Abnormal prompt generation method and device, electronic equipment, storage medium and program product

Abstract

The invention relates to an exception prompt generation method and device, electronic equipment, a storage medium and a program product, and the method comprises the steps: obtaining input data which is obtained by the electronic equipment under the condition that response data comprises target exception information, the response data is response data which is obtained by the electronic equipment in response to an interaction operation on the target page and corresponds to the interaction operation, and the input data comprises target abnormal information; inputting the input data into an exception handling model, outputting a target exception prompt, the exception handling model being used for determining a target exception type to which the exception response event belongs based on the target exception information, and determining a target prompt template corresponding to the target exception type based on an exception handling database, generating a target prompt copywriting corresponding to the exception response event based on the target exception information, filling the target prompt copywriting into a copywriting slot of the target prompt template, and generating a target exception prompt; the exception handling database is used for indicating the corresponding relation between the multiple exception types and the multiple prompt templates.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and in particular, to an abnormal prompt generation method, apparatus, electronic device, storage medium, and program product. Background Art

[0002] In some application programs that include a large number of human-computer interaction scenarios, various abnormal situations will inevitably occur, such as network abnormalities, abnormal access to service interfaces, and abnormalities that do not meet specific service scenario rules. The abnormal situations of service scenarios occur less frequently than the normal scenarios of service scenarios. Therefore, currently, when an abnormal situation occurs, overly general and simple prompt messages such as "Network abnormality, please try again later" are often used for prompting, seriously affecting the user experience. Summary of the Invention

[0003] To solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides an abnormal prompt generation method, apparatus, electronic device, storage medium, and program product.

[0004] In a first aspect of an embodiment of the present disclosure, an abnormal prompt generation method is provided. The method includes: obtaining input data, where the input data is obtained when an electronic device responds to an abnormal response event for an interaction operation on a target page, and the input data includes the target abnormal information; inputting the input data into an abnormal processing model to output a target abnormal prompt, where the abnormal processing model is used to determine a target abnormal type to which the abnormal response event belongs based on the target abnormal information, determine a target prompt template corresponding to the target abnormal type based on an abnormal processing database, generate a target prompt text corresponding to the abnormal response event based on the target abnormal information, fill the target prompt text into a text slot of the target prompt template to generate the target abnormal prompt; and the abnormal processing database is used to indicate the corresponding relationship between multiple abnormal types and multiple prompt templates.

[0005] In some embodiments of the present disclosure, the input data further includes interaction-related information, and the interaction-related information is used to indicate an interaction page corresponding to the interaction operation; before determining the target prompt template corresponding to the target abnormal type based on the abnormal processing database, it further includes: determining a target service scenario to which the interaction page belongs based on the interaction-related information; determining the target prompt template corresponding to the target abnormal type based on the abnormal processing database includes: determining the target prompt template corresponding to the target abnormal type and the target service scenario based on the abnormal processing database; where the abnormal processing database is used to indicate the corresponding relationship between the multiple abnormal types, multiple service scenarios, and the multiple prompt templates.

[0006] In some embodiments of the present disclosure, generating the target prompt text based on the target abnormal information includes: obtaining the page information corresponding to the interaction page from the business database, where the business database includes the page information corresponding to multiple pages, and the multiple pages include the interaction page; determining the target business characteristics of the target business scenario based on the page information corresponding to the interaction page; and determining the target prompt text based on the target abnormal information and the target business characteristics.

[0007] In some embodiments of the present disclosure, determining the target prompt text based on the target abnormal information and the target business characteristics includes: determining the target prompt text that matches the target abnormal information and the target business characteristics based on a corpus, where the corpus is used to indicate various prompt texts.

[0008] In some embodiments of the present disclosure, the target prompt template further includes a recommendation function slot; after determining the target business characteristics of the target business scenario based on the page information corresponding to the interaction page, it further includes: determining at least one recommended solution that matches the target business characteristics; filling the target prompt text into the text slot of the target prompt template to generate the target abnormal prompt, including: filling the target prompt text into the text slot, and filling the at least one recommended solution into the recommendation function slot to generate the target abnormal prompt.

