts the recommended content to focus more on Tang Dynasty pottery figurines and related materials, reflecting the significant change in user interests. This approach ensures that the recommended content is close to the user's immediate interests and provides a more personalized and timely experience.

[0126] For the scenario of gradual interest change between the above two situations: the user has mainly browsed content about Song Dynasty celadon in the past month, including text descriptions, pictures and videos. In recent days, the user has begun to show interest in Song Dynasty Ru kiln porcelain, viewed several related articles and watched high-definition pictures and videos. Although the interest has expanded, it is still concentrated in the field of Song Dynasty porcelain. Therefore, the user's initial interest feature vector h i This reflects the high level of interest in Song Dynasty celadon. The system generates a new real-time feature vector x based on the user's latest behavior. r , capturing the user's new interest in Song Dynasty Ru Kiln porcelain. Calculate x r and the existing feature vector h i The medium difference between them is used, and the moderate learning rate η is used for updating. Therefore, when recommending results, the system gradually introduces information about Song Dynasty Ru Kiln porcelain while continuing to recommend content related to Song Dynasty celadon. This method not only retains the recommended content that users are familiar with, but also gradually explores new points of interest for users, ensuring that the recommended content is both continuous and fresh.

[0127] S103, weighted fusion is performed on the real-time feature vector corresponding to the target cultural relic content and the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-constructed cultural relic knowledge graph to obtain the initial recommended content features corresponding to the target cultural relic content.

[0128] By analyzing the real-time feature vector corresponding to the target cultural relic content, the cultural relic content that the user is interested in can be accurately reflected, and in order to accurately recommend and enrich the recommended content based on the inherent connection of cultural relics. Therefore, in the embodiment of the present application, a knowledge graph of the full amount of cultural relics is pre-constructed. The detailed information of each cultural relic and the relationship between each cultural relic are recorded in the knowledge graph. Therefore, the feature vectors of each cultural relic designed with the target cultural relic content in the cultural relic knowledge graph are weighted and fused. Among them, the feature vector of the cultural relic can be generated according to the information recorded in the knowledge graph. Specifically, the feature vector of the cultural relic corresponding to the target cultural relic content can be combined with the real-time feature vector corresponding to the target cultural relic content according to a certain ratio. Therefore, this process is not only limited to the user's current interest point, but can also be extended to related documents, videos and other background information, thereby improving the depth and breadth of the recommended content.

[0129] Optionally, in another embodiment of the present application, a method for constructing a cultural relics knowledge graph includes:

[0130] Each cultural relic and each cultural relic category is defined as an entity in the knowledge graph, and detailed information of each entity is added. The entity of each cultural relic is connected with the entity of the cultural relic category to which it belongs, and with the entities of other cultural relics belonging to the same cultural relic category, to obtain a cultural relic knowledge graph.

[0131] Among them, the category of cultural relics can specifically include dynasties, cultural backgrounds, relevant documents, etc., so in the embodiment of the present application, cultural relics, dynasties, cultural backgrounds, relevant documents, etc. are defined as entities of the cultural relics knowledge map, so the feature vector of the cultural relics corresponding to the target cultural relics content is not only generated using the information of the cultural relics involved in the target cultural relics content, but also using the information of the entities such as dynasties, cultural backgrounds, and relevant documents related to the cultural relics. Therefore, it is also possible to enrich the recommended content based on dynasties, cultural backgrounds, and relevant documents. In addition, detailed attribute information is added, such as age, material, discovery location, historical background, etc. Then the associated entities are connected, that is, the relationship between the entities is defined, such as "belonging to the same dynasty", "citing the same document", and "appearing in the same place".

[0132] In this way, the cultural relics knowledge graph can reveal the complex semantic relationships between cultural relics and help users understand the stories and meanings behind them. This deep connection is based on detailed research and expertise, rather than simply relying on user behavior data. Moreover, compared with the cultural relics spatiotemporal graph, the content of the cultural relics knowledge graph is more stable because it is based on the inherent attributes and historical facts of the cultural relics themselves, rather than instantaneous changes in user behavior. Therefore, it can serve as a solid foundation for the recommendation system, maintaining a certain degree of coherence even if user interests change significantly.

