A search processing method, a customer service information processing method and a device

Abstract

The present disclosure relates to a search processing method, a customer service information processing method and an apparatus, including: in response to a search operation of a current user, determining a service object of the current user; obtaining session information generated during the consultation of the service object and order-related information of the service object; predicting at least one target search term that the current user is going to search according to the session information and the order-related information; and presenting search results in response to a target search term selected by the current user. By automatically predicting the target search term, the search processing method, the customer service information processing method and the apparatus according to the embodiments of the present disclosure can simplify the search process and improve the search efficiency.

Description

Technical Field

[0001] The present disclosure relates to the field of search technologies, and in particular, to a search processing method, a customer service information processing method, and an apparatus therefor. Background Art

[0002] During the entire shopping process, customers may encounter positive or negative issues in various links before, during, and after sales, and thus seek consultation from human customer service. The entire process of customers seeking consultation from human customer service is called consultation service.

[0003] Locating problem-solving strategies is an important link in consultation service. In related technologies, when a human customer service looks for appropriate problem-solving strategies from a knowledge base according to the problems described by the customer and the demands expressed, the accuracy and efficiency of the search are relatively low. For example, the search results are inaccurate, and it is necessary to search multiple times to find the correct problem-solving strategy, and it is not known what search terms to use for the search.

[0004] Therefore, there is an urgent need for a search method in related technologies that can improve the accuracy and efficiency of the search. Summary of the Invention

[0005] To overcome the problems existing in related technologies, the present application provides a search processing method, a customer service information processing method, and an apparatus therefor. The specific implementation manners are as follows:

[0006] A search processing method is applied to an instant messaging session. The method includes:

[0007] Responding to a search operation of the current user in the session;

[0008] Predicting at least one target search term that the current user intends to search based on the session information in the session and the attribute information of the current user;

[0009] Responding to the target search term selected by the current user and presenting search results.

[0010] A customer service information processing method includes:

[0011] Responding to a switching instruction of a dialogue robot to establish a session between a human customer service and a service object;

[0012] Obtaining the session information in the session between the dialogue robot and the service object, and predicting at least one target search term based on the session information;

[0013] Presenting the at least one target search term to the human customer service.

[0014] A customer service information processing method includes:

[0015] In response to a switching instruction of a dialogue robot, establish a session between a human customer service and a service object;

[0016] Obtain session information in the session between the dialogue robot and the service object, and predict at least one target search term based on the session information;

[0017] Display the search result of one of the at least one target search terms to the human customer service.

[0018] A search processing method, the method includes:

[0019] In response to a search operation of the current user, determine the service object of the current user;

[0020] Obtain the session information generated by the service object during the consultation process and the order-related information of the service object;

[0021] Predict at least one target search term that the current user wants to search according to the session information and the order-related information;

[0022] In response to the target search term selected by the current user, display the search result.

[0023] A customer service information processing method, the method includes:

[0024] In response to a switching instruction of a dialogue robot, establish a session between a human customer service and a service object;

[0025] Provide a search box for the human customer service on the session page;

[0026] Display a target search term in the search box, and the target search term is determined by the server according to the session information in the session between the dialogue robot and the service object.

[0027] A search processing device, which is applied to the session of instant messaging. The device includes a processor and a memory for storing instructions executable by the processor. When the processor executes the instructions, it realizes:

[0028] In response to a search operation of the current user in the session;

[0029] Predict at least one target search term that the current user wants to search based on the session information in the session and the attribute information of the current user;

[0030] In response to the target search term selected by the current user, display the search result.

[0031] A customer service information processing device, the device includes a processor and a memory for storing instructions executable by the processor. When the processor executes the instructions, it realizes:

[0032] In response to a switching instruction of the dialogue robot, establish a session between the human customer service and the service object;

[0033] Obtain the session information in the session between the dialogue robot and the service object, and predict at least one target search term based on the session information;

[0034] Display the at least one target search term to the human customer service.

[0035] A customer service information processing device, the device includes a processor and a memory for storing processor-executable instructions, and when the processor executes the instructions, it realizes:

[0036] In response to a switching instruction of the dialogue robot, establish a session between the human customer service and the service object;

[0037] Obtain the session information in the session between the dialogue robot and the service object, and predict at least one target search term based on the session information;

[0038] Display the search result of one of the at least one target search terms to the human customer service.

[0039] A search processing device, the device includes a processor and a memory for storing processor-executable instructions, and when the processor executes the instructions, it realizes:

[0040] In response to the search operation of the current user, determine the service object of the current user;

[0041] Obtain the session information generated during the consultation of the service object and the order-related information of the service object;

[0042] Predict at least one target search term that the current user wants to search according to the session information and the order-related information;

[0043] In response to the target search term selected by the current user, display the search result.

[0044] A customer service information processing device, the device includes a processor and a memory for storing processor-executable instructions, and when the processor executes the instructions, it realizes:

[0045] In response to a switching instruction of the dialogue robot, establish a session between the human customer service and the service object;

[0046] Provide a search box for the human customer service on the session page;

[0047] Display a target search term in the search box, where the target search term is determined by the server according to the session information in the session between the dialogue robot and the service object.

[0048] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor, enable the processor to execute the above method.

[0049] In the embodiments of the present disclosure, in response to the search operation of the current user in the session, at least one target search term to be searched by the current user can be predicted, so as to display the search results of the target search term selected by the current user, so that when the current user needs to search, there is no need to input the search term by himself, avoiding multiple searches caused by inaccurate search, simplifying the search process, and improving the search efficiency.

[0050] According to the following detailed description of the exemplary embodiments with reference to the accompanying drawings, other features and aspects of the present disclosure will become clear. Brief Description of the Drawings

[0051] The drawings included in the specification and constituting a part of the specification show the exemplary embodiments, features and aspects of the present disclosure together with the specification, and are used to explain the principles of the present disclosure.

[0052] Figure 1a A schematic diagram of an exemplary application scenario of the search processing method showing an embodiment of the present disclosure.

[0053] Figure 1b Show an example of the display of a target search term according to an embodiment of the present disclosure.

[0054] Figure 1c Show an example of the display of a target search term according to an embodiment of the present disclosure.

[0055] Figure 2a A schematic diagram of an exemplary application scenario of the customer service information processing method showing an embodiment of the present disclosure.

[0056] Figure 2b Show an example of the display of a target search term according to an embodiment of the present disclosure.

[0057] Figure 3a Show an example of the search result page according to an embodiment of the present disclosure.

[0058] Figure 3b Show an example of the search result page according to an embodiment of the present disclosure.

[0059] Figure 4 Show a flowchart of the search processing method according to an embodiment of the present disclosure.

