Order confirmation method and device

By identifying the entity in the user's product consultation text and automatically determining the order, the inconvenience problem of users in the prior art that they need to provide order numbers or links is solved, and the customer service communication efficiency and user experience are improved.

CN111985945BActive Publication Date: 2024-11-05ALIBABA (SHENZHEN) TECH CO LTD
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN201910425726.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-05-21
Publication Date
2024-11-05
Estimated Expiration
2039-05-21

AI Technical Summary

Technical Problem

In the existing customer service process, users need to provide order numbers or product links, which leads to inconvenience between users and customer service needs to spend time browsing and filtering, reducing user experience.

Method used

By obtaining the user's product consultation text, identifying the entity and determining the corresponding product orders, customer service can automatically determine the order during the communication process.

Benefits of technology

It reduces the time for customer service to determine orders, improves user experience, and simplifies the order query process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111985945B_ABST
    Figure CN111985945B_ABST
Patent Text Reader

Abstract

The present application discloses an order determination method and device. The method comprises: obtaining a product consultation text for a product; identifying an entity from the product consultation text; and determining a product order corresponding to the product according to the entity. By adopting the present application, the customer service can automatically determine the order during the communication with the customer service, thereby improving the user experience.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an order determination method and device thereof. Background Art

[0002] With the continuous development of technology, online shopping has become more and more popular. Users can use various shopping apps to purchase the goods they need, for example, they can use shopping apps to buy clothes, home furnishings, fresh food, takeout and other goods.

[0003] In order to improve the user experience, it is necessary to provide users with a better customer service experience. In the existing customer service process, after receiving a user's phone call or online consultation, the customer service needs the user to provide the order number or product link, which brings great inconvenience to the user. For example, when a user communicates with the customer service by phone about a purchased product, the customer service informs the user that the order number of the product is required. At this time, the user needs to check the order number while calling. If the user cannot provide the order number, the customer service needs to determine the order of the product that the user inquired about from the orders related to the user. However, this requires the customer service to spend time browsing and screening, which will also reduce the user's customer service experience. Therefore, the relevant technology requires a technical solution for the customer service to automatically determine the order during the communication with the customer service. Summary of the Invention

[0004] The embodiments of the present application provide an order determination method and device thereof, aiming to at least solve the above-mentioned technical problems.

[0005] An embodiment of the present application provides an order determination method, the method comprising: obtaining a product consultation text for a product; identifying an entity from the product consultation text; and determining a product order corresponding to the product based on the entity.

[0006] An embodiment of the present application also provides a computer-readable storage medium having computer instructions stored thereon, which implement the above method when the instructions are executed.

[0007] An embodiment of the present application also provides an order determination device, which includes: a processor; and a memory for storing computer-executable instructions, wherein the executable instructions can be executed by the processor to implement the following steps: obtaining a product consultation text for a product; identifying an entity from the product consultation text; and determining a product order corresponding to the product based on the entity.

[0008] An embodiment of the present application provides an order determination method, the method comprising: converting a voice query request about a product from a user into a product consultation text; identifying at least one entity from the product consultation text; determining at least one candidate order corresponding to the at least one entity; and selecting a product order corresponding to the product from the at least one candidate order.

[0009] According to an embodiment of the present application, an order determination device is provided, characterized in that it includes: a processor; and a memory for storing computer-executable instructions, and the executable instructions can be executed by the processor to perform the following steps: obtain product inquiry information issued by a user; identify an entity from the product inquiry information, and determine the product and product order information corresponding to the entity; and prompt the customer service personnel with the order information so that the customer service personnel can respond to the user's inquiry based on the prompt.

[0010] According to an embodiment of the present application, an intelligent customer service processing method is provided, the method comprising: obtaining product inquiry information sent by a user; identifying an entity from the product inquiry information, and determining the product and product order information corresponding to the entity; and prompting the customer service personnel with the order information so that the customer service personnel can respond to the user's inquiry based on the prompt.

[0011] An embodiment of the present application also provides an intelligent customer service processing device, which includes: a processor; and a memory for storing computer-executable instructions, wherein the executable instructions can be executed by the processor to implement the following steps: obtaining product inquiry information issued by a user; identifying an entity from the product inquiry information, and determining the product and product order information corresponding to the entity; and prompting the customer service personnel with the order information so that the customer service personnel can respond to the user's inquiry based on the prompt.

