Customer service interface docking management system

Abstract

The invention relates to the technical field of interface management, and discloses a customer service interface docking management system which comprises the following steps: acquiring a first dialogue text within a first preset time period; preprocessing the first dialogue text and mapping the first dialogue text to a word vector space to obtain a text vector; determining a logic entity of the to-be-integrated system, and taking a database table corresponding to the logic entity as a real label; training based on the real sample and the text vector to obtain an adversarial network model; within a second preset time period, extracting a generator and a discriminator of the confrontation generation model; translating the target dialogue text based on the generator to obtain translation data of the integrated system; constructing a rule mapping processing unit based on the second dialogue text and the translation database table; and reversely optimizing the mapping relation of the rule mapping processing unit based on the discriminator.

Description

Technical Field

[0001] The present invention relates to the technical field of interface management, and more specifically, to a customer service interface docking management system. Background Art

[0002] In the intelligent customer service system, the conversations between customer service and users often contain rich information. With the expansion of platform business, intelligent customer service needs to be integrated with various business systems to fully mine and store diverse data. Traditional system integration solutions usually rely on a dedicated system docking team to develop docking interfaces to achieve system integration, making the system docking cost high.

[0003] The publication number is CN102982419B, which discloses an integrated interface for a form management information system, including three types of interface modules: single sign-on and page jump, interface call, and data access and push. It can avoid re-login and jump to the page, making operation convenient. It can initiate cross-system business processes in the system, and data can be updated and circulated in a timely manner. After transformation, it can achieve seamless connection with the production information system, the two-ticket expert system and the mobile terminal, so as to achieve system data sharing, collaborative management and process integration.

[0004] The integration interface of the form information management system integrates multiple systems through the interface. However, if new business systems are generated and integrated again with the expansion of business systems, the integration interface is difficult to adapt to the integration of business systems, resulting in integration difficulties. Summary of the invention

[0005] The present invention provides a customer service interface docking management system to solve the technical problems raised in the background technology.

[0006] The present invention provides a customer service interface docking management system, comprising: The data acquisition module is used to obtain the first dialogue text within a first preset time period; and map the first dialogue text to a word vector space after preprocessing to obtain a text vector; The adversarial generation module is used to determine the logical entities of the system to be integrated and use the database table corresponding to the logical entity as the real label; the adversarial network model is trained based on real samples and text vectors; The translation management module is used to obtain the second dialogue text within a second preset time period and perform a translation operation on the second dialogue text, including: Extract the generator and discriminator of the adversarial generative model; Performing translation on the target dialogue text based on the generator to obtain translation data of the integrated system; Based on the second dialogue text and the translation database table, construct a rule mapping processing unit; A mapping relationship of a processing unit based on a reverse optimization rule mapping of a discriminator; The mapping management module is used to obtain a third dialogue text within a third preset time period and perform a translation operation on the third dialogue text, including: The third dialogue text is classified into regular text and irregular text; If it is a regular text, the third dialogue text is translated based on the mapping processing unit; If it is a non-regular text, the third dialogue text is translated based on the generator.

[0007] Further, the first conversation text is preprocessed and mapped to a word vector space to obtain a text vector; The preprocessing includes: text cleaning to remove special characters, punctuation marks and stop words in the first dialogue text to obtain a preprocessed text of the first dialogue text; Map the preprocessed text to the word vector space to obtain the initial text vector; The initial text vector is convolved based on a one-dimensional convolutional neural network to obtain a text vector.

[0008] Furthermore, an adversarial network model is trained based on real samples and text vectors; The adversarial network model includes: generator and discriminator; Input the text vector into the generator to obtain the translation database table, and input the true label into the discriminator to make a true probability judgment for the translation database table; If there are P consecutive times where the absolute difference between the mean of the true probability and the preset convergence threshold is less than or equal to the preset difference threshold, the training converges and the adversarial network model is obtained.