[0009] In some embodiments of the present disclosure, the input data further includes recommendation auxiliary information, where the recommendation auxiliary information includes at least one of the following: relevant operation information within a preset duration before the interaction operation, source path information corresponding to the target page, and user characteristic information; the target prompt template further includes a recommendation function slot; filling the target prompt text into the text slot of the target prompt template to generate the target abnormal prompt, including: determining at least one recommended solution that matches the recommendation auxiliary information; filling the target prompt text into the text slot, and filling the at least one recommended solution into the recommendation function slot to generate the target abnormal prompt.

[0010] In some embodiments of the present disclosure, after inputting the input data into the abnormal processing model and outputting the target abnormal prompt, the method further includes: obtaining the target operation information for the target abnormal prompt; using the target operation information, the target abnormal prompt, and the input data as feedback training data to perform feedback training on the abnormal processing model, so as to determine the feedback type of the feedback training data according to the target operation information, and adjust the target loss function according to the feedback type, and adjust the abnormal processing model according to the adjusted target loss function.

[0011] In some embodiments of the present disclosure, when applied to a server, the obtaining of input data includes: receiving an exception prompt request from the electronic device, where the exception prompt request carries the input data, and the exception prompt request is used to request the server to obtain an exception prompt corresponding to the input data; after inputting the input data into an exception handling model and outputting a target exception prompt, the method further includes: sending the target exception prompt to the electronic device so that the electronic device can display the target exception prompt on the target page.

[0012] In a second aspect of the embodiments of the present disclosure, there is provided an exception prompt generation device, which includes: an obtaining module, configured to obtain input data, where the input data is obtained when the electronic device has an exception response event in response to an interaction operation on a target page, and the input data includes the target exception information; an output module, configured to input the input data into an exception handling model and output a target exception prompt, where the exception handling model is used to determine the target exception type to which the exception response event belongs based on the target exception information, determine a target prompt template corresponding to the target exception type based on an exception handling database, generate a target prompt copy corresponding to the exception response event based on the target exception information, and fill the target prompt copy into a copy slot of the target prompt template to generate the target exception prompt; the exception handling database is used to indicate the corresponding relationship between multiple exception types and multiple prompt templates.

[0013] In some embodiments of the present disclosure, the input data further includes interaction-related information, where the interaction-related information is used to indicate the interaction page corresponding to the interaction operation; before determining the target prompt template corresponding to the target exception type based on the exception handling database, it further includes: determining the target business scenario to which the interaction page belongs based on the interaction-related information; determining the target prompt template corresponding to the target exception type based on the exception handling database includes: determining the target prompt template corresponding to the target exception type and the target business scenario based on the exception handling database; where the exception handling database is used to indicate the corresponding relationship between the multiple exception types, multiple business scenarios, and the multiple prompt templates.

[0014] In some embodiments of the present disclosure, generating the target prompt copy based on the target exception information includes: obtaining the page information corresponding to the interaction page from a business database, where the business database includes the page information corresponding to multiple pages, and the multiple pages include the interaction page; determining the target business characteristics of the target business scenario based on the page information corresponding to the interaction page; determining the target prompt copy based on the target exception information and the target business characteristics.

[0015] In some embodiments of the present disclosure, determining the target prompt text based on the target exception information and the target service feature includes: determining the target prompt text that matches the target exception information and the target service feature based on a corpus, where the corpus is used to indicate various prompt texts.

[0016] In some embodiments of the present disclosure, the target prompt template further includes a recommendation function slot; after determining the target service feature of the target service scenario based on the page information corresponding to the interaction page, it further includes: determining at least one recommendation solution that matches the target service feature; filling the target prompt text into the text slot of the target prompt template to generate the target exception prompt includes: filling the target prompt text into the text slot, and filling the at least one recommendation solution into the recommendation function slot to generate the target exception prompt.