[0012] According to an embodiment of the present application, a method for determining an order is provided, comprising: obtaining inquiry information from a user; identifying an entity from the inquiry information and determining a product corresponding to the entity; and obtaining a product order corresponding to the product from the user order information.

[0013] According to an embodiment of the present application, a device for determining an order is provided, comprising: a processor; and a memory for storing computer-executable instructions, wherein the executable instructions can be executed by the processor to perform the following steps: obtaining user consultation information; identifying an entity from the consultation information, and determining a product corresponding to the entity; and obtaining a product order corresponding to the product from user order information.

[0014] By using this application, the customer service can automatically confirm the order during the communication with the customer service, which improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0016] Figure 1 is a diagram illustrating a scenario of determining an order according to an exemplary embodiment of the present application;

[0017] Figure 2 is a flowchart illustrating an order determination method according to an exemplary embodiment of the present application;

[0018] Figure 3 is a process flow chart illustrating an order determination method according to another exemplary embodiment of the present application;

[0019] Figure 4 is a block diagram illustrating an order determination apparatus according to an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0020] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0021] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0022] Figure 1 : is a scene diagram showing the order determination according to an exemplary embodiment of the present application. Figure 1 As shown, the user can contact the customer service using the mobile terminal. For example, the user can use the mobile terminal to perform voice communication with the customer service, or the user can use the terminal device including the mobile terminal to communicate with the customer service through short messages. It should be noted that the terminal device according to the present application may include, but is not limited to, any of the following devices: personal computers (PCs), mobile devices (such as cellular phones, personal digital assistants (PDAs), digital cameras, portable game consoles, MP3 players, portable / personal multimedia players (PMPs), handheld e-books, tablet PCs, portable laptop PCs, and global positioning system (GPS) navigators), smart TVs, etc.

[0023] exist Figure 1 In the example, a user can use a mobile terminal to inquire about a purchased product (sweater). Subsequently, after receiving the product inquiry request input by the user through voice, the customer service can use the order determination device according to the exemplary embodiment of the present application to determine the order of the product inquired by the user, wherein the order determination device is a device that runs the order determination method according to the exemplary embodiment of the present application. Finally, the customer service can confirm with the user whether to inquire about the order. After obtaining the user's reply, the customer service can perform subsequent operations, for example, providing the user with the express delivery information of the product.

[0024] The following will be combined Figure 2A flowchart of an order determination method according to an exemplary embodiment of the present application is described in detail.

[0025] In step S210, obtain the product consultation text for the product. In practice, the user can Figure 1 As shown, an electronic terminal is used to send a product consultation request, where the product consultation request is a consultation request for a product. In addition, the product consultation request includes but is not limited to voice and / or text requests.

[0026] After receiving the product consultation request, step S210 may be executed, specifically including: converting the product consultation request input by the user's voice into the product consultation text using a speech recognition model, wherein the speech recognition model is a trained model for speech recognition. Speech recognition is also known as automatic speech recognition (ASR), and its goal is to automatically convert human speech content into corresponding text using a computer.

[0027] During implementation, the speech recognition model may be trained based on the correspondence between multiple training corpora and the training texts corresponding to the multiple training expectations. Preferably, the speech recognition model includes a FastText model. Furthermore, if the product consultation request is a text consultation request, step S210 may be directly executed, that is, obtaining the product consultation text for the product.

[0028] Then, step S220 is performed to identify entities from the product consultation text. The entities can use different attributes to describe the product. For example, the brand, category, purchase time, and purchase amount of the product can all be entities of the product. In implementation, an entity recognition model can be used to identify the entities from the product consultation text. The entity recognition model is a pre-trained model.

[0029] In implementation, the entity recognition model can be a single entity recognition model or a combination of multiple entity recognition models, that is, the entity recognition model includes a combination of one or more of the following models: brand entity recognition model, category entity recognition model, time entity recognition model and amount entity recognition model.