[0060] Figure 5 Shows a schematic diagram of a classification model according to an embodiment of the present disclosure.

[0061] Figure 6 Shows a flowchart of a customer service information processing method according to an embodiment of the present disclosure.

[0062] Figure 7a Shows a display example of a session page according to an embodiment of the present disclosure.

[0063] Figure 7b Shows a display example of a session page according to an embodiment of the present disclosure.

[0064] Figure 7c Shows a display example of a search page according to an embodiment of the present disclosure.

[0065] Figure 8 Shows a block diagram of a search processing device according to an embodiment of the present disclosure.

[0066] Figure 9 Shows a block diagram of a customer service information processing device according to an embodiment of the present disclosure. Detailed implementation manners

[0067] The following will describe various exemplary embodiments, features, and aspects of the present disclosure in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements having the same or similar functions. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0068] The term "exemplary" used herein means "serving as an example, embodiment, or illustration". Any embodiment described herein as "exemplary" is not necessarily to be construed as superior to or better than other embodiments.

[0069] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following detailed implementation manners. Those skilled in the art should understand that the present disclosure can also be implemented without some specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art are not described in detail so as to highlight the gist of the present disclosure.

[0070] To facilitate the understanding of the technical solutions provided by the embodiments of the present disclosure by those skilled in the art, the technical environment for implementing the technical solutions will be described first below.

[0071] As described above, due to inaccurate positioning of search terms, human customer service may need to conduct multiple searches to find the correct problem-solving strategy, which takes a long time and is inefficient. Currently, the human customer service group mainly consists of cloud customer service representatives, almost all of whom are part-time, resulting in a large turnover rate and a relatively large number of novice customer service representatives with less experience. These novice customer service representatives have poor problem-solving abilities and low stability. Compared with experienced customer service representatives, due to their lack of experience, they are often very inefficient in problem positioning. Especially when using search tools, they do not know how to select appropriate search terms to quickly locate the correct problem-solving strategy, causing customers to wait a long time to receive a response or assistance, and resulting in low customer satisfaction.

[0072] Based on the actual technical requirements similar to those described above, the search processing method and customer service information processing method provided by the present disclosure use a series of process methods to intelligently recommend target search terms and / or search results for human customer service representatives, especially novice customer service representatives who are not proficient in business, simplify the search process, thereby helping them more efficiently locate problem-solving strategies, better serve members, and improve the customer satisfaction of the entire human customer service group.

[0073] The following uses specific application scenarios to illustrate the search processing method and customer service information processing method provided by each embodiment of the present disclosure.

[0074] When a customer encounters a problem during the shopping process, they can directly find a human customer service representative for consultation. At this time, an instant messaging session is established between the customer and the human customer service representative to facilitate the human customer service representative to provide services to the customer. Figure 1a FIG. shows an exemplary application scenario diagram of the search processing method according to an embodiment of the present disclosure. As Figure 1a shown, taking the human customer service representative as the current user, in the case where an instant communication session has been established between the current user and the customer, the current customer can perform a search operation in the session (for example, triggering the search control in the session page or double-clicking the session page, etc.). In response to this search operation, the background can predict at least one target search term that the current user intends to search for based on the session information in the session and the attribute information of the current user. Figure 1b And Figure 1c respectively show a display example of a target search term according to an embodiment of the present disclosure. As Figure 1b shown, at least one target search term can be displayed on the current session page. As Figure 1c shown, a search page can be displayed, and at least one target search term can be displayed on the search page. The current user can select from the at least one target search term. In response to the target search term selected by the current user, the background can display the search results corresponding to the selected target search term.

[0075] Among them, the session information can be used to locate the solution. The session information can include the text chat content between the text customer and the current user, the voice chat content, and the links shared by the customer, etc. The attribute information of the current user can be used to represent the proficiency of the current user in the search service. For example, the attribute information of the user can be a score, and the higher the score, the higher the proficiency of the user, and vice versa. The attribute information of the user can also be a level. The proficiency of a user with attribute information of level one is higher than that of a user with attribute information of level two, and the proficiency of a user with attribute information of level two is higher than that of a user with attribute information of level three, and so on. The attribute information of the user can also be a category. For example, the attribute information includes veteran customer service and novice customer service, and the proficiency of veteran customer service is higher than that of novice customer service. In one example, the attribute information of the user can be determined based on one or more of the number of searches of the user, the number of search terms used, the evaluation of the user by the customer, and the service duration of the user.

[0076] In a possible implementation manner, the background can first determine the problem-solving strategy according to the session information. Then, determine the search terms corresponding to the problem-solving strategy as candidate search terms; finally, determine at least one target search term from the candidate search terms according to the attribute information of the current user.

[0077] For example, the background can identify the keywords in the session information, and then determine the problem-solving strategy based on the keywords. The background can determine the search terms corresponding to the determined problem-solving strategy as candidate search terms according to the corresponding relationship between the problem-solving strategy and the search terms. Among them, the corresponding relationship between the problem-solving strategy and the search terms is a one-to-many corresponding relationship, that is, one problem-solving strategy corresponds to at least one search term. When the proficiency of the current user is relatively low, at least one candidate search term used more by other users with higher proficiency can be determined as the target search term. When the proficiency of the current user is relatively high, at least one target search term can be determined from the candidate search terms according to the historical search record of the current user.

[0078] In the embodiments of the present disclosure, in response to the search operation of the current user in the instant messaging session, at least one target search term that the current user wants to search can be predicted, so as to display the search results of the target search term selected by the current user, so that when the current user needs to search, there is no need to input the search term by himself, avoiding multiple searches caused by inaccurate search, and simplifying the search process.

[0079] In Figure 1aIn the shown scenario, after the human customer service clicks on the search control in the current conversation page, at least one target search term can be obtained. After the human customer service selects a target search term, the search results for that target search term can be obtained, enabling the human customer service to more efficiently locate the solution and better serve the customers, thereby increasing the satisfaction of the customers with the human customer service group.

[0080] When a customer encounters a problem during the shopping process, they usually first find the chatbot for consultation. The chatbot is essentially a computer program used to simulate human conversations or chats. At this time, in response to the customer's operation of consulting the customer service during the shopping process, a conversation between the chatbot and the customer is established. When the customer is not satisfied with the service, they can choose to switch to the human customer service (i.e., the current user), and at this time, a switching instruction for the chatbot is generated. In response to the switching instruction of the chatbot, the background can establish a conversation between the current user and the customer and generate the search operation of the current user in the conversation. Considering that the customer has already had a conversation with the chatbot, to avoid customer dissatisfaction caused by the customer repeating the problem, in response to the switching instruction of the chatbot, a conversation between the customer and the current user can be established and the search operation of the current user in the conversation can be generated. In response to this search operation, the background can predict at least one target search term that the current user is going to search for based on the conversation information in the conversation and the attribute information of the current user. In this way, without the customer repeating the problem, the current user can obtain the target search term. The current user can select from at least one target search term, and in response to the target search term selected by the current user, the background can display the search results corresponding to the selected target search term.