[0133] Among them, the data of the cultural relics knowledge graph can be derived from professional archaeological materials, historical documents and other authoritative resources, emphasizing the accuracy and depth of knowledge. The data of the cultural relics space-time graph comes from the user's historical behavior log and real-time interaction records, emphasizing the immediacy and dynamism of user behavior. The cultural relics knowledge graph focuses on the inherent attributes and complex semantic relationships of the cultural relics themselves, providing deep background information and support, so it is mainly used to enrich the recommended content, increase the depth and breadth of the recommendation, and support long-term and stable content recommendation. The cultural relics space-time graph focuses on user behavior patterns and temporal and spatial dependencies, captures users' immediate interests and behavioral changes, and is mainly used to generate user interest vectors, achieve accurate personalized recommendations, and dynamically adjust according to user behavior. Therefore, although both the cultural relics knowledge graph and the cultural relics space-time graph involve cultural relics and their attributes, their roles and functions are complementary, and together they constitute a complete personalized recommendation system. The cultural relics knowledge graph provides a solid knowledge foundation, while the cultural relics space-time graph enhances the flexibility and response speed of the system.

[0134] Optionally, in another embodiment of the present application, a specific implementation of step S103 includes:

[0135] The real-time feature vector corresponding to the target cultural relic content is weightedly calculated with the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-built cultural relic knowledge graph according to the fusion weight to obtain the initial recommended content features corresponding to the target cultural relic content.

[0136] So specifically, the initial recommended content features corresponding to the target cultural relic content can be expressed as:

[0137]

[0138] Among them, k i is the feature vector of the cultural relic corresponding to the target cultural relic content in the cultural relic knowledge graph. α is the fusion weight.

[0139] Through the fused features, more abundant content can be recommended to users, and multi-model recommendations can be realized. For example, if a user is interested in Song Dynasty celadon, the system will generate fused recommended content features based on the user's interest vector, that is, the real-time feature vector corresponding to the target cultural relic content and the related entities (Song Dynasty celadon) in the cultural relic knowledge graph.

[0140] S104: Combine the initial recommended content features corresponding to the target cultural relic content with the context features of the currently browsed content in the cultural relic knowledge graph to obtain the final recommended content features corresponding to the target cultural relic content.

[0141] In order to further improve the accuracy of the recommendation, in the embodiment of the present application, not only the current behavior of the target user is considered, but also the content currently browsed by the target user needs to be considered. Therefore, in the present application, the features of the context of the currently browsed content are integrated into the features, such as the features of the related documents and videos of the currently browsed content, so that the content recommended based on the features is closer to the current user's interests. For example, if the user is viewing pictures of Song Dynasty celadon, the system can recommend related documents and video materials, such as research papers on Song Dynasty celadon and teaching videos on the production process.

[0142] Optionally, in another embodiment of the present application, a specific implementation of step S104 includes:

[0143] The initial recommended content features corresponding to the target cultural relic content and the context features of the current browsing content in the cultural relic knowledge graph are weighted according to the context weight to obtain the final recommended content features corresponding to the target cultural relic content.

[0144] Therefore, the specific calculation method of the final recommended content features corresponding to the target cultural relic content is:

[0145]

[0146] Among them, c iis the context feature of the current browsing content. β is the context weight, which is determined according to the type of the current browsing content and / or the key information in the current browsing content. For example, if the user is currently browsing a picture of a cultural relic, then research papers on the cultural relic and teaching videos on the production process may be given a higher weight. It can also be matched based on the details of the current browsing content. For example, if the user is viewing the discovery site information of Song Dynasty celadon, then archaeological reports or field investigation videos about the site may be given a higher weight.

[0147] S105 . Based on the final recommended content features corresponding to the target cultural relic content, match the multimodal current recommended cultural relic content and push it to the target user.