[0030] When the entity recognition model includes multiple models, these models can process the product consulting text in a parallel or serial manner. Before processing the product consulting text, the entity recognition model can be trained based on multiple training corpora and the corresponding relationships between multiple training entities corresponding to the multiple training corpora. It should be noted that entity recognition models of various attributes can be trained using their own training data respectively. Preferably, the entity recognition model includes BiLSTM-CRF models for different entity types. According to Figure 1 For example, at least sweater and yesterday can be identified from the product consultation text. In addition, if the product consultation text includes requests for multiple products, the above operation can be performed when one of the products is determined by the user or by default.

[0031] Finally, step S230 is executed to determine the product order corresponding to the product based on the entity, which specifically includes: filtering out entity orders that include the entity from the historical order set corresponding to the user; if only one entity order is filtered out, the entity order is determined to be the product order.

[0032] That is, after receiving the user's product consultation request, the historical order set corresponding to the user can be obtained. Then, the order corresponding to the entity identified in step S220 can be extracted from the historical order set. Figure 1 For example, physical orders can be extracted from the historical order set based on sweaters and / or yesterday. If only one physical order is filtered out, the physical order is determined to be a product order.

[0033] If multiple entity orders are screened out, the multiple entity orders are classified into at least one candidate order set corresponding to each entity. In other words, if multiple entity orders are screened out, the entity orders are classified into different candidate order sets according to the entity attributes. Figure 1 For example, if multiple physical orders are filtered out using sweaters and yesterday, candidate order set A can be determined based on sweaters, and candidate order set B can be determined based on yesterday.

[0034] Subsequently, the product order is determined using the at least one candidate order set. Specifically, an intermediate order set is obtained by intersecting the at least one candidate order set. If the intermediate order set includes only one intermediate order, the intermediate order is determined as the product order. For example, if the intersection of candidate order set A and candidate order set B includes only one intermediate order, the intermediate order can be determined as the product order.

[0035] If the intermediate order set includes multiple intermediate orders, in implementation, an intention matching model can be used to determine the product order corresponding to the product from the intermediate order set, wherein the intention matching model is a model for determining the intermediate order with the highest similarity to the product consultation text.

[0036] Specifically, an intermediate order vector corresponding to each of the plurality of intermediate orders and a product consultation text vector corresponding to the product consultation text may be generated; each intermediate order vector is compared with the product consultation text vector, and the intermediate order corresponding to the intermediate order vector with the highest similarity to the product consultation text vector is determined as the product order. For example, the COS similarity may be used to determine the intermediate order vector with the highest similarity to the product consultation text vector.

[0037] In addition, the present application also provides an order determination method, which includes: converting a voice query request about a product from a user into a product consultation text; identifying at least one entity from the product consultation text; determining at least one candidate order corresponding to the at least one entity; and selecting a product order corresponding to the product from the at least one candidate order.

[0038] According to an exemplary embodiment of the present application, an intelligent customer service processing method may also be provided, the method comprising: obtaining product inquiry information sent by a user; identifying an entity from the product inquiry information, determining the product and product order information corresponding to the entity; and prompting the customer service personnel with the order information so that the customer service personnel can respond to the user's inquiry based on the prompt. According to an exemplary embodiment of the present application, an order determination method may also be provided, the method comprising: obtaining user inquiry information; identifying an entity from the inquiry information, determining the product corresponding to the entity; and obtaining a product order corresponding to the product from the user's order information.

[0039] In summary, the order determination method according to the exemplary embodiment of the present application can automatically determine the inquired order during the communication with customer service by identifying the entities in the product consultation request and determining the product order based on the entities, thereby reducing the time for customer service to determine the order and improving the user experience. Furthermore, the product consultation request input by voice can be converted into a text request, thereby facilitating the subsequent determination of the entity of the product. Furthermore, the voice recognition model can be used to perform voice conversion to improve the accuracy of voice-to-text conversion. Furthermore, the training text can be used to train the voice recognition model to make the accuracy higher. Furthermore, the entity recognition model can be used to identify entities in the text, thereby improving the accuracy of entity recognition. Furthermore, multiple entity recognition models can be used to determine multiple entities in the text, and multiple entities can be used to finally determine the product order, thereby more accurately determining the product order from multiple candidate orders. Furthermore, the intention matching model can also be used to determine the product order, thereby more accurately determining the product order.

