A semantic field reconstruction and emotional migration translation method and system for cross-cultural marketing

Abstract

The present application relates to the field of computer language translation, and more particularly to a semantic field reconstruction and emotional transfer translation method and system for cross-cultural marketing, wherein the method first establishes a cultural semantic field of a target brand and defines value invariants of the target brand based on the cultural semantic field, then in response to input of source content of the target brand, adopts a preset emotional transfer operator to map the source content to obtain a target emotional vector, then based on a preset metaphor decoupling encoder and a function alignment reconstructor, decouples and functionally reconstructs source cultural symbols in the source content to obtain optimal replacement symbols of the source cultural symbols, and finally based on the value invariants, the target emotional vector and the optimal replacement symbols, generates a free translation text under a target cultural context through semantic splicing. Compared with the prior art, the method improves the cross-border translation effect of the language used by the cross-border brand for overseas promotion.

Description

Technical Field

[0001] This invention relates to the field of computer language translation. More specifically, this invention relates to a semantic field reconstruction and emotional transfer translation method and system for cross-cultural marketing. Background Technology

[0002] In the era of digital marketing, where globalization and localization coexist, brands from different regions / countries urgently need to achieve the dual goals of value consistency and emotional resonance within a multicultural context to meet the real needs and cultural identity of their target audience. With the development of large-scale language models and cross-modal representation learning, cross-cultural marketing has evolved from coarse-grained machine translation adaptation to fine-grained cultural semantic decoding and reconstruction. Current technologies primarily employ the following methods: (1) Translate the source language advertisement into the target language using Neural Machine Translation (NMT) and replace it with keywords. (2) Translate the source language into the target language according to the preset content conversion rules in the Hofstede (Hofstede's Cultural Dimensions Theory) model. (3) Use the LIWC (Linguistic Inquiry and Word Count) model to adjust the polarity of emotional expression in cross-language scenarios. (4) Use the multilingual CLIP (Contrastive Language-Image Pre-training) model to generate localized language based on its image and text semantics.

[0003] The above methods have the following drawbacks: First, the translation results suffer from a flattened cultural representation. These two methods primarily reduce cultural differences to lexical or emotional mapping labels, failing to reconstruct the topological structure of the cultural semantic field (e.g., "free" is associated with different networks in the East and West), leading to a distortion of the core brand value in advertising and promotional language. Second, they only adjust the intensity of emotional expression without adapting to the unique expressive differences between cultures, potentially causing cognitive conflict and weakening the brand's appeal in overseas marketing. Third, cultural metaphors are lost; deeper symbols are stripped of their social function during translation. For example, "red envelope" is translated as "red letter envelope," its content remaining superficial and even containing cultural offense. Fourth, the rule base of these methods is statically outdated; the pre-set mappings cannot respond to the semantic evolution caused by Generation Z discourse and internet slang, resulting in a disconnect between brand information and user cognition.

[0004] In summary, the main problem with existing technologies is poor translation quality. Summary of the Invention

[0005] To address the aforementioned technical issues of poor translation quality, this invention discloses a semantic field reconstruction and emotional transfer translation method and system for cross-cultural marketing.

[0006] In a first aspect, this invention discloses a method for semantic field reconstruction and emotional transfer translation in cross-cultural marketing, comprising: Establish the cultural semantic field of the target brand and define the value invariants of the target brand based on the cultural semantic field; In response to the input of source content from the target brand, a preset sentiment transfer operator is used to map the source content to obtain the target sentiment vector; Based on the preset metaphor decoupling encoder and functional alignment reconstructor, the source cultural symbols in the source content are decoupled and functionally reconstructed to obtain the best replacement symbols for the source cultural symbols. Based on value invariants, target sentiment vectors, and optimal replacement symbols, semantic splicing is used to generate interpretive texts within the target cultural context.

[0007] Beneficial Effects: This invention refines the granularity of cultural modeling by constructing a cultural semantic field and uses this field to define the value invariants of the target brand. This allows for the precise identification of "semantic anchors" that support subsequent semantic splicing, ensuring that the generated paraphrased text does not deviate from the core culture of the target brand. Furthermore, this invention uses an emotion transfer operator to map the target emotion vector of the source content, serving as a "style controller" to determine the tone and mood of the generated text. The optimal replacement symbol approximates a mandatory keyword, used to require the text to generate a corresponding paraphrased text around that symbol. Compared to existing technologies, this invention reconstructs the topological structure of the cultural semantic field and adapts to the unique expressive differences of different cultures through emotion transfer operator mapping. It also decouples and reconstructs cultural metaphors through a metaphor decoupling encoder and a functional alignment reconstructor, eliminating the shortcomings of existing technologies and thus improving the effectiveness of cross-border translation of language used by cross-border brands for overseas promotion.