[0148] Since the final recommended content features corresponding to the target cultural relic content not only take into account the user's recent behavior and related cultural relics, but also take into account the current behavior and the context of the current behavior, based on the final recommended content features corresponding to the target cultural relic content, multimodal cultural relic content that meets the user's current interests can be accurately matched and recommended to the user.

[0149] Optionally, the similarity between the features of each cultural relic content and the final recommended content may be calculated to match the content that meets the current interests of the target user, and then based on the richness of the content, a certain amount of content recommendations of different modalities may be screened from the matched content as the current recommended cultural relic content and recommended to the target user.

[0150] Another embodiment of the present application provides a device for processing cultural relics content information, such as Figure 4 As shown, including:

[0151] The node feature updating unit 401 is used to extract the spatiotemporal features of the current spatiotemporal graph of cultural relics of the target user, and obtain the node feature vectors of the current contents of each target cultural relic.

[0152] The current cultural relic space-time graph records the latest historical behavior data of the target user on each target cultural relic content and the attributes of each target cultural relic content.

[0153] The behavior feature combining unit 402 is used to combine the node feature vector of the current target cultural relic content with the real-time behavior feature vector of the target user for each target cultural relic content, to obtain a real-time feature vector corresponding to the target cultural relic content.

[0154] The cultural relic feature fusion unit 403 is used to perform weighted fusion on the real-time feature vector corresponding to the target cultural relic content and the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-constructed cultural relic knowledge graph to obtain the initial recommended content feature corresponding to the target cultural relic content.

[0155] The context feature combining unit 404 is used to combine the initial recommended content features corresponding to the target cultural relic content with the context features of the currently browsed content in the cultural relic knowledge graph to obtain the final recommended content features corresponding to the target cultural relic content.

[0156] The recommendation unit 405 is used to match the multi-modal current recommended cultural relic content based on the final recommended content features corresponding to the target cultural relic content and push it to the target user.

[0157] Optionally, in another embodiment of the present application, the cultural relics content information processing device further includes:

[0158] The data acquisition unit is used to obtain the latest historical behavior data of the target user.

[0159] The node creation unit is used to create a node corresponding to the target cultural relic content based on the attributes of the target cultural relic content, with respect to the target cultural relic content that generates the behavior recorded in the historical behavior data of the target user.

[0160] The vector initialization unit is used to initialize the node feature vector of the target cultural relic content according to the attributes of the target cultural relic content.

[0161] The node connection unit is used to connect the nodes corresponding to each target cultural relic content according to the behavior sequence in the historical behavior data of the target user, and record the behavior time on the connected edge to obtain the current cultural relic spatiotemporal graph.

[0162] Optionally, in the cultural relics content information processing device provided in another embodiment of the present application, the node feature updating unit includes:

[0163] The neighbor node determination unit is used to determine each neighbor node of the target cultural relic content in the current cultural relic space-time graph for each target cultural relic content.

[0164] The coefficient calculation unit is used to calculate the normalization coefficients between the target cultural relic content and each neighboring node.

[0165] The weight determination unit is used to determine the current weight matrix corresponding to the target cultural relic content.

[0166] The accumulation unit is used to obtain the current weighted sum of the target cultural relic content based on the normalization coefficients of the target cultural relic content and each neighboring node, the node feature vector of the target cultural relic content, and the current weight matrix corresponding to the target cultural relic content.

[0167] The updating unit is used to calculate the latest node feature vector of the current target cultural relic content through the current weighting, preset bias term and preset activation function of the target cultural relic content.

[0168] Optionally, in the cultural relics content information processing device provided in another embodiment of the present application, the behavior feature combining unit includes:

[0169] The behavior feature generating unit is used to generate a real-time behavior feature vector of the target user based on the real-time behavior data of the target user.

[0170] The node feature weighting unit is used to multiply the difference between the node feature vector of the current target cultural relic content and the real-time behavior feature vector of the target user by the learning rate for each target cultural relic content, and add the resulting product to the node feature vector of the current target cultural relic content to obtain the real-time feature vector corresponding to the target cultural relic content.