[0040] The following will be combined Figure 3 The preferred embodiments of the present application will be described in detail. Figure 3 is a process flow chart illustrating an order determination method according to another exemplary embodiment of the present application.

[0041] like Figure 3 As described, the user can make a voice call with the customer service through the mobile terminal and ask the customer service about the situation of related products. For example, the user can ask the customer service, "Hello, why haven't I received the sweater and down jacket I bought yet?" After receiving the user's voice request, the customer service can use the voice recognition model 310 to convert the received voice call into text, and input the text into the entity recognition model 320.

[0042] The entity recognition model 320 extracts entities corresponding to products from the text, such as Figure 3 As described above, "sweaters" and "down jackets" can be extracted and provided to customer service. At this time, customer service can determine the order of the entities inquired from the user. For example, the user can be asked whether to prioritize orders related to sweaters. If the user agrees to prioritize "sweaters", candidate orders related to sweaters can be provided to the intent matching model 330. In implementation, when the request includes multiple products, product orders can also be provided to the user in a default order. In addition, if the request is only for a single product such as a sweater, this order may not be determined from the user.

[0043] In addition, it should be noted that although Figure 3 Only a single entity recognition model is shown in FIG. 1 , but this is merely exemplary, and the entity recognition model may include entity recognition models for recognizing different types of entities.

[0044] like Figure 3 As shown, if it is determined that product orders related to sweaters are given priority, candidate product orders related to sweaters can be sent to the intent matching model, and the intent matching model can be used to determine the final product order from the candidate product orders.

[0045] In order to more clearly understand the inventive concept of the exemplary embodiments of the present application, the following will refer to Figure 4 A block diagram of an order determination device according to an exemplary embodiment of the present application is described. A person skilled in the art will understand that: Figure 4 The device in FIG. 1 only shows components related to this exemplary embodiment, and the device also includes components other than Figure 4 Common components other than those shown in .

[0046] Figure 4 A block diagram showing an order determination device of an exemplary embodiment of the present application. It should be noted that the order determination device may be Figure 1 The server used by the customer service in the Figure 2 An apparatus for illustrating an order determination method.

[0047] refer to Figure 4 At the hardware level, the device includes a processor, an internal bus, and a computer-readable storage medium, wherein the computer-readable storage medium includes a volatile memory and a non-volatile memory. The processor reads the corresponding computer program from the non-volatile memory and runs it. Of course, in addition to software implementation, this application does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0048] Specifically, the processor performs the following operations: obtaining a product consultation text for a product; identifying an entity from the product consultation text; and determining a product order corresponding to the product based on the entity.

[0049] Optionally, before the server implements the step of obtaining the product consultation text for the product, the server further includes: receiving a product consultation request input by user voice.

[0050] Optionally, the server obtaining the product consultation text for the product in the implementation step includes: converting the product consultation request input by the user's voice into the product consultation text using a voice recognition model, wherein the voice recognition model is a trained model.

[0051] Optionally, the speech recognition model is trained based on the correspondence between a plurality of training corpora and training texts corresponding to the plurality of training expectations.

[0052] Optionally, the speech recognition model includes a FastText model.

[0053] Optionally, the server identifying the entity from the product consultation text in the implementation step includes: using an entity recognition model to identify the entity from the product consultation text, wherein the entity recognition model is a trained model.

[0054] Optionally, the entity recognition model includes a combination of one or more of the following models: a brand entity recognition model, a category entity recognition model, a time entity recognition model, and an amount entity recognition model.

[0055] Optionally, the entity recognition model is trained based on a plurality of training corpora and corresponding relationships between a plurality of training entities corresponding to the plurality of training corpora.

[0056] Optionally, the entity recognition model includes a BiLSTM-CRF model for different entity types.

[0057] Optionally, the server determines the product order corresponding to the product based on the entity in the implementation step, including: filtering out entity orders that include the entity from the historical order set corresponding to the user; if only one entity order is filtered out, the entity order is determined to be a product order.

[0058] Optionally, the server further implements the steps of: if multiple entity orders are screened out, classifying the multiple entity orders into at least one candidate order set corresponding to each entity;

[0059] A product order is determined using the at least one candidate order set.

[0060] Optionally, the server determines the product order using the at least one candidate order set in the implementation step, including: obtaining an intermediate order set by taking the intersection of the at least one candidate order set; if the intermediate order set includes only one intermediate order, determining the intermediate order as the product order.