[0009] Furthermore, based on the second dialogue text and the translation database table, a rule mapping processing unit is constructed, including: After preprocessing the second dialogue text, segment the preprocessed text based on a Chinese word segmentation tool to obtain M word segmentation fields; Extract and translate N field values ​​from the database table; Establish a mapping relationship between M word segmentation fields and N field values, including: Initialize and generate a mapping scheme that meets the constraint conditions; wherein the mapping scheme includes a mapping relationship between each field value and a number of word segmentation fields; The constraints include: each field value has a mapping relationship with at least one word segmentation field, each field value has a mapping relationship with at most M word segmentation fields, and each field value has and can only have one mapping relationship with each word segmentation field; A rule mapping processing unit is constructed based on the mapping scheme.

[0010] Further, the mapping relationship of the rule mapping processing unit is reversely optimized based on the discriminator, including determining the score of the rule mapping processing unit, as follows: Generate a corresponding rule translation database table for the second dialogue text based on the rule mapping processing unit; The discriminator based on the adversarial network model determines the true probability of the rule translation database table; The absolute difference between the true probability and the preset convergence threshold is used as the score of the rule mapping processing unit; If the absolute difference between the score and the preset convergence threshold is greater than the preset difference threshold, the mapping relationship of the mapping scheme is updated based on the gradient descent method until the absolute difference between the score and the preset convergence threshold is less than or equal to the preset difference threshold.

[0011] Further, the third dialogue text is classified into regular text and irregular text, including: If the absolute difference between the score of the rule mapping processing unit and the preset convergence threshold is less than or equal to the preset difference threshold, the corresponding second dialogue text is used as the rule text; Preprocessing, word segmentation and part-of-speech tagging of the second dialogue text and the third dialogue text; The part-of-speech tagging obtains the part-of-speech of each word segmentation field corresponding to the second dialogue text and the third dialogue text based on a part-of-speech tagging tool; Based on the position order of the word segmentation fields in the second dialogue text and the third dialogue text, respectively construct corresponding part-of-speech sequences; wherein the i-th unit of the part-of-speech sequence represents the part-of-speech of the i-th word segmentation field in the second dialogue text or the third dialogue text; Calculate the similarity value of the corresponding part-of-speech sequence, specifically including: Loading a sliding extraction window to convert the part-of-speech sequence into a convolution sequence with a dimension of H; wherein the length of the sliding extraction window is dynamically set based on the dimension of the part-of-speech sequence; Calculate the similarity value of the part-of-speech combination of the h-th unit in the corresponding convolution sequence respectively; wherein the part-of-speech combination is extracted from the part-of-speech sequence based on the sliding extraction window; If the similarity value is greater than or equal to a preset similarity threshold, the third dialogue text is classified as a regular text; otherwise, the third dialogue text is classified as an irregular text.

[0012] Furthermore, the similarity value of the part-of-speech combination of the h-th unit in the corresponding convolution sequence is calculated, including: ; Where, 1≤h≤H, h is a positive integer, Represents the similarity value of part-of-speech sequence, represents the number of parts of speech in the part-of-speech combination of the hth unit in the convolution sequence corresponding to the second dialogue text, represents the number of parts of speech in the part-of-speech combination of the hth unit in the convolution sequence corresponding to the third dialogue text, Indicates the number of parts of speech that are the same in the h-th unit's part of speech combination in the convolution sequence corresponding to the second dialogue text and the h-th unit's part of speech combination in the convolution sequence corresponding to the third dialogue text.

[0013] Furthermore, the word vector space is the Word2Ve word vector space.

[0014] The beneficial effects of the present invention are: 1. Through the dual interface management solutions of rule mapping translation and generator dynamic translation, an intelligent docking mechanism covering all scenarios is constructed. For the standardized text (rule text) that appears frequently in customer service conversations, the system relies on the pre-trained rule mapping processing unit to achieve rapid translation based on the mapping relationship between historical conversation word segmentation and business database fields, significantly improving the efficiency of standardized interface docking; and for non-regular texts with complex sentences and changeable semantics, the system dynamically generates adaptation data through the generator of the adversarial generation module, and uses the model generalization ability to solve docking problems. With the dual strategy of rule priority and model guarantee, the customer service interface docking management system can not only efficiently handle repetitive scenarios through solidified rules, but also flexibly respond to personalized needs with the help of generation models, providing a more universal docking management solution for multi-business system integration.