[0008] Preferably, a multilingual cultural semantic field is established, including: Construct a cross-cultural corpus covering languages ​​from multiple regions; A contrastive learning approach is used to extract cultural semantic fields from a cross-cultural corpus to represent the target brand in different cultures.

[0009] Preferably, the value invariants of the target brand defined based on the cultural semantic field include: Identify the common intersection area of ​​multiple languages ​​in the cultural semantic field; Calculate the Euclidean distance between each semantic vector within the common intersection region and the original brand core value vector; The semantic vector that minimizes the Euclidean distance is selected as the value invariant.

[0010] Preferably, the specific algorithm for selecting the semantic vector that minimizes the Euclidean distance as the value invariant is as follows:

[0011] In the formula, Representing value invariants, This represents taking the value of the variable that minimizes the objective function. Represents the semantic vectors within the common intersection region. This represents the original brand's core value vector. Indicates the first The cultural semantic field of a language Indicates a common intersection area. This represents the Euclidean norm.

[0012] Preferably, a preset sentiment transfer operator is used to map the source content, including: Based on the emotional expression bases of the source culture and the target culture, a cross-cultural emotional transfer matrix is ​​constructed as an emotional transfer operator.

[0013] Preferably, the metaphor decoupling encoder is configured to perform the following steps: Establish a vector representation mapping for source cultural symbols; The source cultural symbols are decomposed into surface-level formal feature components and deep-level functional feature components.

[0014] Preferably, the function alignment refactorer is configured to perform the following steps: Receive deep functional feature components; In the symbol library of the target culture, the similarity between the functional feature components and the deep functional feature components of candidate symbols is calculated. The candidate symbol with the highest similarity is selected as the best replacement symbol.

[0015] Preferably, after generating the paraphrased text in the target cultural context, the method of the present invention further includes: Map the paraphrased text back to the semantic space; The sum of distances between the paraphrased texts of different target language versions in the shared semantic space is calculated as the consistency loss; If the loss of consistency exceeds a preset threshold, then return to the step of establishing the cultural semantic field of the target brand.

[0016] Beneficial effects: If the consistency loss exceeds the preset threshold using the above technical solution, the process returns to the step of establishing the cultural semantic field of the target brand. This approach can iteratively update the paraphrased text to improve the cultural fit of the paraphrased text.

[0017] Preferably, based on value invariants, target sentiment vectors, and optimal replacement symbols, semantic splicing is used to generate a paraphrased text within the target cultural context, specifically: Value invariants, target sentiment vectors, and optimal replacement symbols are input into a deep learning-based natural language processing model for semantic concatenation to obtain the paraphrased text.

[0018] Secondly, this invention discloses a semantic field reconstruction and emotional transfer translation system for cross-cultural marketing, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the semantic field reconstruction and emotional transfer translation method for cross-cultural marketing described in the first aspect is implemented.

[0019] The beneficial effects of this invention are as follows: Compared to existing technologies, the method of this invention can reconstruct the topological structure of the cultural semantic field and adapt to the unique expression differences of different cultures through the emotion transfer operator mapping method. It also decouples and reconstructs cultural metaphors through metaphor decoupling encoder and functional alignment reconstructor, which can eliminate the defects existing in the existing technologies, thereby improving the cross-border translation effect of terms used by cross-border brands for overseas promotion. Attached Figure Description

[0020] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent upon reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of the invention are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts, wherein: Figure 1 This is a flowchart of the semantic field reconstruction and emotional transfer translation method for cross-cultural marketing in Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the semantic field reconstruction and emotional transfer translation system for cross-cultural marketing in Embodiment 2 of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0023] Example 1 like Figure 1 As shown, this embodiment discloses a semantic field reconstruction and emotional transfer translation method for cross-cultural marketing, including: S10: Establish the cultural semantic field of the target brand and define the value invariants of the target brand based on the cultural semantic field.

[0024] Step S10 includes: S11: Construct a cross-cultural corpus covering languages ​​from multiple regions.

[0025] In this embodiment, the aforementioned multi-regional languages ​​include more than 50 languages ​​from different regions or countries. The data source for the cross-cultural corpus can be Ethnologue or Glottolog.