[0081] In the embodiment of the present disclosure, after the current user receives the service switched from the chatbot, at least one target search term can be obtained. After the current user selects a target search term, the search results for that target search term can be obtained, enabling the current user to more efficiently locate the solution and better serve the customers. In this way, when the customer service is not satisfied with the chatbot service, timely and efficient service can be obtained, thereby increasing the satisfaction of the customers with the customer service group.

[0082] Figure 2a Exemplary application scenario diagram showing a customer service information processing method according to an embodiment of the present disclosure. As Figure 2aAs shown, with the customer as the service target, in response to the operation of the service target consulting the customer service during the shopping process, a session between the dialogue robot and the service target is established. When the service target is not satisfied with the service, the service target can choose to switch to a human customer service, and at this time, a switching instruction for the dialogue robot is generated. In response to the switching instruction of the dialogue robot, the background can establish a session between the human customer service and the service target. Then, the background can obtain the session information in the session between the dialogue robot and the service target, and predict at least one target search term based on the session information. Then, the background displays the at least one target search term to the human customer service. Figure 2b Show a display example of a target search term according to an embodiment of the present disclosure. As Figure 2b shown, at least one target search term can be displayed on the current session page. As Figure 1c shown, a search page can be displayed, and at least one target search term can be displayed on the search page. The human customer service can select from the at least one target search term. In response to the target search term selected by the human customer service, the background can display the search results corresponding to the selected target search term.

[0083] Among them, the session information in the session between the dialogue robot and the service target can refer to the session information in the session between the current user and the customer, which will not be elaborated here. The method for predicting at least one target search term based on the session information will not be elaborated either.

[0084] When the service target chooses to switch to a human customer service during the session with the dialogue robot, a switching instruction for the dialogue robot is generated at this time. As Figure 2a shown, in response to the switching instruction of the dialogue robot, the background establishes a session between the human customer service and the service target. Then, the background can obtain the session information in the session between the dialogue robot and the service target, predict at least one target search term based on the session information, and display the search results of one of the at least one target search terms to the human customer service. Figure 3a Show an example of a search result page according to an embodiment of the present disclosure. As Figure 3a shown, the search results of the target search term "rapid refund" can be displayed on the search result page.

[0085] In one example, the background can display the search results of the target search term with the largest number of searches by human customer service among at least one target search term to the human customer service, and can also display the search results of the target search term with the largest number of current searches by the human customer service among at least one target search term to the human customer service. It can also randomly select a target search term from at least one target search term and display the search result page of the selected target search term to the human customer service. The above is only an example of selecting one target search term from at least one target search term, and other methods can also be used to select one target search term from at least one target search term, and the present disclosure does not limit this.

[0086] In the embodiment of the present disclosure, by directly displaying the search results of a target search term to the human customer service, the operation of the human customer service to select the target search term is omitted, further simplifying the search process, helping the human customer service to locate the solution more efficiently, and serving the members better.

[0087] In a possible implementation manner, while displaying the search results of a target search term to the human customer service, at least one target search term can also be displayed. For example, all or part of the target search terms in at least one target search term can be displayed. Figure 3b Shows an example of a search result page according to an embodiment of the present disclosure. As Figure 3b shown, while displaying the search results of the target search term "express refund" to the human customer service, all the target search terms "rapid refund", "return problem", and "freight insurance" can also be displayed.

[0088] In the embodiment of the present disclosure, by displaying the target search term while displaying the search results, other options are provided for the human customer service. In this way, when the human customer service is not satisfied with the search results, they can directly select other target search terms for searching without the human customer service having to enter the search term themselves, improving the search efficiency.

[0089] When a customer encounters a problem during the shopping process, the customer finds a certain human customer service for consultation. At this time, in response to the customer's operation of consulting the customer service in the shopping process, a session between the human customer service and the customer can be established. When the customer is not satisfied with the service, the customer can choose to switch to another human customer service, and at this time, a switching instruction for the human customer service is generated. In response to the switching instruction of the human customer service, the background can establish a session between the switched human customer service and the customer, and generate a search operation of the switched human customer service in the session. Furthermore, based on at least the session information in the session between the human customer service before switching and the customer, and the attribute information of the human customer service after switching, at least one target search term to be searched by the switched human customer service is predicted. The switched human customer service can select from at least one target search term. In response to the target search term selected by the switched human customer service, the background can display the search results corresponding to the selected target search term.

[0090] The search processing method according to an embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings. Figure 4 The flowchart showing the search processing method according to an embodiment of the present disclosure is shown. Although the method operation steps as shown in the following embodiments or the accompanying drawings are provided in the present application, more or fewer operation steps may be included in the method based on routine or non-creative labor. In steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided in the embodiments of the present application. During the actual search processing process of the method or when the method is executed, it can be executed in the method order shown in the embodiments or the accompanying drawings or executed in parallel (for example, in an environment of parallel processors or multi-threaded processing). As Figure 4 shown, the search processing method may include:

[0091] Step S11, in response to the search operation of the current user, determine the service object of the current user.

[0092] Step S12, obtain the session information generated during the consultation of the service object and the order-related information of the service object.

[0093] Step S13, predict at least one target search term to be searched by the current user according to the session information and the order-related information.

[0094] Step S14, in response to the target search term selected by the current user, display the search results.

[0095] In an embodiment of the present disclosure, in response to a user's search operation, the service object of the current user is determined, and the session information generated during the consultation process of the service object and the order-related information of the service object are obtained. Then, at least one target search term that the current user is about to search for is predicted based on the session information and the order-related information, enabling the user to quickly locate the search term without multiple attempts and inductions, simplifying the search path. At the same time, after the current user selects a target search term, search results can be obtained immediately, enabling the current user to find the correct search results, thus more efficiently locating the solution and better providing more efficient and accurate services for the service object.

[0096] It should be noted that the search processing method provided in the embodiment of the present disclosure can be used not only in the aforementioned customer service scenario but also in other scenarios that require search processing. The embodiment of the present disclosure can provide search services not only for human customer service but also for other personnel. For example, the embodiment of the present disclosure can also be used in the following scenarios: a user uses the search engine of a video website to search for TV dramas and movies, or a user uses the search engine of a news website to search for news, or a user uses the search engine of a shopping website to search for clothes, etc. In these scenarios, the user who needs to perform the search is both the service object and the current user. The current user can obtain at least one target search through the above steps S11 to S14, and no longer needs to enter the search term by himself, reducing the user's operation, shortening the search time, and improving the search efficiency. In one example, when a user clicks on the "search control" of a shopping website, "dress", "long dress", "white dress", etc. are directly displayed to the user. When the user clicks on "dress", the search results corresponding to "dress" are displayed to the user.