[0015] 2. In the customer service interface docking management system, the generator and discriminator of the adversarial network are creatively decoupled and used in collaboration to build a rule system: the generator generates a data table structure that fits the business system based on the conversation text vector, providing an initial mapping target for the interface docking; the discriminator uses the real business database table as a label, reversely evaluates the accuracy of the rule mapping, and dynamically optimizes the mapping relationship between the word segmentation field and the database field through gradient descent. Through the closed-loop mechanism of "generation-discrimination-optimization", the system can automatically learn the mapping rules between customer service conversation text and business data without relying on manual processing of preset rules, and build a highly adaptive rule mapping processing unit. Compared with the single generation function of the traditional adversarial network, this design gives the customer service interface docking management system the dual capabilities of "rule self-construction" and "dynamic optimization", which not only greatly reduces the cost of manual configuration, but also realizes the precise structured conversion from conversation text to business data through the deep integration of models and rules. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a module diagram of a customer service interface docking management system of the present invention. DETAILED DESCRIPTION

[0017] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the contents of this specification. Each example may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0018] like Figure 1 As shown, a customer service interface docking management system includes: The data acquisition module is used to obtain the first dialogue text within a first preset time period; and map the first dialogue text to a word vector space after preprocessing to obtain a text vector; The adversarial generation module is used to determine the logical entities of the system to be integrated and use the database table corresponding to the logical entity as the real label; the adversarial network model is trained based on real samples and text vectors; The translation management module is used to obtain the second dialogue text within a second preset time period and perform a translation operation on the second dialogue text, including: Extract the generator and discriminator of the adversarial generative model; Perform translation on the target dialogue text based on the generator to obtain translation data of the integrated system; Based on the second dialogue text and the translation database table, construct a rule mapping processing unit; Mapping relationship of processing units based on discriminator reverse optimization rule mapping; The mapping management module is used to obtain a third dialogue text within a third preset time period and perform a translation operation on the third dialogue text, including: The third dialogue text is classified into regular text and irregular text; If it is a regular text, the third dialogue text is translated based on the mapping processing unit; If it is a non-regular text, the third dialogue text is translated based on the generator.

[0019] It should be noted that the system to be integrated refers to the business system to be integrated into the customer service system. Among them, the logical entity refers to the abstract data model used to describe the core business objects in the system to be integrated, which usually corresponds to a table in the database. For example, if the system to be integrated is an e-commerce order system, the logical entity includes: order entity or logistics entity; further, the order entity corresponds to the database table order_info, and the logistics entity corresponds to the database table logistics_info.

[0020] In one embodiment of the present invention, the first dialogue text is preprocessed and mapped to a word vector space to obtain a text vector. The preprocessing includes: text cleaning to remove special characters, punctuation marks, and stop words in the first dialogue text to obtain a preprocessed text of the first dialogue text. The preprocessed text is mapped to a word vector space to obtain an initial text vector. Based on a one-dimensional convolutional neural network, convolutional processing is performed on the initial text vector to obtain a text vector.

[0021] It should be noted that text cleaning is used to remove invalid information in the original dialogue text, retain the core semantic content, and reduce the interference of noise on subsequent semantic analysis. Specifically, it includes: matching and removing non-semantic characters such as emoticons, format control characters, and illegal characters (such as "@#￥%") in the dialogue text through regular expressions; deleting punctuation marks such as full stops, commas, question marks, and exclamation marks (for example, converting "When will my order arrive?" to "When will my order arrive") to eliminate the impact of punctuation on the accuracy of word segmentation; based on a predefined stop word list (such as high-frequency meaningless words like "of", "already", "in", "excuse me", etc.), filtering stop words in the text through the dictionary matching method. For example, cleaning "Hello, excuse me, what is the status of my order?" to "order status" and retaining the core keywords. Technical value: Through standardized cleaning, the original dialogue text is converted into a "pure text" containing only valid semantic words, providing high-quality input for subsequent word segmentation and semantic representation.

