Non-perpetual digital resource recommendation method and system based on non-perpetual portrait case library
By building an intangible cultural heritage portrait case library and combining real-time situation data, the problem of inaccurate recommendation of intangible cultural heritage digital resources in the existing technology has been solved, and more efficient user needs satisfaction and experience improvement have been achieved.
Patent Information
- Application Number
- CN202411229249.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-11-29
AI Technical Summary
The existing methods of recommending intangible cultural heritage digital resources are based only on the users' social attributes and living habits, and cannot meet the actual needs of users, and the recommended intangible cultural heritage digital resources are not accurate enough.
Using the method based on the intangible cultural heritage portrait case library, by collecting intelligence resources associated with specific types of intangible cultural heritage, using semantic analysis tools to extract personnel and scene attribute characteristics, combining general big model analysis, constructing intangible cultural heritage portrait case library, and based on the target object The real-time situation data is matched and calculated, and the most suitable intangible cultural heritage digital resources are recommended.
It improves the accuracy of intangible cultural heritage digital resource recommendation, can better meet users' appreciation and learning needs of intangible cultural heritage resources, and provide a better experience.
Smart Images

Figure CN119046515A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of digital resource management, and in particular to a method and system for recommending intangible cultural heritage digital resources based on an intangible cultural heritage portrait case library. Background Art
[0002] The digitization of intangible cultural heritage is the process of recording, preserving, disseminating and recreating intangible cultural heritage using modern information technology. Scientific management of intangible cultural heritage resources based on information resource management science has important practical significance for application scenarios such as intangible cultural heritage inheritance and protection, cultural tourism, etc.
[0003] The recommendation of intangible cultural heritage digital resources is conducive to providing users with a better experience of appreciating and learning intangible cultural heritage resources. However, the existing methods are based on simple factors such as the user's social attributes and living habits to recommend intangible cultural heritage digital resources, resulting in the recommended intangible cultural heritage digital resources often failing to meet the actual needs of users. Further improvements are needed to the recommendation mechanism of intangible cultural heritage digital resources. Summary of the invention
[0004] In this regard, the present invention provides a method, system, electronic device, computer storage medium and computer program product for recommending intangible cultural heritage digital resources based on an intangible cultural heritage portrait case library to solve the above-mentioned technical problems.
[0005] The present invention discloses a method for recommending intangible cultural heritage digital resources based on an intangible cultural heritage portrait case library, the method comprising the following steps:
[0006] Collect intelligence resources associated with a specific type of intangible cultural heritage, and use semantic analysis tools to extract first person attribute features and first scene attribute features of intangible cultural heritage followers from the intelligence resources;
[0007] Use a general large model to analyze the first person attribute characteristics and the first scene attribute characteristics respectively, obtain a corresponding number of first person type labels and a number of first scene type labels, associate each of the first person type labels and each of the first scene type labels with a specific type of intangible cultural heritage to obtain an intangible cultural heritage portrait case, and construct all the intangible cultural heritage portrait cases into an intangible cultural heritage portrait case library;
[0008] Extracting a second person attribute feature and a second scene attribute feature of the target object based on the real-time situation data of the target object, and using a general large model to analyze the second person attribute feature and the second scene attribute feature respectively, to obtain a corresponding number of second person type labels and a number of second scene type labels;
[0009] Based on the plurality of the second person type labels and the plurality of the second scene type labels, matching calculations are performed with each of the intangible cultural heritage portrait cases in the intangible cultural heritage portrait case library to obtain a plurality of matching intangible cultural heritage portrait cases;
[0010] The intangible cultural heritage digital resources corresponding to the matching intangible cultural heritage portrait case are recommended to the target object.