[0097] Taking the aforementioned customer service scenario as an example below, Figure 4 a detailed description of the shown search processing method will be given.

[0098] In step S11, the search operation of the current user can be generated by the operation of the current human customer service triggering the search control in the session (as shown in Figure 1a ), or can be generated in response to the switching instruction of the dialogue robot (as shown in Figure 2a ), or can also be generated in response to the switching instruction of other human customer service (not shown), and the present disclosure does not limit this. The background can determine the service object of the current user in response to the search operation of the current user. In the embodiment of the present disclosure, the service object can represent the customer consulting the problem.

[0099] In step S12, the background can obtain the session information generated by the service object during the consultation process.

[0100] If a customer directly consults a certain human customer service, then the customer is the service object, the consulted human customer service is the current user, and the conversation information in the conversation between the customer and the human customer service is the conversation information generated by the service object during the consultation process.

[0101] If a customer first consults a chatbot and then switches to a human customer service for consultation, then the customer is the service object, the human customer service is the current user, and the conversation information in the conversation between the customer and the chatbot and / or the conversation information in the conversation between the customer and the human customer service is the conversation information generated by the service object during the consultation process.

[0102] If a customer first consults a certain human customer service and then switches to another human customer service for consultation, then the customer is the service object, the switched human customer service is the current user, and the conversation information in the conversation between the customer and the human customer service before switching and / or the conversation information in the conversation between the customer and the human customer service after switching is the conversation information generated by the service object during the consultation process.

[0103] The background can also obtain order-related information of the service object. The order-related information may include: factor information, refund reason, after-sales status, return status, etc. The order-related information is enumerable information. The embodiments of the present disclosure do not limit the order-related information.

[0104] Based on the conversation information, the basic demands of the service object can be determined. Based on the order-related information, the specific demands of the service object can be determined. Therefore, the conversation information and the order-related information can reflect the problems encountered by the service object, that is, the problems to be solved by the current user. In step S13, the background can predict at least one target search term that the current user is going to search according to the conversation information and the order-related information. As Figure 1b shown, the at least one target search term can be displayed on the current conversation page. As Figure 1c shown, a search page can be displayed, and the at least one target search term can be displayed on the search page. The current user can select one target search term from the at least one target search term. In step S14, in response to the target search term selected by the current user, the background can display the search results of the target search term (as Figure 3a 、 Figure 3b shown).

[0105] In a possible implementation manner, step S13 predicting at least one target search term that the current user is going to search according to the conversation information and the order-related information may include: determining a problem-solving strategy according to the conversation information and the order-related information; determining the search terms corresponding to the problem-solving strategy as candidate search terms; and determining at least one target search term from the candidate search terms.

[0106] In the embodiments of the present disclosure, the problem-solving strategy may be the FAQ questions or SOP questions configured by the business party. The problem-solving strategy is actually a solution that meets the user's demands and solves the customer's problems.

[0107] In a possible implementation manner, determining the problem-solving strategy according to the session information and the order-related information may include: using a Convolutional Neural Networks (CNN) to extract the feature vector of the session information as the first feature vector; encoding the order-related information based on the one-hot network to obtain a second feature vector; splicing the first feature vector and the second feature vector to obtain a third feature vector; inputting the third feature vector into a Deep Neural Network (DNN); and determining the problem-solving strategy according to the output result of the deep neural network.

[0108] Figure 5 Shows a schematic diagram of a classification model according to an embodiment of the present disclosure. As Figure 5 shown, the classification model includes a shallow network and a deep network, where the shallow network includes a one-hot network and a CNN network. The classification model mainly uses two types of data as features. The first type is session information, and the second type is order-related information. The background can use the CNN network to extract the feature vector of the session information, encode the order-related information based on the one-hot network to obtain the feature vector of the order-related information, then splice the two feature vectors, and input the spliced feature vector into the DNN network. After that, the background can obtain the classification result according to the output of the DNN network, so as to determine the problem-solving strategy.

[0109] In a possible implementation manner, obtaining the search term corresponding to the problem-solving strategy may include: determining the search term corresponding to the problem-solving strategy according to the association relationship between the problem-solving strategy and the search term.

[0110] The background may be configured with the association relationship between the problem-solving strategy and the search term. After determining the problem-solving strategy, the background may determine the search term corresponding to the problem-solving strategy according to the association relationship between the problem-solving strategy and the search term.

[0111] The association relationship between the problem-solving strategy and the search term may be a one-to-many relationship, that is, one problem-solving strategy may correspond to multiple search terms. In an example, the background may count the search terms used when each artificial customer service selects a certain problem-solving strategy, and establish the association relationship between the search terms with more usage times and the problem-solving strategy.

[0112] In a possible implementation, obtaining the search term corresponding to the problem-solving strategy may include: obtaining the historical search data of the current user; determining the search term corresponding to the problem-solving strategy according to the session information, the historical search data, and the problem-solving strategy.

[0113] In the embodiments of the present disclosure, the historical search data may include multiple search records, and a search record may include the identification information of the user (artificial customer service) for one search, the search term used, the located problem-solving strategy, and the session information.

[0114] The background can use an encode-decode model based on the session information, the determined problem-solving strategy, and the obtained historical search data to obtain the search term. In this way, search terms that conform to the respective usage habits of different users can be provided, which is convenient for search users to accept and improves the operation efficiency of search users.

[0115] In a possible implementation, determining at least one target search term from the candidate search terms may include: obtaining the attribute information of the current user, where the attribute information of the current user is used to represent the proficiency of the current user in the search service; determining at least one target search term from the candidate search terms according to the attribute information.

[0116] In the above embodiments, the background in the search processing method and the customer service information processing method may refer to a server, or a client, or may be jointly completed by the cooperation of the server and the client.

[0117] Figure 6 The flowchart of the customer service information processing method according to an embodiment of the present disclosure is shown. This method can be applied to a client. As Figure 6 shown, this method may include:

[0118] Step S21, in response to the switching instruction of the dialogue robot, establish a session between the artificial customer service and the service object.

[0119] Step S22, provide a search box for the artificial customer service on the session page.

[0120] Step S23, display a target search term in the search box, where the target search term is determined by the server according to the session information in the session between the dialogue robot and the service object.