[0022] It should be noted that the one-dimensional convolutional neural network processing is used to extract local semantic features and context dependencies in the text through convolutional operations, generating a text vector containing deep semantic information, including: Taking the initial text vector sequence as the input of the one-dimensional convolutional neural network, whose dimension is [number of samples × sequence length × word vector dimension]; using convolutional kernels with multiple different window sizes (such as window sizes 3, 5, and 7) to perform sliding convolution on the input vector to extract n-gram level semantic features (for example, a window size of 3 can capture the combined semantics of 3 consecutive words, such as "status query" in "order status query"); introducing a non-linear transformation through the ReLU activation function, and then compressing the feature dimension through a pooling layer (such as max pooling). Finally, the feature vectors output by each convolutional kernel are concatenated to generate a text vector with a fixed dimension (such as a vector with a dimension of 300). This vector contains the local semantic features and global context information of the text. Different from the traditional method that only uses the average of word vectors, the one-dimensional convolutional neural network can automatically capture the combined semantics between words (such as "logistics exception" as an overall semantic unit), improving the semantic representation ability of the text vector and providing more effective input features for the subsequent adversarial generation module.

[0023] In one embodiment of the present invention, an adversarial network model is obtained by training based on real samples and text vectors; The adversarial network model includes: generator and discriminator; Input the text vector into the generator to obtain the translation database table, and input the true label into the discriminator to make a true probability judgment for the translation database table; If there are P consecutive times where the absolute difference between the mean of the true probability and the preset convergence threshold is less than or equal to the preset difference threshold, the training converges and the adversarial network model is obtained.

[0024] It should be noted that, within the first preset time period, a plurality of first conversation texts are obtained, so as to construct enough text vectors as the input of the generator.

[0025] It should be noted that the adversarial network model architecture includes a generator and a discriminator.

[0026] The input of the generator is the text vector output by the data acquisition module, and the output is the "translation database table", that is, the structured data generated based on the text vector and corresponding to the logical entity of the system to be integrated.

[0027] Generator goal: By learning the mapping relationship between text vectors and the real database table structure, generate a translation database table that is as close to the real label as possible, so that the real probability output by the discriminator is close to 1.

[0028] Discriminator: The input is the "real label" (that is, the real database table structure corresponding to the logical entity of the system to be integrated, such as the original table fields and data format of the order management system) and the "translated database table" output by the generator. The output is a probability value ranging from 0 to 1, indicating the discriminator's confidence in whether the input table structure "belongs to the real business system data".

[0029] The discriminator's goal is to accurately distinguish the true label from the translation table output by the generator, output a high probability (close to 1) for the true label, and a low probability (close to 0) for the generated table.

[0030] The generator receives the text vector and outputs the translation database table. The discriminator receives the true label and the translation database table at the same time and outputs the corresponding true probability.

[0031] The loss function includes generator loss and discriminator loss: Generator loss: The probability of misjudgment of the generated table by the discriminator is maximized through gradient ascent. represents the generator loss, represents the true probability of translating the database table, Represents the translation database table, Represents the operation of finding the expected true probability of all translated database tables, which is used to statistically average the true probabilities to measure the performance of the model on the overall data distribution.

[0032] Discriminator loss: Minimize the probability of misjudgment of the true label and the probability of omission of the generated table through gradient descent. represents the discriminator loss, represents the true probability of the true label, represents the true label.

[0033] Alternating optimization: The generator and the discriminator update their parameters alternately according to preset rounds, forming an adversarial training cycle of "generation-discrimination-feedback".

[0034] Training convergence conditions, including preset convergence threshold, preset difference threshold and number of consecutive times. Preset convergence threshold θ: represents the expected true probability of the discriminator for the true label. For example, if it is set to 0.95, it means that the expected probability of the discriminator for the true label is not less than 95%. Preset difference threshold : indicates the maximum deviation allowed between the true probability mean and the preset convergence threshold (such as 0.01). Number of consecutive times P: indicates the number of consecutive valid training rounds used to judge convergence. For example, P=10, that is, 10 consecutive training rounds that meet the conditions are considered to be converged. Calculate the true probability mean Q of the discriminator pair generated table in consecutive P training rounds. If it meets , it is considered that the distribution difference between the translation table output by the generator and the true label has been narrowed to an acceptable range, the training process is terminated, and the final adversarial network model is obtained.

