A process data automation system

Abstract

The application discloses a kind of flow data automatic processing systems, it is related to intelligent customer service processing technical field, including management center, the management center communication connection has user end, data input node, data processing node and reply content formulation node;By classifying the customer service demand information initiated by user, so as to extract corresponding semantic features according to different types of customer service demand information, and according to the semantic features extracted by information atlas determine the reply content corresponding to each semantic feature, so as to generate the customized reply content corresponding to the customer service demand information initiated by user, reduce irrelevant reply content generation, improve reply efficiency.

Description

Technical Field

[0001] This invention relates to the field of intelligent customer service processing technology, specifically a process data automation processing system. Background Technology

[0002] Against the backdrop of rapid development in internet and communication technologies, customer service demands have exploded. Traditional human customer service can no longer meet the dual needs of businesses and users, leading to the emergence of intelligent customer service data processing technology. Initially, intelligent customer service data processing focused on simple keyword matching. The system would identify keywords in the user's input text by setting rules, and then search for corresponding responses from a pre-set answer database.

[0003] How to generate more customized content based on users' customer service needs, reduce irrelevant replies, and thus improve the response efficiency of intelligent customer service is a problem we need to solve. To this end, we now provide a process data automation processing system. Summary of the Invention

[0004] The purpose of this invention is to provide an automated process data processing system.

[0005] The objective of this invention can be achieved through the following technical solution: an automated process data processing system, comprising a management center, wherein the management center is communicatively connected to a user terminal, a data input node, a data processing node, and a response content setting node;

[0006] The user terminal is used for users to input customer service request information;

[0007] The data input node is used to extract features from the customer service request information entered by the user to obtain corresponding candidate semantic features;

[0008] The data processing node is used to perform correlation filtering on the obtained candidate semantic features, and to perform rationality screening on the customer service request information entered by the user based on the correlation filtering results.

[0009] The response content setting node is used to set key response content and integrate the set key response content to obtain corresponding customized response content.

[0010] Furthermore, users can input customer service request information through the user terminal, which includes customer service inquiry information and customer service after-sales information;

[0011] Generate corresponding consultation tags based on the customer service consultation information entered by the user, generate corresponding after-sales tags based on the customer service after-sales information entered by the user, and associate consultation tags with the customer service consultation information entered by the user, and associate after-sales tags with the customer service after-sales information entered by the user.

[0012] Furthermore, the process by which the data input node extracts features from the customer service request information input by the user to obtain corresponding candidate semantic features includes:

[0013] Read the tags corresponding to the customer service request information entered by the user, and construct the corresponding blank semantic sequence based on the read tags;

[0014] Among them, the blank semantic sequence corresponding to the consultation tag consists of product fragments and demand fragments; the blank semantic sequence corresponding to the after-sales tag consists of demand fragments and time fragments.

[0015] Set up a standard semantic feature library, and build semantic terms associated with each product in the product list and semantic terms associated with after-sales items within the standard semantic feature library;

[0016] When the user inputs customer service consultation information, extract the semantic features from the customer service consultation information;

[0017] The extracted semantic features are matched with the semantic terms associated with each product in the product list. If any semantic feature matches any semantic term associated with any product, the corresponding semantic feature is bound to the blank semantic sequence corresponding to that product and recorded as a candidate semantic feature.

[0018] Furthermore, when the user inputs customer service after-sales information, the semantic features associated with the after-sales items corresponding to the product selected by the user are extracted from the customer service after-sales information. The extracted semantic features are then matched with the semantic terms associated with each after-sales item. If any semantic feature matches the semantic term associated with the after-sales item, the corresponding semantic feature is bound to the blank semantic sequence corresponding to the product and recorded as a candidate semantic feature.

[0019] Furthermore, the data processing node performs correlation filtering on the obtained semantic features, and the process of screening the reasonableness of the customer service request information entered by the user based on the correlation filtering results includes:

[0020] When the user inputs customer service consultation information, the obtained candidate semantic features are marked respectively, and the semantic terms that match the marked candidate semantic features are summarized. Then, the semantic terms are divided into sub-separations according to the products associated with each semantic term to obtain the semantic feature subsets corresponding to each product.