[0011] In some embodiments, the collecting of intelligence resources associated with a specific type of intangible cultural heritage includes:
[0012] Collecting preliminary intelligence resources associated with a specific type of intangible cultural heritage, analyzing the exposure curve of the specific type of intangible cultural heritage based on the preliminary intelligence resources, and analyzing the stability of the exposure curve;
[0013] If the stability is higher than the stability threshold, determining the preliminary intelligence resource as the intelligence resource;
[0014] If the smoothness is lower than the smoothness threshold, the interception duration is determined based on the difference between the smoothness threshold and the smoothness, and the target intelligence resource is intercepted from the preliminary intelligence resource according to the interception duration, and the target intelligence resource is determined as the intelligence resource.
[0015] In some embodiments, determining the interception duration based on the difference between the smoothness threshold and the smoothness includes:
[0016] Substitute the difference into the following formula to calculate the interception duration:
[0017]
[0018] In the above formula, Δt is the interception time, T is the empirical value of the interception time, ΔB is the difference between the stability threshold and the stability, and A is the median value of the interception time of other specific types of intangible cultural heritage. It is the average length of interception of other specific types of intangible cultural heritage.
[0019] In some embodiments, the using of the general large model to analyze the first person attribute feature and the first scene attribute feature respectively to obtain corresponding first person type labels and first scene type labels includes:
[0020] Generate a training data set, and use the training data set to train the general large model to achieve fine-tuning;
[0021] The first person attribute feature and the first scene attribute feature are simultaneously input into the fine-tuned general large model to obtain a corresponding plurality of first person type labels and a corresponding plurality of first scene type labels.
[0022] In some embodiments, the extracting of the second person attribute feature and the second scene attribute feature of the target object based on the real-time situation data of the target object includes:
[0023] Acquire the real-time situation data of the target object, wherein the real-time situation data includes identity attribute information, network trace data, and geographic information data of the target object;
[0024] Use a semantic analysis tool to perform semantic analysis on the identity attribute information and the network trace data to obtain identity attribute features and network features respectively, and obtain the second person attribute features based on the identity attribute features and the network features;
[0025] Based on the analysis of the geographic information data, geographic scene attributes are obtained, and / or based on the analysis of the network trace data, network scene attributes are obtained, and the geographic scene attributes and / or the network scene attributes are used as the second scene attribute features.
[0026] In some embodiments, the recommending the intangible cultural heritage digital resources corresponding to the matched intangible cultural heritage portrait case to the target object includes:
[0027] Determine the recommended popularity of the intangible cultural heritage digital resources of the scene where the target object is located based on the geographic information data, and determine the recommended order of the intangible cultural heritage digital resources corresponding to the matched intangible cultural heritage portrait case based on the recommended popularity;
[0028] The intangible cultural heritage digital resources corresponding to the matching intangible cultural heritage portrait cases are gradually recommended to the target object in the recommendation order.
[0029] The present invention also discloses an intangible cultural heritage digital resource recommendation system based on an intangible cultural heritage portrait case library, the system comprising a communication device, a processing device, and a storage device;
[0030] The communication device is used to collect intelligence resources associated with a specific type of intangible cultural heritage, as well as real-time situation data of the target object;
[0031] The storage device is used to store a set of computer programs;
[0032] The processing device is used to retrieve and execute the computer program to implement the method described in any of the preceding items based on the intelligence resources and the real-time situation data.
[0033] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in any of the preceding items.
[0034] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.
[0035] The present invention also discloses a computer program product. When the computer program product is run on a terminal, the terminal implements any of the above methods when executing the computer program product.
[0036] The beneficial effect of the present invention is that: the scheme of the present invention is based on the intangible cultural heritage portrait case library, comprehensively considers the personnel type of the target object and the actual scene type to analyze the most suitable intangible cultural heritage digital resources, and then recommends them to them. Compared with the traditional recommendation method that only considers simple factors such as the user's social attributes and living habits, the recommendation is more accurate and can bring users a better experience of appreciating and learning intangible cultural heritage resources. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0038] Figure 1 It is a flow chart of a method for recommending intangible cultural heritage digital resources based on an intangible cultural heritage portrait case library disclosed in an embodiment of the present invention;
[0039] Figure 2 It is a schematic diagram of a process for collecting and processing intelligence resources disclosed in an embodiment of the present invention;
[0040] Figure 3 It is a structural schematic diagram of an intangible cultural heritage digital resource recommendation system based on an intangible cultural heritage portrait case library disclosed in an embodiment of the present invention. DETAILED DESCRIPTION
[0041] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are 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 the field without creative work are within the scope of protection of the present application.