[0035] In one embodiment of the present invention, a rule mapping processing unit is constructed based on the second dialogue text and the translation database table, including: After preprocessing the second dialogue text, the preprocessed text is segmented based on a Chinese word segmentation tool to obtain M segmentation fields; Extract and translate N field values ​​from the database table; Establish a mapping relationship between M word segmentation fields and N field values, including: Initialize and generate a mapping scheme that meets the constraint conditions; wherein the mapping scheme includes a mapping relationship between each field value and a number of word segmentation fields; The constraints include: each field value has a mapping relationship with at least one word segmentation field, each field value has a mapping relationship with at most M word segmentation fields, and each field value has and can only have one mapping relationship with each word segmentation field; A rule mapping processing unit is constructed based on the mapping scheme.

[0036] It should be noted that the preprocessed text is segmented using Chinese word segmentation tools, including but not limited to: jieba, THULAC and other Chinese word segmentation tools, to split it into M independent word segmentation fields. For example, for the sentence "query the logistics status of order 123", after word segmentation, M word segmentation fields such as "query", "order", "123", "logistics", and "status" may be obtained.

[0037] Extract N field values ​​from the translation database table. The translation database table is structured data corresponding to the logical entity of the system to be integrated, generated by the generator in the adversarial network model based on the text vector. For example, the order_id of the order table has a corresponding field value of 123, which means the 123rd order.

[0038] Generate an initial mapping scheme according to specific constraints. The mapping scheme describes the correspondence between each field value and several word segmentation fields. Among them, each field value has a mapping relationship with at least one word segmentation field: ensure that each field value in the translation database table can find the corresponding semantic information source from the second dialogue text to ensure the integrity of the mapping. For example, the order_id field value must be mapped with at least one of the word segmentation fields such as order, 123, etc., otherwise the field value will have no corresponding information in the dialogue. Each field value has a mapping relationship with at most M word segmentation fields, which is used to limit the number of word segmentation fields associated with a field value, and to avoid confusion in the mapping relationship caused by excessive association. Each field value and each word segmentation field can only have one and only one mapping relationship, which is used to ensure the uniqueness of the mapping, avoid multiple conflicting mappings for a field value or word segmentation field, and ensure the accuracy and certainty of the mapping relationship.

[0039] A rule mapping processing unit is constructed based on the generated mapping scheme. This unit will serve as a core component. In the subsequent customer service interface docking process, it can accurately convert the natural language information in the customer service dialogue into structured data that can be recognized by the business system according to the established mapping relationship, thereby achieving efficient interface docking.

[0040] In one embodiment of the present invention, the mapping relationship of the rule mapping processing unit is reversely optimized based on the discriminator, including determining the score of the rule mapping processing unit as follows: Generate a corresponding rule translation database table for the second dialogue text based on the rule mapping processing unit; The discriminator based on the adversarial network model determines the true probability of the rule translation database table; The absolute difference between the true probability and the preset convergence threshold is used as the score of the rule mapping processing unit; If the absolute difference between the score and the preset convergence threshold is greater than the preset difference threshold, the mapping relationship of the mapping scheme is updated based on the gradient descent method until the absolute difference between the score and the preset convergence threshold is less than or equal to the preset difference threshold.

[0041] It should be noted that the generation of the rule translation database table includes: Input: the second dialogue text (M segmentation fields after preprocessing and segmentation) and the current mapping scheme of the rule mapping processing unit (the correspondence between the segmentation fields and the database fields); Output: rule translation database table (structured data), that is, according to the mapping scheme, the word segmentation field in the conversation text is mapped to N field values ​​in the translation database table to form a data table structure that can be recognized by the business system. For example, in the order query scenario, "Order 123" is mapped to order_id=123.

[0042] Based on the correspondence between "segmentation fields and field values" in the mapping scheme, valid information in the conversation text is extracted and filled into the corresponding fields of the translation database table to realize the conversion of natural language text into structured data.