[0021] Obtain the number of candidate semantic features within each semantic feature subset, and select the product with the most candidate semantic features as the target product for user consultation;

[0022] Candidate semantic features that match the semantic terms corresponding to the target product consulted by the user are marked as relevance semantic features;

[0023] The relevance semantic features are mapped to the demand fragments within the blank semantic sequence, and the user's target product is imported into the product fragment to obtain the consultation semantic fragment.

[0024] Furthermore, when the user inputs customer service after-sales information, the obtained candidate semantic features are marked respectively, and the semantic terms that match the marked candidate semantic features are summarized. Then, the semantic terms are divided into secondary categories according to the after-sales items associated with each semantic term to obtain a semantic feature subset corresponding to each after-sales item. The candidate semantic features in each semantic feature subset are associated with the corresponding after-sales item.

[0025] Import the candidate semantic features from the subset of semantic features associated with the after-sales project into the requirement segment in the blank semantic sequence, and simultaneously import the time when the user inputs customer service after-sales information into the time segment to obtain the after-sales semantic segment;

[0026] Match the time within the time segment with the corresponding after-sales time for the after-sales project. If the time falls within the after-sales time, the corresponding after-sales project is considered reasonable; otherwise, it is considered unreasonable, and the corresponding after-sales project is marked as an overdue project.

[0027] Furthermore, the process of defining key response content at the response content definition node, and integrating the defined key response content to obtain corresponding customized response content, includes:

[0028] An information database is set up, which includes information entries associated with each product and its corresponding after-sales items;

[0029] Construct corresponding information graphs based on information terms within the information database;

[0030] When a user inputs customer service inquiry information, the semantic fragment of the inquiry is input into the constructed information graph;

[0031] Read the user's target product in the consultation semantic fragment and determine the secondary consultation knowledge node corresponding to the user's target product;

[0032] Obtain the semantic features of each semantic fragment in the consultation, match each semantic feature with the information terms in each third-level consultation knowledge node in the information graph, and summarize the information terms associated with the matched third-level consultation knowledge nodes to obtain the response term set;

[0033] When the user inputs customer service and after-sales information, the after-sales semantic fragments are input into the constructed information graph;

[0034] Based on the product selected by the user, determine the corresponding secondary after-sales knowledge node for that product;

[0035] Obtain the semantic features of each semantic segment in the after-sales semantic segment, match each semantic feature with the information terms in each third-level after-sales knowledge node in the information graph, and summarize the information terms associated with the matched third-level after-sales knowledge nodes to obtain the response term set;

[0036] After integrating the various information entries within the obtained set of response terms, corresponding customized customer service responses are obtained.

[0037] Furthermore, the construction process of the information graph includes:

[0038] Based on the consultation tags and after-sales tags, construct corresponding first-level consultation knowledge nodes and first-level after-sales knowledge nodes respectively;

[0039] Construct corresponding secondary consultation knowledge nodes and secondary after-sales knowledge nodes for each product in the product list;

[0040] Based on the semantic terms associated with each product, construct tertiary consultation knowledge nodes that are associated with the secondary consultation knowledge nodes. Each tertiary consultation knowledge node corresponds to a semantic term, and associate each tertiary consultation knowledge node with a corresponding information term.

[0041] Based on semantic terms related to each after-sales project, construct tertiary after-sales knowledge nodes that are associated with secondary after-sales knowledge nodes. Each tertiary after-sales knowledge node corresponds to a semantic term, and associates a corresponding information term with each tertiary after-sales knowledge node.

[0042] Compared with the prior art, the beneficial effects of the present invention are:

[0043] By classifying customer service requests initiated by users, corresponding semantic features are extracted based on different types of customer service requests. Then, based on the extracted semantic features, information graphs are used to determine the corresponding response content for each semantic feature. This generates customized response content that corresponds to the customer service requests initiated by users, reduces the generation of irrelevant response content, and improves response efficiency. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0045] Figure 1This is a schematic diagram of the present invention. Detailed Implementation

[0046] like Figure 1 As shown, an automated process data processing system includes a management center, which is communicatively connected to a user terminal, a data input node, a data processing node, and a response content specification node.