[0042] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.
[0043] like Figure 1 As shown, an embodiment of the present invention discloses a method for recommending intangible cultural heritage digital resources based on an intangible cultural heritage portrait case library, the method comprising the following steps:
[0044] Collect intelligence resources associated with a specific type of intangible cultural heritage, and use semantic analysis tools to extract first person attribute features and first scene attribute features of intangible cultural heritage followers from the intelligence resources;
[0045] Use a general large model to analyze the first person attribute characteristics and the first scene attribute characteristics respectively, obtain a corresponding number of first person type labels and a number of first scene type labels, associate each of the first person type labels and each of the first scene type labels with a specific type of intangible cultural heritage to obtain an intangible cultural heritage portrait case, and construct all the intangible cultural heritage portrait cases into an intangible cultural heritage portrait case library;
[0046] Extracting a second person attribute feature and a second scene attribute feature of the target object based on the real-time situation data of the target object, and using a general large model to analyze the second person attribute feature and the second scene attribute feature respectively, to obtain a corresponding number of second person type labels and a number of second scene type labels;
[0047] Based on the plurality of the second person type labels and the plurality of the second scene type labels, matching calculations are performed with each of the intangible cultural heritage portrait cases in the intangible cultural heritage portrait case library to obtain a plurality of matching intangible cultural heritage portrait cases;
[0048] The intangible cultural heritage digital resources corresponding to the matching intangible cultural heritage portrait case are recommended to the target object.
[0049] The core of the scheme of the present invention is to recommend the most suitable intangible cultural heritage digital resources to the target object based on the intangible cultural heritage portrait case library. Specifically, first collect intelligence resources associated with a specific type of intangible cultural heritage, use semantic analysis tools to extract the first personnel attribute characteristics and the first scene attribute characteristics of the intangible cultural heritage followers from the intelligence resources, use a general large model to perform in-depth semantic understanding on it, obtain the corresponding first personnel type label and the first scene type label, associate the obtained first personnel type label and the first scene type label with the specific type of intangible cultural heritage to obtain an intangible cultural heritage portrait case, which characterizes that certain types of people will be interested in the corresponding type of intangible cultural heritage digital resources when they are in certain types of scenes. Then, obtain the real-time situation information of the target object, extract and analyze the second personnel type label and the second scene type label of the target object in the same way, match and calculate based on the two labels and each intangible cultural heritage portrait case in the intangible cultural heritage portrait case library, and the intangible cultural heritage digital resource corresponding to the successful matching intangible cultural heritage portrait case is the best intangible cultural heritage digital resource adapted to the personnel type and actual scene of the target object, and recommend it to the target object.
[0050] Therefore, the solution of the present invention is based on the intangible cultural heritage portrait case library, and comprehensively considers the personnel type of the target object and the actual scene type to analyze the most suitable intangible cultural heritage digital resources, and then recommends them to them. Compared with the traditional recommendation method that only considers simple factors such as the user's social attributes and living habits, the recommendation is more accurate and can bring users a better experience of appreciating and learning intangible cultural heritage resources.
[0051] The semantic analysis tools mentioned above may adopt existing semantic analysis tools such as OpenAI and TexSmart, or may be self-built and trained based on Transformer, convolutional network, etc., and the present invention is not limited to this.
[0052] It should be noted that a target object may correspond to multiple person type labels and scene type labels, so each intangible cultural heritage portrait case actually includes multiple combinations of multiple first person type labels and first scene type labels, that is, multiple sub-cases. Correspondingly, the multiple combinations of the second person type labels and the second scene type labels obtained in real time are matched and calculated with the sub-cases of each intangible cultural heritage portrait case in the intangible cultural heritage portrait case library.