[0043] The discriminator trained by the adversarial network model is used to evaluate the authenticity of the generated rule translation database table, and the matching probability (value range [0, 1]) between the table and the real database table (real label) of the system to be integrated is output, that is, the real probability. This probability reflects the degree of consistency between the rule translation table and the real table in terms of field composition, data format, business constraints, etc. (such as no missing fields, correct data types, and compliance with business logic rules).

[0044] The score is determined by the absolute difference between the true probability and the preset convergence threshold (denoted as θ, such as 0.95), that is: The smaller the score, the higher the matching degree between the rule translation table and the real table, and the better the performance of the rule mapping processing unit.

[0045] If the score is greater than the preset difference threshold (denoted as , such as 0.01), that is , indicating that the difference between the rule translation table generated by the current mapping scheme and the real table exceeds the acceptable range, and the mapping relationship needs to be optimized.

[0046] In one embodiment of the present invention, the mapping relationship of the mapping scheme is updated based on the gradient descent method, including: initializing the association weight of each field value and M word segmentation fields, the association weight value is 0 to 1, and establishing a mapping relationship between the association weight greater than or equal to the preset association threshold and the field value. The gradient of the score to the association weight is calculated by the gradient descent method to adjust the mapping parameters in the opposite direction of the gradient, and dynamically update the association weight of the word segmentation field and the field value.

[0047] In one embodiment of the present invention, the third dialogue text is classified into regular text and irregular text, including: If the absolute difference between the score of the rule mapping processing unit and the preset convergence threshold is less than or equal to the preset difference threshold, the corresponding second dialogue text is used as the rule text; Preprocessing, word segmentation and part-of-speech tagging of the second dialogue text and the third dialogue text; The part-of-speech tagging obtains the part-of-speech of each word segmentation field corresponding to the second dialogue text and the third dialogue text based on a part-of-speech tagging tool; Based on the position order of the word segmentation fields in the second dialogue text and the third dialogue text, respectively construct corresponding part-of-speech sequences; wherein the i-th unit of the part-of-speech sequence represents the part-of-speech of the i-th word segmentation field in the second dialogue text or the third dialogue text; Calculate the similarity value of the corresponding part-of-speech sequence, specifically including: Loading a sliding extraction window to convert the part-of-speech sequence into a convolution sequence with a dimension of H; wherein the length of the sliding extraction window is dynamically set based on the dimension of the part-of-speech sequence; Calculate the similarity value of the part-of-speech combination of the h-th unit in the corresponding convolution sequence respectively; wherein the part-of-speech combination is extracted from the part-of-speech sequence based on the sliding extraction window; If the similarity value is greater than or equal to a preset similarity threshold, the third dialogue text is classified as a regular text; otherwise, the third dialogue text is classified as an irregular text.

[0048] In one embodiment of the present invention, calculating the similarity value of the part-of-speech combination of the hth unit in the corresponding convolution sequence includes: ; Where, 1≤h≤H, h is a positive integer, Represents the similarity value of part-of-speech sequence, represents the number of parts of speech in the part-of-speech combination of the hth unit in the convolution sequence corresponding to the second dialogue text, represents the number of parts of speech in the part-of-speech combination of the hth unit in the convolution sequence corresponding to the third dialogue text, Indicates the number of parts of speech that are the same in the h-th unit's part of speech combination in the convolution sequence corresponding to the second dialogue text and the h-th unit's part of speech combination in the convolution sequence corresponding to the third dialogue text.

[0049] In one embodiment of the present invention, a third dialogue text is obtained within a third preset time period, and the third dialogue text is compared with a regular text (such as the second dialogue text). If the similarity value is greater than or equal to a preset similarity threshold, the third dialogue text is also a regular text.

[0050] When the dialogue text is a regular text, the rule mapping processing unit is used as the interface of the integrated system to achieve the connection between the customer service system and the business system. When the dialogue text is an irregular text, the generator is used as the interface of the integrated system to achieve the connection between the customer service system and the business system.