[0047] The user terminal is used for users to input customer service request information;

[0048] The data input node is used to extract features from the customer service request information entered by the user to obtain corresponding candidate semantic features;

[0049] The data processing node is used to perform correlation filtering on the obtained candidate semantic features, and to perform rationality screening on the customer service request information entered by the user based on the correlation filtering results.

[0050] The response content setting node is used to set key response content and integrate the set key response content to obtain corresponding customized response content.

[0051] It should be further explained that users input customer service request information through the user terminal, which includes customer service inquiry information and customer service after-sales information;

[0052] In practice, customer service inquiry information refers to inquiries made by users before purchasing any goods; after-sales customer service information refers to inquiries made by users after purchasing at least one item, based on the purchased item.

[0053] Generate corresponding consultation tags based on the customer service consultation information entered by the user, generate corresponding after-sales tags based on the customer service after-sales information entered by the user, associate consultation tags with the customer service consultation information entered by the user, and associate after-sales tags with the customer service after-sales information entered by the user.

[0054] Users can send customer service inquiries directly through the user client. Users need to select at least one purchased item to send customer service after-sales information.

[0055] It should be further explained that the process by which the data input node extracts features from the customer service request information entered by the user to obtain the corresponding candidate semantic features includes:

[0056] Read the tags corresponding to the customer service request information entered by the user, and construct the corresponding blank semantic sequence based on the read tags;

[0057] Among them, the blank semantic sequence corresponding to the consultation tag consists of product fragments and demand fragments; the blank semantic sequence corresponding to the after-sales tag consists of demand fragments and time fragments.

[0058] Set up a standard semantic feature library, and build semantic terms associated with each product in the product list and semantic terms associated with after-sales items within the standard semantic feature library;

[0059] When the user inputs customer service consultation information, extract the semantic features from the customer service consultation information;

[0060] The extracted semantic features are matched with the semantic terms associated with each product in the product list. If any semantic feature matches any semantic term associated with any product, the corresponding semantic feature is bound to the blank semantic sequence corresponding to that product and recorded as a candidate semantic feature.

[0061] When the user inputs customer service after-sales information, extract the semantic features associated with the after-sales items corresponding to the product selected by the user from the customer service after-sales information, and match the extracted semantic features with the semantic terms associated with each after-sales item. If any semantic feature matches the semantic term associated with the after-sales item, then bind the corresponding semantic feature with the blank semantic sequence corresponding to the product, and record it as a candidate semantic feature.

[0062] It should be further explained that the process by which the data processing node performs correlation filtering on the obtained semantic features, and then performs reasonableness screening on the customer service request information entered by the user based on the correlation filtering results, includes:

[0063] When the user inputs customer service consultation information, the obtained candidate semantic features are marked respectively, and the semantic terms that match the marked candidate semantic features are summarized. Then, the semantic terms are divided into sub-separations according to the products associated with each semantic term to obtain the semantic feature subsets corresponding to each product.

[0064] Obtain the number of candidate semantic features in each semantic feature subset, and select the product with the most candidate semantic features as the user's consultation target product; it should be noted that if there are multiple semantic feature subsets with the same number of candidate semantic features and the most, then generate the corresponding intention product options and send the intention product options to the user terminal, and after the user makes a selection, the selected product will be the user's consultation target product.

[0065] Selectable semantic features that match the semantic terms corresponding to the target product consulted by the user are marked as relevant semantic features, and other selectable semantic features are marked as unrelevant semantic features;

[0066] The relevance semantic features are mapped to the demand fragments within the blank semantic sequence, and the user's target product is imported into the product fragment to obtain the consultation semantic fragment.

[0067] When the user inputs customer service and after-sales information, the obtained candidate semantic features are marked, and the semantic terms that match the marked candidate semantic features are summarized. Then, the after-sales items associated with each semantic term are divided into a second division to obtain a semantic feature subset corresponding to each after-sales item. The candidate semantic features in each semantic feature subset are associated with the corresponding after-sales item.

[0068] Import the candidate semantic features from the subset of semantic features associated with the after-sales project into the requirement segment in the blank semantic sequence, and simultaneously import the time when the user inputs customer service after-sales information into the time segment to obtain the after-sales semantic segment;

[0069] Match the time within the time segment with the corresponding after-sales time for the after-sales project. If the time falls within the after-sales time, the corresponding after-sales project is considered reasonable; otherwise, it is considered unreasonable, and the corresponding after-sales project is marked as an overdue project.