[0053] In some embodiments, reference Figure 2 As shown, the information resources collected and associated with a specific type of intangible cultural heritage include:
[0054] Collecting preliminary intelligence resources associated with a specific type of intangible cultural heritage, analyzing the exposure curve of the specific type of intangible cultural heritage based on the preliminary intelligence resources, and analyzing the stability of the exposure curve;
[0055] If the stability is higher than the stability threshold, determining the preliminary intelligence resource as the intelligence resource;
[0056] If the smoothness is lower than the smoothness threshold, the interception duration is determined based on the difference between the smoothness threshold and the smoothness, and the target intelligence resource is intercepted from the preliminary intelligence resource according to the interception duration, and the target intelligence resource is determined as the intelligence resource.
[0057] In an embodiment of the present invention, the collected intelligence resources associated with a specific type of intangible cultural heritage can be used to analyze the above-mentioned first personal attribute characteristics and first scene attribute characteristics of intangible cultural heritage followers. However, since different types of intangible cultural heritage have different audiences, it is necessary to process the collected preliminary intelligence resources according to different situations.
[0058] Specifically, all network records related to a specific type of intangible cultural heritage are first obtained through web crawling technology, including news reports, reports from relevant institutions, microblog discussions, short videos and other content. These network records contain topic content related to a specific type of intangible cultural heritage. Semantic analysis tools are used to understand the unstructured data contained therein (such as news text, voice content in short videos, etc.), and the first person attribute characteristics and the first scene attribute characteristics of the intangible cultural heritage followers can be obtained. Based on the crawled preliminary intelligence resources, the exposure curve of the specific type of intangible cultural heritage is analyzed, where the exposure refers to the conversion value of the number of network exposures of the specific type of intangible cultural heritage in a period of time. The larger the exposure number, the larger the corresponding conversion value, and vice versa. The stability of the curve is calculated based on the equivalent value (such as the mean value or median value) of the fluctuation amplitude of each point of the exposure curve relative to the baseline (i.e., the straight line parallel to the x-axis drawn by the average value of the curve). The higher the stability, the more stable the network's heat for the specific type of intangible cultural heritage is, which means that the type of people who pay attention to the specific type of intangible cultural heritage has not changed much. For example, the main followers of Peking Opera have always been middle-aged and elderly people, and young people have fewer followers; the lower the stability, the less stable the network's heat for the specific type of intangible cultural heritage is, for example, some intangible cultural heritage projects originally had low attention, but due to the adoption of measures such as increasing experience projects and grafting on cultural tourism projects, they have been loved by young people recently, showing an obvious trend of rejuvenation. In view of the above characteristics, the present invention is arranged to determine all network resources obtained by crawling, that is, preliminary intelligence resources, as intelligence resources when the stability is higher than the stable threshold, and sufficient data volume can ensure the accuracy of the first personnel attribute characteristics and the first scene attribute characteristics obtained by subsequent analysis; and when the stability is lower than the stable threshold, the difference between the stable threshold and the stability is set to determine the interception duration, and the target intelligence resource is intercepted from the preliminary intelligence resource (based on the current moment, intercepted in the direction of historical time), and it is determined as the final intelligence resource, so that the first personnel attribute characteristics and the first scene attribute characteristics can be accurately analyzed based on the latest development trend of the specific type of intangible cultural heritage.
[0059] In some embodiments, determining the interception duration based on the difference between the smoothness threshold and the smoothness includes:
[0060] Substitute the difference into the following formula to calculate the interception duration:
[0061]
[0062] In the above formula, Δt is the interception time, T is the empirical value of the interception time, ΔB is the difference between the stability threshold and the stability, and A is the median value of the interception time of other specific types of intangible cultural heritage. It is the average length of interception of other specific types of intangible cultural heritage.