[0061] Optionally, the server further implements the step of: if the intermediate order set includes multiple intermediate orders, using an intention matching model to determine a product order corresponding to the product from the intermediate order set.

[0062] Optionally, the intent matching model is a model for determining an intermediate order having the highest similarity to the product inquiry text.

[0063] Optionally, the server uses the intention matching model in the implementation step to determine the product order corresponding to the product from the intermediate order set, including: generating an intermediate order vector corresponding to each intermediate order in the multiple intermediate orders and a product consultation text vector corresponding to the product consultation text; by comparing each intermediate order vector with the product consultation text vector, determining the intermediate order corresponding to the intermediate order vector with the highest similarity to the product consultation text vector as the product order.

[0064] In addition, according to an exemplary embodiment, the processor may also perform the following operations: converting a voice query request about a product from a user into a product consultation text; identifying at least one entity from the product consultation text; determining at least one candidate order corresponding to the at least one entity; and selecting a product order corresponding to the product from the at least one candidate order.

[0065] In addition, according to an exemplary embodiment, the processor can also perform the following operations: obtain product inquiry information issued by the user; identify an entity from the product inquiry information, determine the product and product order information corresponding to the entity; and prompt the customer service personnel with the order information so that the customer service personnel can respond to the user's inquiry based on the prompt.

[0066] In addition, according to an exemplary embodiment, the processor may further perform the following operations: obtaining user consultation information; identifying an entity from the consultation information and determining a product corresponding to the entity; and obtaining a product order corresponding to the product from user order information.

[0067] In summary, the order determination device according to the exemplary embodiment of the present application can automatically determine the inquired order during the communication with customer service by identifying the entities in the product consultation request and determining the product order based on the entities, thereby reducing the time for customer service to determine the order and improving the user experience. Furthermore, the product consultation request input by voice can be converted into a text request, thereby facilitating the subsequent determination of the entity of the product. Furthermore, the voice recognition model can be used to perform voice conversion to improve the accuracy of voice-to-text conversion. Furthermore, the training text can be used to train the voice recognition model to make the accuracy higher. Furthermore, the entity recognition model can be used to identify entities in the text, thereby improving the accuracy of entity recognition. Furthermore, multiple entity recognition models can be used to determine multiple entities in the text, and multiple entities can be used to finally determine the product order, thereby more accurately determining the product order from multiple candidate orders. Furthermore, the intention matching model can also be used to determine the product order, thereby more accurately determining the product order.

[0068] It should be noted that the execution entity of each step of the method provided in Example 1 can be the same device, or the method can be executed by different devices. For example, the execution entity of steps 21 and 22 can be device 1, and the execution entity of step 23 can be device 2; for another example, the execution entity of step 21 can be device 1, and the execution entity of steps 22 and 23 can be device 2; and so on.

[0069] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0071] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0073] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0074] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0075] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0076] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0077] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0078] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. An order confirmation method, It is characterized in that include: Get product consultation text for products; Using a plurality of pre-trained entity recognition models, a plurality of entities are identified from the product consultation text, wherein the entities are used to describe product attributes; Filtering out multiple entity orders including the entity from a historical order set corresponding to the user; Classifying the plurality of entity orders into a plurality of candidate order sets corresponding to each entity; Obtain an intermediate order set by taking the intersection of the multiple candidate order sets; A product order corresponding to the product is automatically determined from the intermediate order set.

2. The method according to claim 1, It is characterized in that Before obtaining product consultation text for the product, it also includes: A product consultation request for the product input by a user's voice is received.

3. The method according to claim 2, It is characterized in that Get product advisory text for products including: The product consultation request input by the user's voice is converted into the product consultation text using a voice recognition model, wherein the voice recognition model is a trained model.

4. The method according to claim 3, It is characterized in that The speech recognition model is trained based on the correspondence between a plurality of training corpora and the training texts respectively corresponding to the plurality of training corpora.

5. The method according to claim 4, It is characterized in that The speech recognition model includes a FastText model.

6. The method according to claim 1, It is characterized in that The entity recognition model includes a combination of multiple models of the following models: a brand entity recognition model, a category entity recognition model, a time entity recognition model and an amount entity recognition model.