[0070] It should be further explained that, in the specific implementation process, the process of defining key response content at the response content definition node and integrating the defined key response content to obtain the corresponding customized response content includes:

[0071] An information database is set up, which includes information entries associated with each product and its corresponding after-sales items;

[0072] Construct corresponding information graphs based on information terms within the information database;

[0073] It should be further explained that, in the specific implementation process, the construction process of the information graph includes:

[0074] Based on the consultation tags and after-sales tags, construct corresponding first-level consultation knowledge nodes and first-level after-sales knowledge nodes respectively;

[0075] Construct corresponding secondary consultation knowledge nodes and secondary after-sales knowledge nodes for each product in the product list;

[0076] Based on the semantic terms associated with each product, construct tertiary consultation knowledge nodes that are associated with the secondary consultation knowledge nodes. Each tertiary consultation knowledge node corresponds to a semantic term, and associate each tertiary consultation knowledge node with a corresponding information term.

[0077] Based on the semantic terms related to each after-sales project, construct tertiary after-sales knowledge nodes that are associated with secondary after-sales knowledge nodes. Each tertiary after-sales knowledge node corresponds to a semantic term, and associates the corresponding information terms with each tertiary after-sales knowledge node.

[0078] When a user inputs customer service inquiry information, the semantic fragment of the inquiry is input into the constructed information graph;

[0079] Read the user's target product in the consultation semantic fragment and determine the secondary consultation knowledge node corresponding to the user's target product;

[0080] Obtain the semantic features of each semantic fragment in the consultation, match each semantic feature with the information terms in each third-level consultation knowledge node in the information graph, and summarize the information terms associated with the matched third-level consultation knowledge nodes to obtain the response term set;

[0081] When the user inputs customer service and after-sales information, the after-sales semantic fragments are input into the constructed information graph;

[0082] Based on the product selected by the user, determine the corresponding secondary after-sales knowledge node for that product;

[0083] The system acquires the semantic features of each semantic segment in the after-sales service, matches each semantic feature with the information terms in each third-level after-sales knowledge node in the information graph, summarizes the information terms associated with the matched third-level after-sales knowledge nodes, obtains the response term set, and automatically generates "After-sales project is overdue" for overdue projects in the after-sales service project. Users can continue to select human customer service.

[0084] After integrating the various information entries within the obtained set of response terms, corresponding customized customer service responses are obtained.

[0085] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any modifications or equivalent substitutions made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A process data automation handling system comprising a management center, characterized in that, The management center is communicatively connected with a user terminal, a data input node, a data processing node, and a reply content formulation node; The user terminal is configured to receive customer service demand information input by a user; The data input node is configured to extract features from the customer service demand information input by the user to obtain corresponding candidate semantic features; The data processing node is configured to perform relevance screening on the obtained candidate semantic features, and perform rationality screening on the customer service demand information input by the user according to the relevance screening result; The reply content formulation node is configured to formulate key reply content, integrate the formulated key reply content, and obtain corresponding customized reply content; A label corresponding to the customer service demand information input by the user is read, and a corresponding blank semantic sequence is constructed according to the read label; The blank semantic sequence corresponding to the consultation label is composed of a product segment and a demand segment; and the blank semantic sequence corresponding to the after-sales label is composed of a demand segment and a time segment; A standard semantic feature library is set up, and semantic terms associated with each product in a commodity list and semantic terms associated with an after-sales item are constructed in the standard semantic feature library; When the customer service information input by the user is customer service consultation information, the obtained candidate semantic features are respectively marked, each semantic term matching the marked candidate semantic features is respectively summarized, and each semantic term is secondarily divided according to the product associated with each semantic term to obtain a semantic feature subset corresponding to each product; The number of candidate semantic features in each semantic feature subset is obtained, and the product with the largest number of candidate semantic features is selected as a user consultation target product; The candidate semantic features matching the semantic term corresponding to the user consultation target product are marked as relevance semantic features; The relevance semantic features are mapped to the demand segment in the blank semantic sequence, and the user consultation target product is introduced into the product segment, thereby obtaining a consultation semantic segment; An information database is set up, and the information database includes information terms associated with each product and corresponding after-sales items; An information graph is constructed based on the information terms in the information database; When the customer service information input by the user is customer service consultation information, the consultation semantic segment is input into the constructed information graph; The user consultation target product in the consultation semantic segment is read, and a secondary consultation knowledge node corresponding to the user consultation target product is determined; Each semantic feature in the consultation semantic segment is obtained, each semantic feature is matched with information terms in each tertiary consultation knowledge node in the information graph, and the information terms associated with the matched tertiary consultation knowledge nodes are summarized to obtain a reply term set.