[0026] S12: Employ contrastive learning to extract cultural semantic fields from cross-cultural corpora to represent the target brand in different cultures.

[0027] It should be explained that the aforementioned contrastive learning method refers to performing similarity comparison queries in a cross-cultural corpus based on a rule engine. Specifically, the target brand extracts the aforementioned cultural semantic field by inputting comparison conditions into the rule engine. This can be the market the target brand wants to enter, such as "Southeast Asia," "Middle East," or "Western Europe," or the product / service the target platform wants to promote, or a combination of the above two, or a combination including other comparison conditions.

[0028] Specifically, step S12 above extracts the cultural semantic field embedding through contrastive learning. Each term is represented as a context-aware vector. Indicates the first The cultural semantic field of a language express The dimension of the real vector space depends on the number of conditions set in the rule engine. The information returned by the query is generated in an encoded form. , The vocabulary of different languages ​​is mapped to a high-dimensional geometric space, where each point represents the semantics of a word.

[0029] Furthermore, step S10 above also includes: S13: Identify the common intersection area of ​​multiple languages ​​in the cultural semantic field.

[0030] In this embodiment, the common intersection area represents the cross-cultural human commonalities existing in all target cultures. It is a kind of "consensus" at the psychological and cognitive level. At the level of physical basic language description, it includes product attributes, such as softness or hardness, color or taste; it also includes product concepts, such as cheap, expensive or new. At the level of emotional basic language description, it includes basic emotions, such as joy, anger, sorrow and happiness; it also includes family and love, such as maternal love, protectiveness towards young children or friendship.

[0031] S14: Calculate the Euclidean distance between each semantic vector within the common intersection region and the original brand core value vector.

[0032] S15: Select the semantic vector that minimizes the Euclidean distance as the value invariant.

[0033] The specific calculation expressions for steps S14-S15 above are as follows:

[0034] In the formula, Representing value invariants, This represents taking the value of the variable that minimizes the objective function. Represents the semantic vectors within the common intersection region. This represents the original brand's core value vector. Indicates the first The cultural semantic field of a language Indicates a common intersection area. This represents the Euclidean norm.

[0035] Through steps S10-S15 above, the method of this embodiment refines the granularity of cultural modeling by constructing the above-mentioned cultural semantic field, and uses the cultural semantic field to calculate the value invariant of the target brand, thereby accurately finding the "semantic anchor point" that supports subsequent semantic splicing, thus ensuring that the brand value remains consistent in each cultural semantic field after migration, so that the final generated paraphrased text will not deviate from the core culture of the target brand.

[0036] S20: In response to the input of source content from the target brand, the source content is mapped using a preset sentiment transfer operator to obtain the target sentiment vector.

[0037] Furthermore, step S20 above includes: Based on the emotional expression bases of the source culture and the target culture, a cross-cultural emotional transfer matrix is ​​constructed as an emotional transfer operator.

[0038] Specifically, regarding the construction of emotion expression bases: First, define the emotional expression basis for each culture. In the formula, Representing culture The basis of emotional expression This indicates the basis for the expression of emotion. There are 3 basis vectors, each representing a unique archetype of emotional expression in that culture, such as semantic expressions of “subtlety,” “irony,” or “directness.”

[0039] Then, based on the above-mentioned emotional expression basis, an emotional transfer operator is designed, specifically as follows: Utilizing pre-built linear mappings Transforming the source culture's emotional expression into the target culture's expression:

[0040] In the formula, Indicate target culture The target sentiment vector in Representing the source culture The emotional expression vector in This represents a cross-cultural emotional transfer matrix.

[0041] Among them, the aforementioned cross-cultural emotion transfer matrix is ​​a transfer matrix learned through adversarial training, which is used to rotate / scale the expression of the source culture into the space of the target culture.

[0042] Through the above technical solution, the method of this embodiment obtains the target sentiment vector of the source content by mapping the sentiment transfer operator, which serves as a "style controller" to determine the tone and emotion of the generated text.

[0043] S30: Based on the preset metaphor decoupling encoder and functional alignment reconstructor, the source cultural symbols in the source content are decoupled and functionally reconstructed to obtain the best replacement symbol for the source cultural symbols.

[0044] The metaphor decoupling encoder is configured to perform the following steps: S31: Establish a vector representation mapping of source cultural symbols.

[0045] S32: Decompose the source cultural symbols into surface formal feature components and deep functional feature components.