[0121] When the service object selects to switch to the artificial customer service in the conversation with the dialogue robot, a switching instruction of the dialogue robot is generated at this time. Figure 7a A display example of the session page according to an embodiment of the present disclosure is shown. As Figure 7aAs shown, in response to the switching instruction of the dialogue machine, the client establishes a dialogue between the artificial customer service and the service object, and provides a search box for the artificial customer service on the session page.

[0122] In a possible implementation, the client can directly display a target search term in the search box. The target search term is determined by the server according to the session information in the session between the dialogue robot and the service object. The determination method can refer to Figure 4 the search processing method shown, which will not be elaborated here. Figure 7b Shows a display example of the session page according to an embodiment of the present disclosure. As Figure 7b shown, the client can directly display the target search term "rapid refund" in the search box on the session page.

[0123] In a possible implementation, the client can, in response to a search operation on the search box, display the search results of the target search term displayed in the search box (as Figure 3a and Figure 3b shown).

[0124] In a possible implementation, the client can provide a search control for the artificial customer service on the session page. In response to the triggering operation of the search control, a search page is displayed, and a search box is provided for the artificial customer service on the search page. For example, the client can provide a search control for the artificial customer service on the session page as Figure 7a shown. In response to the triggering operation of this search control, the Figure 7c shown search page is displayed, and a search box is provided for the artificial customer service on this search page. In one example, the client can directly display a target search term in the search box as Figure 7c shown.

[0125] In a possible implementation, when the server determines multiple target search terms, the client can display the multiple target search terms in the drop-down list of the search box, as Figure 1b and Figure 1c shown.

[0126] In a possible implementation, the client can obtain the target search term selected by the artificial customer service in the drop-down list and display the target search term in the search box, as Figure 7b shown.

[0127] In a possible implementation, obtain the target search term selected by the artificial customer service in the drop-down list and display the search results of the target search term, as Figure 3b shown.

[0128] In one example, the target search terms in the drop-down list can be arranged in descending order of scores. Further, the target search term in the search box can be the target search term with the highest score. The score of the target search term can be determined based on the number of times the target search term is searched by a certain customer service or all customer services, or can be determined by other means, and the present disclosure does not limit this. The client can obtain the scores of the target search terms from the server.

[0129] In the embodiments of the present disclosure, by displaying the target search terms in the drop-down list, more choices are given to the user, so that the user can find search terms that more conform to their own usage habits and expectations.

[0130] Figure 8 The block diagram of a search processing device according to an embodiment of the present disclosure is shown. The device is applied to an instant messaging session. The device includes a processor and a memory for storing instructions executable by the processor. When the processor executes the instructions, the following is implemented:

[0131] Respond to the search operation of the current user in the session;

[0132] Based on the session information in the session and the attribute information of the current user, predict at least one target search term that the current user is going to search for;

[0133] Respond to the target search term selected by the current user and display the search results.

[0134] In a possible implementation manner, when the processor implements the step of predicting at least one target search term that the current user is going to search for based on the session information in the session and the attribute information of the current user, it includes:

[0135] Determine a problem-solving strategy according to the session information;

[0136] Determine the search terms corresponding to the problem-solving strategy as candidate search terms;

[0137] Determine at least one target search term from the candidate search terms according to the attribute information of the current user.

[0138] In a possible implementation manner, the processor also implements the following steps:

[0139] Display the at least one target search term on the current session page;

[0140] Or,

[0141] Display a search page and display the at least one target search term on the search page.

[0142] In a possible implementation, the processor further implements the following steps:

[0143] In response to a switching instruction of the dialogue robot, generate a search operation of the current user in the session.

[0144] In a possible implementation, the attribute information of the current user is used to represent the proficiency of the current user in the search service.

[0145] Another search processing device according to an embodiment of the present disclosure includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, the following is implemented:

[0146] In response to a search operation of the current user, determine the service object of the current user;

[0147] Obtain the session information generated during the consultation of the service object and the order-related information of the service object;

[0148] According to the session information and the order-related information, predict at least one target search term that the current user is going to search for;

[0149] In response to the target search term selected by the current user, display the search results.

[0150] In a possible implementation, when the processor implements the step of predicting at least one target search term that the current user is going to search for according to the session information and the order-related information, it includes:

[0151] According to the session information and the order-related information, determine a problem-solving strategy;

[0152] Determine the search terms corresponding to the problem-solving strategy as candidate search terms;

[0153] Determine at least one target search term from the candidate search terms.

[0154] In a possible implementation, when the processor implements the step of determining a problem-solving strategy according to the session information and the order-related information, it includes:

[0155] Use a convolutional neural network to extract the feature vector of the session information as the first feature vector;

[0156] Based on the one-hot network, encode the order-related information to obtain a second feature vector;

[0157] Concatenate the first feature vector and the second feature vector to obtain a third feature vector;

[0158] Input the third feature vector into a deep neural network;

[0159] Determine a problem-solving strategy based on the output result of the deep neural network.

[0160] In a possible implementation, when the processor implements the step of obtaining the search term corresponding to the problem-solving strategy, it includes:

[0161] Determine the search term corresponding to the problem-solving strategy according to the association relationship between the problem-solving strategy and the search term.

[0162] In a possible implementation, when the processor implements the step of determining at least one target search term from the candidate search terms, it includes:

[0163] Obtain the attribute information of the current user, where the attribute information of the current user is used to represent the proficiency of the current user in the search service;

[0164] Determine at least one target search term from the candidate search terms according to the attribute information.

[0165] In a possible implementation, the processor also implements the following steps:

[0166] Display the at least one target search term on the current session page;

[0167] Or,

[0168] Display a search page and display the at least one target search term on the search page.

[0169] Figure 9 The block diagram of a customer service information processing device according to an embodiment of the present disclosure is shown. The device includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, it implements:

[0170] In response to the switching instruction of the dialogue robot, establish a session between the human customer service and the service object;

[0171] Obtain the session information in the session between the dialogue robot and the service object, and predict at least one target search term based on the session information;

[0172] Show the at least one target search term to the human customer service.

[0173] In a possible implementation, when the processor implements the step of showing the at least one target search term to the human customer service, it includes:

[0174] Display the at least one target search term on the current session page;

[0175] Or,

[0176] Display a search page and display the at least one target search term on the search page.

[0177] In a possible implementation, the processor further implements the following steps:

[0178] In response to the target search term selected by the human customer service, display search results.

[0179] In a possible implementation, the processor further implements the following steps:

[0180] In response to the operation of the service object consulting the customer service during the shopping process, establish a session between the chatbot and the service object.