2. The process data automation system of claim 1, wherein, A user inputs customer service demand information through a user terminal, and the customer service demand information includes customer service consultation information and customer service after-sales information; A consultation label is generated according to the customer service consultation information input by the user, an after-sales label is generated according to the customer service after-sales information input by the user, the consultation label is associated with the customer service consultation information input by the user, and the after-sales label is associated with the customer service after-sales information input by the user.

3. The process data automation system of claim 2, wherein, The data input node extracts features of the customer service demand information input by the user, and a process of obtaining corresponding candidate semantic features includes: When the user input is customer service consultation information, each semantic feature in the customer service consultation information is extracted; The extracted semantic features are matched with semantic terms associated with each product in the product list. If any semantic feature matches a semantic term associated with any product, the corresponding semantic feature is bound to the blank semantic sequence corresponding to the product, and is recorded as a candidate semantic feature.

4. The process data automatic processing system according to claim 2, characterized in that, When the user input is customer service after-sales information, each semantic feature associated with the after-sales project corresponding to the product selected by the user in the customer service after-sales information is extracted, and the extracted semantic features are matched with semantic terms associated with each after-sales project. If any semantic feature matches a semantic term associated with the after-sales project, the corresponding semantic feature is bound to the blank semantic sequence corresponding to the product, and is recorded as a candidate semantic feature.

5. The process data automation system of claim 4, wherein, When the user input is customer service after-sales information, the obtained candidate semantic features are labeled respectively, and each semantic term matching the labeled candidate semantic features is summarized respectively, and then is divided again according to the after-sales project associated with each semantic term, to obtain a semantic feature subset corresponding to each after-sales project. The candidate semantic features in each semantic feature subset are associated with the corresponding after-sales project; The candidate semantic features in the semantic feature subset associated with the after-sales project are imported into the demand segment in the blank semantic sequence, and the time when the user inputs the customer service after-sales information is imported into the time segment, to obtain an after-sales semantic segment; The time in the time segment is matched with the after-sales time corresponding to the after-sales project. If the time is within the after-sales time, it means that the corresponding after-sales project is reasonable, otherwise it is not reasonable. The corresponding after-sales project is marked as an overdue project.

6. The automated process data handling system of claim 5, wherein, The reply content formulation node formulates key reply content, and integrates the formulated key reply content to obtain corresponding customized reply content, and a process includes: When the user input is customer service after-sales information, the after-sales semantic segment is input into the constructed information graph; According to the product selected by the user, a secondary after-sales knowledge node corresponding to the product is determined; Each semantic feature in the after-sales semantic segment is obtained, and each semantic feature is matched with information terms in each tertiary after-sales knowledge node in the information graph. The information terms associated with the matched tertiary after-sales knowledge nodes are summarized to obtain a reply term set; After integrating each information term in the obtained reply term set, corresponding customer service customized reply content is obtained.

7. The automated process data handling system of claim 6, wherein, The construction process of the information graph includes: According to the consultation label and the after-sales label, a primary consultation knowledge node and a primary after-sales knowledge node corresponding to each are constructed; According to each product in the product list, a secondary consultation knowledge node and a secondary after-sales knowledge node corresponding to each are constructed; According to the semantic term associated with each commodity, a third consultation knowledge node associated with the second consultation knowledge node is constructed, each third consultation knowledge node corresponds to a semantic term, and each third consultation knowledge node is associated with a corresponding information term; According to the semantic term related to each after-sales project, a third after-sales knowledge node associated with the second after-sales knowledge node is constructed, each third after-sales knowledge node corresponds to a semantic term, and each third after-sales knowledge node is associated with a corresponding information term.

Images