[0063] In an embodiment of the present invention, the interception duration is negatively correlated with the difference between the stability threshold and the stability, that is, the larger the difference, the more significant the difference between the attention paid to a specific type of intangible cultural heritage at the current stage and the historical attention paid. In this case, the interception duration is set to be shorter, so that the first personnel attribute characteristics and the first scene attribute characteristics mentioned above can be analyzed based on the intelligence resources at the current stage first, thereby reducing the interference of early intelligence resources. When the difference is smaller, it means that the attention paid to a specific type of intangible cultural heritage at the current stage is not significantly different from the historical attention paid. In this case, the interception duration is set to be longer, so that more intelligence resources can be obtained to analyze the first personnel attribute characteristics and the first scene attribute characteristics mentioned above, thereby improving the accuracy of the analysis results.
[0064] In addition, the above calculation formula of the present invention also refers to the interception time of other specific types of intangible cultural heritage, that is, the ratio of the median value to the average value of the interception time of other specific types of intangible cultural heritage is used as the adjustment coefficient, which can reduce the impact of short-term abnormal fluctuations caused by interference from other non-focus factors on the above stability.
[0065] In some embodiments, the using of the general large model to analyze the first person attribute feature and the first scene attribute feature respectively to obtain corresponding first person type labels and first scene type labels includes:
[0066] Generate a training data set, and use the training data set to train the general large model to achieve fine-tuning;
[0067] The first person attribute feature and the first scene attribute feature are simultaneously input into the fine-tuned general large model to obtain a corresponding plurality of first person type labels and a corresponding plurality of first scene type labels.
[0068] In an embodiment of the present invention, the above-mentioned general large model in the present invention refers to ChatGPT, BERT, T5, etc. in the field of natural language processing (NLP), which is a deep learning model with hundreds of millions or even hundreds of billions of parameters obtained by pre-training with a large amount of data. The present invention first uses the training data to fine-tune it, so as to obtain the above-mentioned general large model that can be used for the above-mentioned scheme of the present invention.
[0069] The training data in the training data set may be unstructured text data, including text data related to personnel attribute features, text data related to scene attribute features, and text description data and label classification rules added to these text data manually or automatically, and these text description data are used to explain the approximate correspondence between different personnel attributes and personnel label classification rules, and the approximate correspondence between different scene attributes and scene label classification rules. The general large model obtained after fine-tuning the training can master the label classification method, so that the first personnel attribute features and the first scene attribute features can be semantically understood, and then several appropriate first personnel type labels and several first scene type labels can be determined respectively.
[0070] In some embodiments, the extracting of the second person attribute feature and the second scene attribute feature of the target object based on the real-time situation data of the target object includes:
[0071] Acquire the real-time situation data of the target object, wherein the real-time situation data includes identity attribute information, network trace data, and geographic information data of the target object;
[0072] Use a semantic analysis tool to perform semantic analysis on the identity attribute information and the network trace data to obtain identity attribute features and network features respectively, and obtain the second person attribute features based on the identity attribute features and the network features;
[0073] Based on the analysis of the geographic information data, geographic scene attributes are obtained, and / or based on the analysis of the network trace data, network scene attributes are obtained, and the geographic scene attributes and / or the network scene attributes are used as the second scene attribute features.
[0074] In the embodiment of the present invention, for the target object, its recent network trace data, geographic information data, and identity attribute information can be obtained through mobile terminal authorization, etc. Among them, network trace data refers to the network access data of the target object, such as browsing products in shopping apps, viewing and participating in discussions on related intangible cultural heritage topics in Weibo, etc.; geographic information data refers to real-time positioning information obtained through the mobile phone positioning system.