[0051] In one embodiment of the present invention, the part-of-speech tagging tool includes but is not limited to jieba or HanLP. For example, the second dialogue text is "I want to check the order status", and the third dialogue text is "He wants to check the express delivery progress". Among them, "I" and "he" are usually marked as personal pronouns (such as "r"), "want" and "want" may be marked as modal verbs (such as "v"), "query" and "check" are verbs ("v"), "order" and "express delivery" are nouns ("n"), and "status" and "progress" are also nouns ("n"). Then the part-of-speech sequence of the second dialogue text is [r, v, v, n, n], and the part-of-speech sequence of the third dialogue text is [r, v, v, n, n].

[0052] In detail, part-of-speech sequences of different lengths (such as 8 and 10) cannot be directly compared based on fixed positions. By dynamically adjusting the sliding window length, they are unified into the same dimension H=6, so that the similarity between the two can be calculated under a consistent framework, avoiding comparison obstacles caused by different lengths.

[0053] The sliding window dynamically extracts local part-of-speech combinations and can adapt to the structural characteristics of sequences of different lengths. For example, the long sequence 10 can capture detailed features through a smaller window, and the short sequence 8 can ensure feature coverage through a larger window. Finally, under the dimension of H=6, the local structural patterns of the two are fully extracted and compared to explore potential similarities.

[0054] For example, the second dialogue text is "I go to school for class". After part-of-speech tagging, the part-of-speech sequence P2 is [r, v, n, v, n], with a length of 5. Set the sliding window length to 3 for sliding extraction. The resulting convolution sequence C2 includes: the first unit [r, v, n], the second unit: [v, n, v], and the third unit: [n, v, n].

[0055] The third dialogue text is "He came to the company", and the part-of-speech sequence P3 is [r, v, n, u], with a length of 4. The sliding window length of the third dialogue text is set to 2, and a certain overlap and integration are performed during extraction to obtain a convolution sequence of length 3. The obtained convolution sequence C3 includes: the first unit [r, v], the second unit: [v, n], and the third unit: [n, u]. Among them, u represents the part of speech of the auxiliary word.

[0056] Based on the formula, the similarity value of the first unit is 0.8, the similarity value of the second unit is 0.8, and the similarity value of the third unit is 0.8. The overall similarity value of the second dialogue text and the third dialogue text is 0.8. If the preset similarity threshold is 0.95, the third dialogue text is irregular text and needs to be translated by the generator. If the preset similarity threshold is 0.7, the third dialogue text is regular text and needs to be translated by the rule mapping processing unit.

[0057] In one embodiment of the present invention, the word vector space is a Word2Ve word vector space.

[0058] The above describes an embodiment of the present embodiment, but the present embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present embodiment, ordinary technicians in this field can also make many forms, all of which are within the protection of the present embodiment.

Claims

1. A customer service interface docking management system, characterized in that: include: A data acquisition module, used to obtain a first conversation text within a first preset time period; Map the first conversation text to the word vector space after preprocessing to obtain a text vector; The adversarial generation module is used to determine the logical entities of the system to be integrated and use the database tables corresponding to the logical entities as the true labels; The adversarial network model is trained based on real samples and text vectors; The translation management module is used to obtain the second dialogue text within a second preset time period and perform a translation operation on the second dialogue text, including: Extract the generator and discriminator of the adversarial generative model; Performing translation on the target dialogue text based on the generator to obtain translation data of the integrated system; Based on the second dialogue text and the translation database table, construct a rule mapping processing unit; Mapping relationship of processing units based on discriminator reverse optimization rule mapping; The mapping management module is used to obtain a third dialogue text within a third preset time period and perform a translation operation on the third dialogue text, including: The third dialogue text is classified into regular text and irregular text; If it is a regular text, the third dialogue text is translated based on the mapping processing unit; If it is a non-regular text, the third dialogue text is translated based on the generator.

2. A customer service interface docking management system according to claim 1, characterized in that: Map the first conversation text to the word vector space after preprocessing to obtain a text vector; The preprocessing includes: text cleaning to remove special characters, punctuation marks and stop words in the first dialogue text to obtain a preprocessed text of the first dialogue text; Map the preprocessed text to the word vector space to obtain the initial text vector; The initial text vector is convolved based on a one-dimensional convolutional neural network to obtain a text vector.