[0181] Another customer service information processing device according to an embodiment of the present disclosure includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, it implements:

[0182] In response to a switching instruction of the chatbot, establish a session between the human customer service and the service object;

[0183] Obtain session information in the session between the chatbot and the service object, and predict at least one target search term based on the session information;

[0184] Display the search results of one of the at least one target search terms to the human customer service.

[0185] In a possible implementation, the processor further implements the following steps:

[0186] While displaying the search results of one of the at least one target search terms to the human customer service, display the at least one target search term.

[0187] Another customer service information processing device according to an embodiment of the present disclosure includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, it implements:

[0188] In response to a switching instruction of the chatbot, establish a session between the human customer service and the service object;

[0189] Provide a search box for the human customer service on the session page;

[0190] Display a target search term in the search box, and the target search term is determined by the server according to the session information in the session between the chatbot and the service object.

[0191] In a possible implementation, the processor further implements the following steps:

[0192] Provide a search control for the human customer service in the conversation page;

[0193] In response to a trigger operation of the search control, display a search page, and provide a search box for the human customer service in the search page.

[0194] In a possible implementation, the processor also implements the following steps:

[0195] When the server determines multiple target search terms, display the multiple target search terms in the drop-down list of the search box.

[0196] In a possible implementation, the processor also implements the following steps:

[0197] Obtain the target search term selected by the human customer service in the drop-down list, and display the target search term in the search box.

[0198] In a possible implementation, the processor also implements the following steps:

[0199] Obtain the target search term selected by the human customer service in the drop-down list, and display the search results of the target search term.

[0200] In a possible implementation, the processor also implements the following steps:

[0201] In response to a search operation on the search box, display the search results of the target search term displayed in the search box.

[0202] On the other hand, this application also provides a computer-readable storage medium, on which computer instructions are stored, and when the instructions are executed, the steps of the method described in any of the above embodiments are implemented.

[0203] The computer-readable storage medium may include a physical device for storing information, usually storing the information after digitization and then using a medium such as electricity, magnetism or optics to store it. The computer-readable storage medium described in this embodiment may include: devices for storing information using electrical energy, such as various memories, such as RAM, ROM, etc.; devices for storing information using magnetic energy, such as hard disks, floppy disks, magnetic tapes, magnetic core memories, bubble memories, USB flash drives; devices for storing information using optical methods, such as CDs or DVDs. Of course, there are also other ways of readable storage media, such as quantum memories, graphene memories, and so on.

[0204] In the 1990s, it was obvious to distinguish whether an improvement in a technology was a hardware improvement (e.g., improvement in circuit structures such as diodes, transistors, switches, etc.) or a software improvement (improvement in method processes). However, with the development of technology, many improvements in method processes today can be regarded as direct improvements in hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structures by programming the improved method processes into the hardware circuits. Therefore, it cannot be said that an improvement in a method process cannot be implemented with hardware entity modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user's programming of the device. The designer can program by himself to "integrate" a digital system on a piece of PLD without asking the chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called Hardware Description Language (HDL), and there is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones currently are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be clear that only by slightly logically programming the method process with the above-mentioned several hardware description languages and programming it into the integrated circuit can the hardware circuit implementing the logic method process be easily obtained.

[0205] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0206] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0207] For the convenience of description, the above devices are described by dividing them into various units according to functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0208] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0209] The present invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each flow and / or block of the flowchart illustrations and / or block diagrams, and combinations of flows and / or blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing apparatus create means for implementing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0210] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means that implement the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0211] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0212] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory. The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read only memory (ROM) or flash memory. Memory is an example of computer-readable media.

[0213] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. 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 disk read-only memory (CD-ROM), digital versatile disk (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 temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0214] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0215] 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 adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0216] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0217] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the method embodiment.

[0218] The above description is only for the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A search processing method, characterized in that, applied to an instant messaging session, the method includes: responding to a search operation of the current user in the session; based on the session information in the session and the attribute information of the current user, predicting at least one target search term that the current user is going to search for. The session is an instant messaging session established between the current user and a customer, and the current user provides customer service to the customer. The session information includes at least one of the following: text chat content, voice chat content, or a link shared by the customer; responding to the target search term selected by the current user and presenting search results; wherein, based on the session information in the session and the attribute information of the current user, predicting at least one target search term that the current user is going to search for includes: determining a problem-solving strategy according to the session information, and obtaining the historical search data of the current user; using an encode-decode model to determine the search term corresponding to the problem-solving strategy according to the session information, the historical search data, and the problem-solving strategy, and determining the search term corresponding to the problem-solving strategy as a candidate search term; determining at least one target search term from the candidate search terms according to the attribute information of the current user. The attribute information of the current user is used to represent the proficiency of the current user in the search service, and the attribute information of the current user is determined according to one or more of the search times of the current user, the number of search terms used, the evaluation of the current user by the customer, and the service duration of the current user.

2. The method according to claim 1, characterized in that, the method further includes: presenting the at least one target search term on the current session page; or, displaying a search page and presenting the at least one target search term on the search page.

3. The method according to claim 1, characterized in that, the method further includes: responding to a switching instruction of a chatbot and generating a search operation of the current user in the session.

4. A customer service information processing method, characterized in that, the method includes: responding to a switching instruction of a chatbot and establishing a session between an artificial customer service and a service object; obtaining the session information in the session between the chatbot and the service object, and predicting at least one target search term based on the session information and the attribute information of the artificial customer service; the session information includes at least one of the following: text chat content, voice chat content, or a link shared by the service object; presenting the at least one target search term to the artificial customer service; wherein, predicting at least one target search term based on the session information and the attribute information of the artificial customer service includes: determining a problem-solving strategy according to the session information, and obtaining the historical search data of the artificial customer service; using an encode-decode model to determine the search term corresponding to the problem-solving strategy according to the session information, the historical search data, and the problem-solving strategy; and determining the search term corresponding to the problem-solving strategy as a candidate search term; Determine at least one target search term from the candidate search terms according to the attribute information of the human customer service, where the attribute information of the human customer service is used to represent the proficiency of the human customer service in the search service, and the attribute information of the human customer service is determined according to one or more of the search times of the human customer service, the number of search terms used, the evaluation of the human customer service by customers, and the service duration of the human customer service.

5. The method according to claim 4, wherein, Displaying the at least one target search term to the human customer service includes: Displaying the at least one target search term on the current session page; Or, Displaying a search page and displaying the at least one target search term on the search page.

6. The method according to claim 4, wherein, The method further includes: In response to the target search term selected by the human customer service, displaying search results.

7. The method according to claim 4, wherein, The method further includes: In response to the operation of the service object consulting the customer service in the shopping process, establishing a session between the dialogue robot and the service object.