[0075] By using the aforementioned semantic analysis tool to perform semantic analysis on the target object's identity attribute information and network trace data, its identity attribute characteristics and network characteristics can be obtained respectively. The identity attribute characteristics are used to describe the type of intangible cultural heritage that the target object's identity may be interested in, and the network characteristics can be directly determined based on the target object's search and viewing of intangible cultural heritage-related content on the Internet. The second person attribute characteristics of the target object can be analyzed based on the identity attribute characteristics and network characteristics. At the same time, based on the geographic information data, the geographical scene attributes of the target object can be determined, such as the area associated with a certain type of intangible cultural heritage (such as the place of origin or development), and based on the network trace data, the network scene attributes of the target object can be analyzed, such as a shopping APP (the target object is viewing clothing, musical instruments, etc. related to a certain type of intangible cultural heritage), and the geographical scene attributes and / or network scene attributes are used as the second scene attribute characteristics.
[0076] In some embodiments, the recommending the intangible cultural heritage digital resources corresponding to the matched intangible cultural heritage portrait case to the target object includes:
[0077] Determine the recommended popularity of the intangible cultural heritage digital resources of the scene where the target object is located based on the geographic information data, and determine the recommended order of the intangible cultural heritage digital resources corresponding to the matched intangible cultural heritage portrait case based on the recommended popularity;
[0078] The intangible cultural heritage digital resources corresponding to the matching intangible cultural heritage portrait cases are gradually recommended to the target object in the recommendation order.
[0079] In an embodiment of the present invention, there may be multiple intangible cultural heritage digital resources determined above, and a recommendation order needs to be determined at this time. Specifically, based on the above-mentioned geographic information data of the target object, the recommended heat of various types of intangible cultural heritage digital resources in the scene in which it is located is determined, and the intangible cultural heritage digital resources obtained by the above-mentioned matching are sorted accordingly according to the recommended heat. For example, the intangible cultural heritage digital resources obtained by matching are three types, A, B, and F, and their recommended heats are B, D, A, E, F, and G. Therefore, the recommended order of the intangible cultural heritage digital resources obtained by matching are A, B, and F is B, A, and F.
[0080] like Figure 3 As shown, the embodiment of the present invention also discloses an intangible cultural heritage digital resource recommendation system based on an intangible cultural heritage portrait case library, the system comprising a communication device, a processing device, and a storage device;
[0081] The communication device is used to collect intelligence resources associated with a specific type of intangible cultural heritage, as well as real-time situation data of the target object;
[0082] The storage device is used to store a set of computer programs;
[0083] The processing device is used to retrieve and execute the computer program to implement the method described in the above embodiment based on the intelligence resources and the real-time situation data.
[0084] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, characterized in that: the processor executes the computer program to implement the method described in the above embodiment.
[0085] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and is characterized in that: the computer program is executed by a processor to implement the method described in the above embodiment.
[0086] The embodiment of the present invention further discloses a computer program product. When the computer program product is run on a terminal, the terminal implements the method described in the above embodiment.
[0087] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0088] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0090] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.
Claims
1. A method for recommending intangible cultural heritage digital resources based on an intangible cultural heritage portrait case library, characterized in that: The method comprises the following steps: Collect intelligence resources associated with a specific type of intangible cultural heritage, and use semantic analysis tools to extract first person attribute features and first scene attribute features of intangible cultural heritage followers from the intelligence resources; Use a general large model to analyze the first person attribute characteristics and the first scene attribute characteristics respectively, obtain a corresponding number of first person type labels and a number of first scene type labels, associate each of the first person type labels and each of the first scene type labels with a specific type of intangible cultural heritage to obtain an intangible cultural heritage portrait case, and construct all the intangible cultural heritage portrait cases into an intangible cultural heritage portrait case library; Extracting a second person attribute feature and a second scene attribute feature of the target object based on the real-time situation data of the target object, and using a general large model to analyze the second person attribute feature and the second scene attribute feature respectively, to obtain a corresponding number of second person type labels and a number of second scene type labels; Based on the plurality of the second person type labels and the plurality of the second scene type labels, matching calculations are performed with each of the intangible cultural heritage portrait cases in the intangible cultural heritage portrait case library to obtain a plurality of matching intangible cultural heritage portrait cases; The intangible cultural heritage digital resources corresponding to the matching intangible cultural heritage portrait case are recommended to the target object.