[0046] Specifically, the expressions for steps S31-S32 at the algorithm layer are as follows:

[0047] The above formula represents the source cultural symbols Decomposed into surface-level feature components and deep functional characteristic components For example, the source cultural symbol is "red envelope," which, through the aforementioned metaphorical decoupling encoder, is decoupled into the surface formal feature component "red envelope" and the deep functional feature component "social reciprocity ritual." The source cultural symbol is "dragon," which, through the aforementioned metaphorical decoupling encoder, is decoupled into the surface formal feature component "flying snake-like creature" and the deep functional feature component "totem, auspiciousness, or power."

[0048] Furthermore, the aforementioned function alignment refactorer is configured to perform the following steps: S33: Receive deep functional feature components.

[0049] S34: In the symbol library of the target culture, calculate the similarity between the functional feature components and the deep functional feature components of the candidate symbols.

[0050] S35: Select the candidate symbol with the highest similarity as the best replacement symbol.

[0051] Specifically, the specific algorithm expression for implementing steps S33-S35 above is as follows:

[0052] In the formula, Indicates the best substitution symbol. This indicates the search for symbols that maximize similarity. Represents the cosine similarity function. The functional feature components representing candidate symbols, The best replacement symbol belongs to the target culture. The set of candidate symbols in.

[0053] By using the technical solutions described in steps S33-S35 above, the metaphorical transfer of "form changes but spirit remains the same" can be achieved, reducing cultural cognitive errors and stereotypes.

[0054] S40: Based on value invariants, target sentiment vectors, and optimal replacement symbols, semantic splicing generates interpretive texts within the target cultural context.

[0055] Specifically, by inputting value invariants, target sentiment vectors, and optimal substitution symbols into a deep learning-based natural language processing model for semantic concatenation, a paraphrased text is obtained. In the aforementioned natural language processing model, value invariants serve as "semantic anchors," the target sentiment vectors serve as "style controllers," and optimal substitution symbols serve as "mandatory keywords." These three elements work together to guide the natural language processing model in generating paraphrased text incorporating optimal substitution symbols.

[0056] Through the above steps S10-S40, the method of this embodiment can eliminate the defects existing in the prior art, thereby improving the cross-border translation effect of terms used by cross-border brands for overseas promotion.

[0057] Furthermore, to improve the translation effect, after step S40 above, the method of this embodiment further includes: S50: Dynamically update the cultural semantic field.

[0058] Specifically, the cultural semantic field embedding is updated via a sliding window using real-time interaction data from user-generated content (UGC) and social media:

[0059] In the formula, express The cultural semantic field is constantly updated; express The cultural semantic field of time; This represents the forgetting factor, used to control the proportion of historical information retained. This represents the encoding function, used to encode... Real-time interactive data collected at all times Convert to a semantic vector.

[0060] Through the above step S50, the method of this embodiment has a dynamically updated cultural semantic field. Compared with the existing technology based on a static rule base, the method of this embodiment is more adaptable to network traffic hotspots.

[0061] Furthermore, to further improve the accuracy of the paraphrasing in this embodiment, after step S40 above, the method further includes: S60: Map the paraphrased text back to the semantic space.

[0062] S70: Calculate the sum of distances between the paraphrased texts of different target language versions in the shared semantic space as the consistency loss.

[0063] The algorithmic expression for calculating the consistency loss is as follows:

[0064] In the formula, This indicates a loss of consistency. Indicates the summation symbol; Cultural index numbers representing two different languages; This represents a cross-linguistic projection function used to map vectors from different cultures to the same shared alignment space, ensuring that brand value remains consistent throughout its evolution. Indicate target brand In the Semantic vectors in a cultural context; Indicate target brand In the Semantic vectors within a cultural context.

[0065] For example, Nike, in American culture, If it can be [Action, Individualism, Achievement], then the semantic vector (i.e., the vector representation of the paraphrased text) generated using steps S10-S40 above will be used in China. It can be associated with [striving, making progress, and winning].

[0066] S80: If the consistency loss exceeds the preset threshold, return to step S10.

[0067] The technical advantages of the method in this embodiment, which differs from existing technologies, are as follows:

[0068] Furthermore, after the above-mentioned paraphrased text is generated, when the target brand generates the corresponding commercial advertisement, the video clips, audio, and the above-mentioned paraphrased text can be multimodally segmented and encoded, and then multimodal highlight synthesis can be performed using the Chinese patent technology with announcement number CN120321474B to output a highlight-mixed commercial advertisement short film with paraphrased text.