8. A customer service information processing method, wherein, The method includes: In response to the switching instruction of the dialogue robot, establishing a session between the human customer service and the service object; Obtaining the session information in the session between the dialogue robot and the service object, and predicting at least one target search term based on the session information and the attribute information of the human customer service; the session information includes at least one of the following: text chat content, voice chat content, or the link shared by the service object; Displaying the search result of one target search term among the at least one target search term to the human customer service; Among them, predicting at least one target search term based on the session information and the attribute information of the human customer service includes: determining a problem-solving strategy according to the session information, and obtaining the historical search data of the current user; using an encode-decode model to determine the search term corresponding to the problem-solving strategy according to the session information, the historical search data, and the problem-solving strategy, and determining the search term corresponding to the problem-solving strategy as the candidate search term; Determine at least one target search term from the candidate search terms according to the attribute information of the human customer service, where the attribute information of the human customer service is used to represent the proficiency of the human customer service in the search service, and the attribute information of the human customer service is determined according to one or more of the search times of the human customer service, the number of search terms used, the evaluation of the human customer service by customers, and the service duration of the human customer service.

9. The method according to claim 8, wherein, The method further includes: While displaying the search result of one target search term among the at least one target search term to the human customer service, displaying the at least one target search term.

10. A search processing method, wherein, The method includes: In response to the search operation of the current user, determining the service object of the current user; Obtain the session information generated by the service object during the consultation process and the order-related information of the service object; the session information includes at least one of the following: text chat content, voice chat content, or a link shared by the service object; Predict at least one target search term that the current user is about to search based on the session information and the order-related information; Display search results in response to the target search term selected by the current user; Among them, predicting at least one target search term that the current user is about to search based on the session information and the order-related information includes: Determine a problem-solving strategy based on the session information and the order-related information; Obtain the historical search data of the current user; use an encode-decode model to determine the search term corresponding to the problem-solving strategy based on the session information, the historical search data, and the problem-solving strategy, and determine the search term corresponding to the problem-solving strategy as a candidate search term; Obtain the attribute information of the current user, where the attribute information of the current user is used to represent the proficiency of the current user in the search service; determine at least one target search term from the candidate search terms; determine at least one target search term from the candidate search terms.

11. The method according to claim 10, characterized in that, Determining a problem-solving strategy based on the session information and the order-related information includes: Use a convolutional neural network to extract the feature vector of the session information as the first feature vector; Encode the order-related information based on the one-hot network to obtain a second feature vector; Concatenate the first feature vector and the second feature vector to obtain a third feature vector; Input the third feature vector into a deep neural network; Determine a problem-solving strategy based on the output result of the deep neural network.

12. The method according to claim 10, characterized in that, The method further includes: Display the at least one target search term on the current session page; Or, Display a search page and display the at least one target search term on the search page.

13. A customer service information processing method, characterized in that, The method includes: In response to the switching instruction of the chatbot, establish a session between the human customer service and the service object; Provide a search box for the human customer service on the session page; Display a target search term in the search box, where the target search term is determined by the server based on the session information in the session between the chatbot and the service object and the attribute information of the human customer service, and the session information includes at least one of the following: text chat content, voice chat content, or a link shared by the service object; Among them, determining at least one target search term according to the conversation information in the conversation between the dialogue robot and the service object and the attribute information of the human customer service includes: determining a problem-solving strategy according to the conversation information, and obtaining the historical search data of the human customer service; using an encode-decode model to determine the search term corresponding to the problem-solving strategy according to the conversation information, the historical search data, and the problem-solving strategy; and determining the search term corresponding to the problem-solving strategy as a candidate search term. Determining at least one target search term from the candidate search terms according to the attribute information of the human customer service, where the attribute information of the human customer service is used to represent the proficiency of the human customer service in the search service, and the attribute information of the human customer service is determined according to one or more of the search times of the human customer service, the number of search terms used, the evaluation of the human customer service by the customer, and the service duration of the human customer service.

14. The method according to claim 13, wherein, the method further includes: providing a search control for the human customer service on the conversation page; responding to the trigger operation of the search control, displaying a search page, and providing a search box for the human customer service on the search page.

15. The method according to claim 13 or 14, wherein, the method further includes: when the server determines multiple target search terms, displaying the multiple target search terms in the drop-down list of the search box.

16. The method according to claim 15, wherein, the method further includes: obtaining the target search term selected by the human customer service in the drop-down list, and displaying the target search term in the search box.

17. The method according to claim 15, wherein, the method further includes: obtaining the target search term selected by the human customer service in the drop-down list, and displaying the search results of the target search term.

18. The method according to claim 13, wherein, the method further includes: responding to the search operation on the search box, and displaying the search results of the target search term displayed in the search box.

19. A search processing device, wherein, applied to an instant messaging conversation, the device includes a processor and a memory for storing processor-executable instructions, and when the processor executes the instructions, it realizes: responding to the search operation of the current user in the conversation; predicting at least one target search term that the current user wants to search based on the conversation information in the conversation and the attribute information of the current user; the conversation is an instant messaging conversation established between the current user and the customer, the current user provides customer service to the customer, and the conversation information includes at least one of the following: text chat content, voice chat content, or a link shared by the customer; responding to the target search term selected by the current user, and displaying the search results; wherein, predicting at least one target search term that the current user wants to search based on the conversation information in the conversation and the attribute information of the current user includes: Determine a problem-solving strategy based on the session information, and obtain the historical search data of the human customer service; use an encode-decode model to determine the search term corresponding to the problem-solving strategy according to the session information, the historical search data, and the problem-solving strategy; determine the search term corresponding to the problem-solving strategy as the candidate search term; Determine at least one target search term from the candidate search terms according to the attribute information of the current user, where the attribute information of the current user is used to represent the proficiency of the current user in the search service, and the attribute information of the current user is determined according to one or more of the number of searches of the current user, the number of search terms used, the evaluation of the current user by the customer, and the service duration of the current user.

20. The apparatus according to claim 19, characterized in that, the processor further implements the following steps: display the at least one target search term on the current session page; or, display a search page, and display the at least one target search term on the search page.

21. The apparatus according to claim 19, characterized in that, the processor further implements the following steps: generate a search operation of the current user in the session in response to a switching instruction of the dialogue robot.