3. A customer service interface docking management system according to claim 2, characterized in that: The adversarial network model is trained based on real samples and text vectors; The adversarial network model includes: generator and discriminator; Input the text vector into the generator to obtain the translation database table, and input the true label into the discriminator to make a true probability judgment for the translation database table; If there are P consecutive times where the absolute difference between the mean of the true probability and the preset convergence threshold is less than or equal to the preset difference threshold, the training converges and the adversarial network model is obtained.

4. A customer service interface docking management system according to claim 3, characterized in that: Based on the second dialogue text and the translation database table, a rule mapping processing unit is constructed, including: After preprocessing the second dialogue text, segment the preprocessed text based on a Chinese word segmentation tool to obtain M segmentation fields; Extract and translate N field values ​​from the database table; Establish a mapping relationship between M word segmentation fields and N field values, including: Initialize and generate a mapping scheme that meets the constraint conditions; wherein the mapping scheme includes a mapping relationship between each field value and a number of word segmentation fields; The constraints include: each field value has a mapping relationship with at least one word segmentation field, each field value has a mapping relationship with at most M word segmentation fields, and each field value has and can only have one mapping relationship with each word segmentation field; A rule mapping processing unit is constructed based on the mapping scheme.

5. A customer service interface docking management system according to claim 4, characterized in that: The mapping relationship of the rule mapping processing unit is reversely optimized based on the discriminator, including determining the score of the rule mapping processing unit, as follows: Generate a corresponding rule translation database table for the second dialogue text based on the rule mapping processing unit; The discriminator based on the adversarial network model determines the true probability of the rule translation database table; The absolute difference between the true probability and the preset convergence threshold is used as the score of the rule mapping processing unit; If the absolute difference between the score and the preset convergence threshold is greater than the preset difference threshold, the mapping relationship of the mapping scheme is updated based on the gradient descent method until the absolute difference between the score and the preset convergence threshold is less than or equal to the preset difference threshold.

6. A customer service interface docking management system according to claim 5, characterized in that: The third dialogue text is classified into regular text and irregular text, including: If the absolute difference between the score of the rule mapping processing unit and the preset convergence threshold is less than or equal to the preset difference threshold, the corresponding second dialogue text is used as the rule text; Preprocessing, word segmentation and part-of-speech tagging of the second dialogue text and the third dialogue text; The part-of-speech tagging obtains the part-of-speech of each word segmentation field corresponding to the second dialogue text and the third dialogue text based on a part-of-speech tagging tool; Based on the position order of the word segmentation fields in the second dialogue text and the third dialogue text, respectively construct corresponding part-of-speech sequences; wherein the i-th unit of the part-of-speech sequence represents the part-of-speech of the i-th word segmentation field in the second dialogue text or the third dialogue text; Calculate the similarity value of the corresponding part-of-speech sequence, specifically including: Loading a sliding extraction window to convert the part-of-speech sequence into a convolution sequence with a dimension of H; wherein the length of the sliding extraction window is dynamically set based on the dimension of the part-of-speech sequence; Calculate the similarity value of the part-of-speech combination of the h-th unit in the corresponding convolution sequence respectively; wherein the part-of-speech combination is extracted from the part-of-speech sequence based on the sliding extraction window; If the similarity value is greater than or equal to a preset similarity threshold, the third dialogue text is classified as a regular text; otherwise, the third dialogue text is classified as an irregular text.

7. A customer service interface docking management system according to claim 6, characterized in that: Calculate the similarity value of the part-of-speech combination of the hth unit in the corresponding convolution sequence, including: ； Where, 1≤h≤H, h is a positive integer, Represents the similarity value of part-of-speech sequence, represents the number of parts of speech in the part-of-speech combination of the hth unit in the convolution sequence corresponding to the second dialogue text, represents the number of parts of speech in the part-of-speech combination of the hth unit in the convolution sequence corresponding to the third dialogue text, Indicates the number of parts of speech that are the same in the h-th unit's part of speech combination in the convolution sequence corresponding to the second dialogue text and the h-th unit's part of speech combination in the convolution sequence corresponding to the third dialogue text.

8. A customer service interface docking management system according to claim 7, characterized in that: The word vector space is Word2Ve word vector space.

Images