[0069] Example 2 like Figure 2 As shown, this embodiment discloses a semantic field reconstruction and emotional transfer translation system for cross-cultural marketing, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the semantic field reconstruction and emotional transfer translation method for cross-cultural marketing described in Embodiment 1 is implemented.

[0070] The system in this embodiment also includes other components well known to those skilled in the art, such as communication interfaces. Their settings and functions are known in the art, and therefore will not be described in detail here.

[0071] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented using computer-readable / executable instructions that can be stored or otherwise maintained by such a computer-readable medium.

[0072] In the description of this specification, "multiple" means at least two, such as two, three or more, etc., unless otherwise expressly and specifically defined.

[0073] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.

Claims

1. A semantic field reconstruction and emotional transfer translation method for cross-cultural marketing, characterized in that, include: Establish the cultural semantic field of the target brand and define the value invariants of the target brand based on the cultural semantic field; In response to the input of source content for the target brand, a preset sentiment transfer operator is used to map the source content to obtain the target sentiment vector; Based on a preset metaphor decoupling encoder and functional alignment reconstructor, the source cultural symbols in the source content are decoupled and functionally reconstructed to obtain the best replacement symbols for the source cultural symbols. Based on the value invariants, the target sentiment vector, and the optimal replacement symbol, a semantically translated text in the target cultural context is generated through semantic splicing. Establishing a multilingual cultural semantic field, including: Construct a cross-cultural corpus covering languages ​​from multiple regions; A contrastive learning method was used to extract cultural semantic fields representing the target brand in different cultures from the cross-cultural corpus. The metaphorical decoupling encoder is configured to perform the following steps: Establish a vector representation mapping for the source cultural symbols; The source cultural symbols are decomposed into surface-level formal feature components and deep-level functional feature components; The function alignment refactorer is configured to perform the following steps: Receive the deep functional feature components; In the symbol library of the target culture, the similarity between the functional feature components of candidate symbols and the deep functional feature components is calculated; The candidate symbol with the highest similarity is selected as the best replacement symbol; Among them, value invariants serve as semantic anchors, target sentiment vectors serve as style controllers, and optimal substitution symbols serve as mandatory keywords. Together, these three elements guide the natural language processing model to generate interpretive text that incorporates optimal substitution symbols.

2. The semantic field reconstruction and emotional transfer translation method for cross-cultural marketing according to claim 1, characterized in that, Based on the aforementioned cultural semantic field, the value invariants of the target brand are defined, including: Identify the common intersection region of multiple languages ​​in the cultural semantic field; Calculate the Euclidean distance between each semantic vector within the common intersection region and the original brand core value vector; The semantic vector that minimizes the Euclidean distance is selected as the value invariant.

3. The semantic field reconstruction and emotional transfer translation method for cross-cultural marketing according to claim 2, characterized in that, The specific algorithm for selecting the semantic vector that minimizes the Euclidean distance as the value invariant is as follows: In the formula, Representing value invariants, This represents taking the value of the variable that minimizes the objective function. This represents the semantic vectors within the common intersection region. This represents the original brand's core value vector. Indicates the first The cultural semantic field of a language This indicates the common intersection area. This represents the Euclidean norm.

4. The semantic field reconstruction and emotional transfer translation method for cross-cultural marketing according to claim 1, characterized in that, The source content is mapped using a preset sentiment transfer operator, including: Based on the emotional expression bases of the source culture and the target culture, a cross-cultural emotional transfer matrix is ​​constructed as the emotional transfer operator.

5. The semantic field reconstruction and emotional transfer translation method for cross-cultural marketing according to claim 1, characterized in that, After generating the paraphrased text in the target cultural context, the method further includes: Map the paraphrased text back to the semantic space; The sum of distances between the paraphrased texts of different target language versions in the shared semantic space is calculated as the consistency loss; If the consistency loss exceeds a preset threshold, then return to the step of establishing the cultural semantic field of the target brand.

6. The semantic field reconstruction and emotional transfer translation method for cross-cultural marketing according to claim 1, characterized in that, Based on the aforementioned value invariants, the target sentiment vector, and the optimal replacement symbol, a semantically translated text within the target cultural context is generated through semantic concatenation, specifically as follows: The value invariant, the target sentiment vector, and the optimal replacement symbol are input into a deep learning-based natural language processing model for semantic concatenation to obtain the paraphrased text.

7. A semantic field reconstruction and emotional transfer translation system for cross-cultural marketing, characterized in that, It includes a processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement the semantic field reconstruction and emotional transfer translation method for cross-cultural marketing as described in any one of claims 1-6.

Images