[0171] Optionally, in another embodiment of the present application, the cultural relics content information processing device further includes:

[0172] The entity creation unit is used to define each cultural relic and each cultural relic category as an entity in the knowledge graph and add detailed information for each entity.

[0173] The entity connection unit is used to connect the entity of each cultural relic with the entity of the cultural relic category to which it belongs, and with the entities of other cultural relics belonging to the same cultural relic category, so as to obtain a cultural relic knowledge graph.

[0174] Optionally, in the cultural relics content information processing device provided in another embodiment of the present application, the cultural relics feature fusion unit includes:

[0175] The cultural relic feature weighting unit performs weighted calculation according to the fusion weight on the real-time feature vector corresponding to the target cultural relic content and the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-built cultural relic knowledge graph to obtain the initial recommended content features corresponding to the target cultural relic content.

[0176] Optionally, in the cultural relics content information processing device provided in another embodiment of the present application, the context feature combining unit includes:

[0177] The context feature combining subunit is used to weight the initial recommended content features corresponding to the target cultural relic content and the context features of the currently browsed content in the cultural relic knowledge graph according to the context weight to obtain the final recommended content features corresponding to the target cultural relic content. The context weight is determined according to the type of the currently browsed content and / or the key information in the currently browsed content.

[0178] It should be noted that the specific working process of each unit provided in the above embodiments of the present application can refer to the implementation process of the corresponding steps in the above method embodiments, and will not be repeated here.

[0179] Another embodiment of the present application provides an electronic device, such as Figure 5As shown, including:

[0180] Memory 501 and processor 502 .

[0181] The memory 501 is used to store programs.

[0182] The processor 502 is used to execute the program stored in the memory 501. When the program is executed, it is specifically used to implement the cultural relic content information processing method provided in any one of the above embodiments.

[0183] Another embodiment of the present application provides a computer storage medium for storing a computer program. When the computer program is executed by a processor, it is used to implement the cultural relics content information processing method provided in any of the above embodiments.

[0184] Computer storage media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0185] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0186] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for processing cultural relics content information, characterized in that: include: Extracting spatiotemporal features from the target user's current spatiotemporal graph of cultural relics to obtain node feature vectors of each current target cultural relic content; wherein the current spatiotemporal graph of cultural relics records the latest historical behavior data of the target user on each target cultural relic content and the attributes of each target cultural relic content; For each target cultural relic content, the node feature vector of the current target cultural relic content is combined with the real-time behavior feature vector of the target user to obtain a real-time feature vector corresponding to the target cultural relic content; Performing weighted fusion on the real-time feature vector corresponding to the target cultural relic content and the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-constructed cultural relic knowledge graph to obtain the initial recommended content feature corresponding to the target cultural relic content; Combining the initial recommended content features corresponding to the target cultural relic content with the context features of the currently browsed content in the cultural relic knowledge graph to obtain the final recommended content features corresponding to the target cultural relic content; Based on the final recommended content features corresponding to the target cultural relic content, multimodal current recommended cultural relic content is matched and pushed to the target user.

2. The method according to claim 1, characterized in that: Before extracting the spatiotemporal features of the target user's current spatiotemporal graph of cultural relics to obtain the node feature vectors of the current contents of each target cultural relic, the method further includes: Obtain the latest historical behavior data of the target user; For the target cultural relic content that generates the behavior recorded in the historical behavior data of the target user, creating a node corresponding to the target cultural relic content based on the attributes of the target cultural relic content; Initializing a node feature vector of the target cultural relic content according to the attributes of the target cultural relic content; According to the behavior sequence in the historical behavior data of the target user, the nodes corresponding to the target cultural relic contents are connected, and the behavior time is recorded on the connected edges to obtain the current cultural relic spatiotemporal graph.