22. A customer service information processing apparatus, characterized in that, the apparatus includes a processor and a memory for storing instructions executable by the processor, and when the processor executes the instructions, it implements: establish a session between the human customer service and the service object in response to a switching instruction of the dialogue robot; obtain the session information in the session between the dialogue robot and the service object, and predict at least one target search term based on the session information and the attribute information of the human customer service; the session information includes at least one of the following: text chat content, voice chat content, or a link shared by the service object; display the at least one target search term to the human customer service; wherein, predicting at least one target search term based on the session information and the attribute information of the human customer service includes: determining a problem-solving strategy according to the session information, and obtaining the historical search data of the human customer service; using an encode-decode model to determine the search term corresponding to the problem-solving strategy according to the session information, the historical search data, and the problem-solving strategy; determining the search term corresponding to the problem-solving strategy as the candidate search term; determine at least one target search term from the candidate search terms according to the attribute information of the human customer service, where the attribute information of the human customer service is used to represent the proficiency of the human customer service in the search service, and the attribute information of the human customer service is determined according to one or more of the number of searches of the human customer service, the number of search terms used, the evaluation of the human customer service by the customer, and the service duration of the human customer service.

23. The apparatus according to claim 22, characterized in that, when the processor implements the step of displaying the at least one target search term to the human customer service, it includes: display the at least one target search term on the current session page; or, Display a search page and present the at least one target search term on the search page.

24. The apparatus according to claim 22, wherein, the processor further implements the following steps: In response to the target search term selected by the human customer service, display search results.

25. The apparatus according to claim 22, wherein, the processor further implements the following steps: In response to the operation of the service object consulting the customer service during the shopping process, establish a session between the dialogue robot and the service object.

26. A customer service information processing apparatus, wherein, the apparatus includes a processor and a memory for storing processor-executable instructions, and when the processor executes the instructions, it implements: In response to a switching instruction of the dialogue robot, establish a session between the human customer service and the service object; Obtain session information in the session between the dialogue robot and the service object, and predict at least one target search term based on the session information and the attribute information of the human customer service; the session information includes at least one of the following: text chat content, voice chat content, or a link shared by the service object; Display the search result of one of the at least one target search terms to the human customer service; Among them, predicting at least one target search term based on the session information and the attribute information of the human customer service includes: according to the session information, determine a problem-solving strategy, and obtain the historical search data of the human customer service; use an encode-decode model to determine the search term corresponding to the problem-solving strategy according to the session information, the historical search data, and the problem-solving strategy; determine the search term corresponding to the problem-solving strategy as a candidate search term; According to the attribute information of the human customer service, determine at least one target search term from the candidate search terms, the attribute information of the human customer service is used to represent the proficiency of the human customer service in the search service, and the attribute information of the human customer service is determined according to one or more of the search times of the human customer service, the number of search terms used, the evaluation of the human customer service by the customer, and the service duration of the human customer service.

27. The apparatus according to claim 26, wherein, the processor further implements the following steps: While displaying the search result of one of the at least one target search terms to the human customer service, display the at least one target search term.

28. A search processing apparatus, wherein, the apparatus includes a processor and a memory for storing processor-executable instructions, and when the processor executes the instructions, it implements: In response to the search operation of the current user, determine the service object of the current user; Obtain the session information generated by the service object during the consultation process and the order-related information of the service object; The session information includes at least one of the following: text chat content, voice chat content, or a link shared by the service object; Predict at least one target search term that the current user is about to search according to the session information and the order-related information; In response to the target search term selected by the current user, display the search result; Among them, predicting at least one target search term that the current user is about to search according to the session information and the order-related information includes: Determining a problem-solving strategy according to the session information and the order-related information; obtaining the historical search data of the current user; using an encode-decode model to determine the search term corresponding to the problem-solving strategy according to the session information, the historical search data, and the problem-solving strategy, and determining the search term corresponding to the problem-solving strategy as a candidate search term; Obtaining the attribute information of the current user, where the attribute information of the current user is used to represent the proficiency of the current user in the search service; determining at least one target search term from the candidate search terms according to the attribute information; Determining at least one target search term from the candidate search terms.

29. The device according to claim 28, wherein, when the processor implements the step of determining a problem-solving strategy according to the session information and the order-related information, it includes: Using a convolutional neural network to extract the feature vector of the session information as the first feature vector; Encoding the order-related information based on the one-hot network to obtain a second feature vector; Concatenating the first feature vector and the second feature vector to obtain a third feature vector; Inputting the third feature vector into a deep neural network; Determining a problem-solving strategy according to the output result of the deep neural network.

30. The device according to claim 28, wherein, The processor also implements the following steps: Displaying the at least one target search term on the current session page; Or, Displaying a search page and displaying the at least one target search term on the search page.

31. A customer service information processing device, wherein, The device includes a processor and a memory for storing instructions executable by the processor. When the processor executes the instructions, it implements: Responding to a switching instruction of a dialogue robot to establish a session between an artificial customer service and a service object; Providing a search box for the artificial customer service on the session page; Displaying a target search term in the search box, where the target search term is determined by the server according to the session information in the session between the dialogue robot and the service object and the attribute information of the artificial customer service, and the session information includes at least one of the following: text chat content, voice chat content, or a link shared by the service object; Among them, determining at least one target search term according to the session information in the session between the dialogue robot and the service object and the attribute information of the artificial customer service includes: determining a problem-solving strategy according to the session information, and obtaining the historical search data of the artificial customer service; using an encode-decode model to determine the search term corresponding to the problem-solving strategy according to the session information, the historical search data, and the problem-solving strategy; and determining the search term corresponding to the problem-solving strategy as a candidate search term; Determine at least one target search term from the candidate search terms according to the attribute information of the human customer service, where the attribute information of the human customer service is used to represent the proficiency of the human customer service in the search service, and the attribute information of the human customer service is determined according to one or more of the search times of the human customer service, the number of search terms used, the evaluation of the human customer service by customers, and the service duration of the human customer service.

32. The apparatus according to claim 31, wherein, the processor further implements the following steps: Provide a search control for the human customer service on the session page; In response to the triggering operation of the search control, display a search page, and provide a search box for the human customer service on the search page.

33. The apparatus according to claim 31 or 32, wherein, the processor further implements the following steps: When multiple target search terms are determined on the server, display the multiple target search terms in the drop-down list of the search box.

34. The apparatus according to claim 33, wherein, the processor further implements the following steps: Obtain the target search term selected by the human customer service in the drop-down list, and display the target search term in the search box.

35. The apparatus according to claim 33, wherein, the processor further implements the following steps: Obtain the target search term selected by the human customer service in the drop-down list, and display the search results of the target search term.

36. The apparatus according to claim 31, wherein, the processor further implements the following steps: In response to the search operation on the search box, display the search results of the target search term displayed in the search box.

37. A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor, enable the processor to execute the search processing method according to any one of claims 1-3, 10-12.

38. A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor, enable the processor to execute the customer service information processing method according to any one of claims 4-7, 8-9, 13-18.

Images