7. The method according to claim 1, It is characterized in that The entity recognition model is obtained by training based on a plurality of training corpora and corresponding relationships between a plurality of training entities respectively corresponding to the plurality of training corpora.

8. The method according to claim 1, It is characterized in that The entity recognition model includes a BiLSTM-CRF model for different entity types.

9. The method according to claim 1, It is characterized in that Determining a product order corresponding to the product from the intermediate order set includes: If the intermediate order set includes only one intermediate order, the intermediate order is determined as a product order.

10. The method according to claim 9, It is characterized in that Also includes: If the intermediate order set includes multiple intermediate orders, the intention matching model is used to determine the product order corresponding to the product from the intermediate order set.

11. The method according to claim 10, It is characterized in that The intent matching model is a model for determining the intermediate order with the highest similarity to the product consultation text.

12. The method according to claim 11, It is characterized in that Determining a product order corresponding to the product from the intermediate order set using the intention matching model includes: Generate an intermediate order vector corresponding to each intermediate order of the plurality of intermediate orders and a product consulting text vector corresponding to the product consulting text; By comparing each intermediate order vector with the product consultation text vector, the intermediate order corresponding to the intermediate order vector with the highest similarity to the product consultation text vector is determined as the product order.

13. A computer-readable storage medium having computer instructions stored thereon, It is characterized in that When the instructions are executed, the method of any one of claims 1 to 12 is implemented.

14. An order confirmation device, It is characterized in that include: processor; as well as A memory for storing computer executable instructions, wherein the executable instructions can be executed by a processor to implement the method of any one of claims 1 to 12.

15. An order confirmation method, It is characterized in that include: Converting voice query requests from users about products into product consultation texts; Using a plurality of pre-trained entity recognition models, a plurality of entities are identified from the product consultation text, wherein the entities are used to describe product attributes; determining a plurality of candidate orders corresponding to the plurality of entities; Classifying the plurality of candidate orders into a plurality of candidate order sets corresponding to each entity respectively; Obtain an intermediate order set by taking the intersection of the multiple candidate order sets; A product order corresponding to the product is automatically determined from the intermediate order set.

16. An order confirmation device, It is characterized in that include: A memory for storing computer executable instructions, wherein the executable instructions can be executed by a processor to implement the method of claim 15.

17. An intelligent customer service processing method, It is characterized in that include: Obtain product consultation information from users; Using a plurality of pre-trained entity recognition models, a plurality of entities are identified from the product inquiry information, wherein the entities are used to describe product attributes; Filtering out multiple entity orders including the entity from a historical order set corresponding to the user; Classifying the plurality of entity orders into a plurality of candidate order sets corresponding to each entity; Obtain an intermediate order set by taking the intersection of the multiple candidate order sets; Automatically determine product order information corresponding to the product from the intermediate order set; The order information is prompted to the customer service personnel so that the customer service personnel can respond to the user's inquiry based on the prompt.

18. An intelligent customer service processing device, It is characterized in that include: A memory for storing computer executable instructions, wherein the executable instructions can be executed by a processor to implement the method of claim 17.

19. A method of determining an order, It is characterized in that include: Obtain consultation information from users; Using a plurality of pre-trained entity recognition models, a plurality of entities are identified from the inquiry information, and products corresponding to the entities are determined, wherein the entities are used to describe product attributes; Filtering out multiple entity orders including the entity from a historical order set corresponding to the user; Classifying the plurality of entity orders into a plurality of candidate order sets corresponding to each entity; Obtain an intermediate order set by taking the intersection of the multiple candidate order sets; A product order corresponding to the product is automatically determined from the intermediate order set.

20. A device for determining an order, It is characterized in that include: A memory for storing computer executable instructions, wherein the executable instructions can be executed by a processor to implement the method of claim 19.

Citation Information

Patent Citations

  • Order processing method and apparatus, electronic device, and computer-readable storage medium

    CN108171576A

  • Phone bill classifying method, device, server and storage medium

    CN108597519A

  • A method and a device for providing customer service

    CN108959633A

  • Customer service method and apparatus, and computer readable storage medium

    CN108984777A

  • Response method and device for service consultation

    CN109345282A