2. The method for recommending intangible cultural heritage digital resources based on an intangible cultural heritage portrait case library according to claim 1, characterized in that: Collect intelligence resources related to specific types of intangible cultural heritage, including: Collecting preliminary intelligence resources associated with a specific type of intangible cultural heritage, analyzing the exposure curve of the specific type of intangible cultural heritage based on the preliminary intelligence resources, and analyzing the stability of the exposure curve; If the stability is higher than the stability threshold, determining the preliminary intelligence resource as the intelligence resource; If the smoothness is lower than the smoothness threshold, the interception duration is determined based on the difference between the smoothness threshold and the smoothness, and the target intelligence resource is intercepted from the preliminary intelligence resource according to the interception duration, and the target intelligence resource is determined as the intelligence resource.
3. The method for recommending intangible cultural heritage digital resources based on an intangible cultural heritage portrait case library according to claim 2, characterized in that: Determining the interception duration based on the difference between the stability threshold and the stability, including: Substitute the difference into the following formula to calculate the interception duration: In the above formula, Δt is the interception time, T is the empirical value of the interception time, ΔB is the difference between the stability threshold and the stability, and A is the median value of the interception time of other specific types of intangible cultural heritage. It is the average length of interception of other specific types of intangible cultural heritage.
4. The method for recommending intangible cultural heritage digital resources based on an intangible cultural heritage portrait case library according to claim 3, characterized in that: The first person attribute feature and the first scene attribute feature are analyzed respectively using a general large model to obtain a corresponding plurality of first person type labels and a plurality of first scene type labels, including: Generate a training data set, and use the training data set to train the general large model to achieve fine-tuning; The first person attribute feature and the first scene attribute feature are simultaneously input into the fine-tuned general large model to obtain a corresponding plurality of first person type labels and a corresponding plurality of first scene type labels.
5. The method for recommending intangible cultural heritage digital resources based on an intangible cultural heritage portrait case library according to claim 1, characterized in that: The second person attribute feature and the second scene attribute feature of the target object are obtained based on the real-time situation data of the target object, including: Acquire the real-time situation data of the target object, wherein the real-time situation data includes identity attribute information, network trace data, and geographic information data of the target object; Use a semantic analysis tool to perform semantic analysis on the identity attribute information and the network trace data to obtain identity attribute features and network features respectively, and obtain the second person attribute features based on the identity attribute features and the network features; Based on the analysis of the geographic information data, geographic scene attributes are obtained, and / or based on the analysis of the network trace data, network scene attributes are obtained, and the geographic scene attributes and / or the network scene attributes are used as the second scene attribute features.
6. The method for recommending intangible cultural heritage digital resources based on an intangible cultural heritage portrait case library according to claim 5, characterized in that: Recommending the intangible cultural heritage digital resources corresponding to the matched intangible cultural heritage portrait case to the target object includes: Determine the recommended popularity of the intangible cultural heritage digital resources of the scene where the target object is located based on the geographic information data, and determine the recommended order of the intangible cultural heritage digital resources corresponding to the matched intangible cultural heritage portrait case based on the recommended popularity; The intangible cultural heritage digital resources corresponding to the matching intangible cultural heritage portrait cases are gradually recommended to the target object in the recommendation order.
7. A non-legacy digital resource recommendation system based on a non-legacy portrait case library, the system comprising a communication device, a processing device, and a storage device; characterized in that: The communication device is used to collect intelligence resources associated with a specific type of intangible cultural heritage, as well as real-time situation data of the target object; The storage device is used to store a set of computer programs; The processing device is used to retrieve and execute the computer program to implement the method according to any one of claims 1 to 6 based on the intelligence resources and the real-time situation data.
8. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 6.
9. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program stored on a non-transitory computer readable medium, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.