3. The method according to claim 1, characterized in that The step of extracting spatiotemporal features from the current spatiotemporal graph of cultural relics of the target user to obtain node feature vectors of the current contents of each target cultural relic includes: For each target cultural relic content, determine each neighbor node of the target cultural relic content in the current cultural relic spatiotemporal graph; Calculating the normalization coefficients of the target cultural relic content and each of the neighboring nodes; Determining a current weight matrix corresponding to the target cultural relic content; Based on the normalization coefficients of the target cultural relic content and each of the neighboring nodes, the node feature vector of the target cultural relic content, and the current weight matrix corresponding to the target cultural relic content, a current weighted sum of the target cultural relic content is obtained; The latest node feature vector of the current target cultural relic content is obtained by calculating the current weight of the target cultural relic content, the preset bias term and the preset activation function.

4. The method according to claim 1, characterized in that The step of combining the node feature vector of the current target cultural relic content with the real-time behavior feature vector of the target user for each target cultural relic content to obtain a real-time feature vector corresponding to the target cultural relic content includes: Generating a real-time behavior feature vector of the target user based on the real-time behavior data of the target user; For each target cultural relic content, a real-time feature vector corresponding to the target cultural relic content is obtained through the node feature vector of the current target cultural relic content and the real-time behavior feature vector of the target user.

5. The method according to claim 1, characterized in that: Also includes: Define each cultural relic and each cultural relic category as an entity in the knowledge graph, and add detailed information for each of the entities; The entities of each of the cultural relics are connected with the entities of the cultural relic category to which they belong, and with the entities of other cultural relics belonging to the same cultural relic category, to obtain a cultural relic knowledge graph.

6. The method according to claim 1, characterized in that The step of weighting and fusing the real-time feature vector corresponding to the target cultural relic content with the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-constructed cultural relic knowledge graph to obtain the initial recommended content feature corresponding to the target cultural relic content includes: The real-time feature vector corresponding to the target cultural relic content and the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-constructed cultural relic knowledge graph are weightedly calculated according to the fusion weight to obtain the initial recommended content features corresponding to the target cultural relic content.

7. The method according to claim 1, characterized in that The combining of the initial recommended content features corresponding to the target cultural relic content with the context features of the currently browsed content in the cultural relic knowledge graph to obtain the final recommended content features corresponding to the target cultural relic content includes: The initial recommended content features corresponding to the target cultural relic content and the context features of the currently browsed content in the cultural relic knowledge graph are weighted according to the context weight to obtain the final recommended content features corresponding to the target cultural relic content; wherein the context weight is determined according to the type of the currently browsed content and / or the key information in the currently browsed content.

8. A cultural relic content information processing device, characterized in that: include: A node feature updating unit is used to extract the spatiotemporal features of the current spatiotemporal graph of cultural relics of the target user to obtain the node feature vectors of each current target cultural relic content; wherein the current spatiotemporal graph of cultural relics records the latest historical behavior data of the target user on each target cultural relic content and the attributes of each target cultural relic content; A behavior feature combining unit is used to combine the node feature vector of the current target cultural relic content with the real-time behavior feature vector of the target user for each target cultural relic content, so as to obtain a real-time feature vector corresponding to the target cultural relic content; A cultural relic feature fusion unit, used to perform weighted fusion on the real-time feature vector corresponding to the target cultural relic content and the feature vector of the cultural relic corresponding to the target cultural relic content in the pre-constructed cultural relic knowledge graph, to obtain the initial recommended content feature corresponding to the target cultural relic content; A context feature combining unit, used to combine the initial recommended content features corresponding to the target cultural relic content with the context features of the currently browsed content in the cultural relic knowledge graph to obtain the final recommended content features corresponding to the target cultural relic content; The recommendation unit is used to match the multimodal current recommended cultural relic content based on the final recommended content features corresponding to the target cultural relic content and push it to the target user.

9. An electronic device, characterized in that: include: Memory and processor; Wherein, the memory is used to store programs; The processor is used to execute the program, and when the program is executed, it is specifically used to implement the cultural relics content information processing method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, is used to implement the cultural relics content information processing method as described in any one of claims 1 to 7.

Images