[0017] In some embodiments of the present disclosure, the input data further includes recommendation auxiliary information, and the recommendation auxiliary information includes at least one of the following: relevant operation information within a preset duration before the interaction operation, source path information corresponding to the target page, user feature information; the target prompt template further includes a recommendation function slot; filling the target prompt text into the text slot of the target prompt template to generate the target exception prompt includes: determining at least one recommendation solution that matches the recommendation auxiliary information; filling the target prompt text into the text slot, and filling the at least one recommendation solution into the recommendation function slot to generate the target exception prompt.

[0018] In some embodiments of the present disclosure, after inputting the input data into the exception handling model and outputting the target exception prompt, the method further includes: obtaining target operation information for the target exception prompt; using the target operation information, the target exception prompt, and the input data as feedback training data to perform feedback training on the exception handling model, so as to determine the feedback type of the feedback training data according to the target operation information, and adjust the target loss function according to the feedback type, and adjust the exception handling model according to the adjusted target loss function.

[0019] In some embodiments of the present disclosure, when applied to a server, the obtaining module is specifically configured to receive an exception prompt request from the electronic device, where the exception prompt request carries the input data, and the exception prompt request is used to request the server to obtain an exception prompt corresponding to the input data; the apparatus further includes: a sending module, configured to send the target exception prompt to the electronic device after inputting the input data into the exception handling model and outputting the target exception prompt, so that the electronic device displays the target exception prompt on the target page.

[0020] In a third aspect of the embodiments of the present disclosure, an electronic device is provided. The electronic device includes a processor, a memory, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the method for generating an exception prompt as described in the first aspect is implemented.

[0021] In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, the method for generating an exception prompt as described in the first aspect is implemented.

[0022] In a fifth aspect of the embodiments of the present disclosure, a computer program product is provided. The computer program product includes a computer program. When the computer program product runs on a processor, the processor is caused to execute the computer program to implement the method for generating an exception prompt as described in the first aspect.

[0023] In a sixth aspect of the embodiments of the present disclosure, a chip is provided. The chip includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is configured to run program instructions to implement the method for generating an exception prompt as described in the first aspect.

[0024] The technical solution provided by the embodiments of the present disclosure has the following advantages compared with the prior art: obtaining input data, which is obtained when an electronic device responds to an abnormal response event during an interaction operation on a target page, and the input data includes the target abnormal information; inputting the input data into an abnormal processing model to output a target abnormal prompt. The abnormal processing model is used to determine the target abnormal type to which the abnormal response event belongs based on the target abnormal information, determine the target prompt template corresponding to the target abnormal type based on an abnormal processing database, generate a target prompt copy corresponding to the abnormal response event based on the target abnormal information, and fill the target prompt copy into the copy slot of the target prompt template to generate the target abnormal prompt; the abnormal processing database is used to indicate the corresponding relationship between multiple abnormal types and multiple prompt templates. In the embodiments of the present disclosure, when there is target abnormal information in the response data of the interaction operation on the target page that can determine that an abnormal response event has occurred, the target abnormal information is used as input data and input into the abnormal processing model, so that the abnormal processing model can determine the target abnormal type to which the abnormal response event belongs according to the target abnormal information, then determine the target prompt template corresponding to the target abnormal type based on the abnormal processing database, and generate a target prompt copy based on the target abnormal information, and fill the target prompt copy into the copy slot of the target prompt template to generate the target abnormal prompt. In this way, a target abnormal prompt matching the abnormal response event can be determined, the diversity of the abnormal prompt can be improved, and the user experience can be improved. Description of the Drawings

[0025] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0026] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0027] Figure 1 One of the flow diagrams of the abnormal prompt generation method provided by the embodiment of the present disclosure;

[0028] Figure 2 One of the interface diagrams of the abnormal prompt generation method provided by the embodiment of the present disclosure;

[0029] Figure 3 One of the interface diagrams of the abnormal prompt generation method provided by the embodiment of the present disclosure;

[0030] Figure 4 One of the interface diagrams of the abnormal prompt generation method provided by the embodiment of the present disclosure;

[0031] Figure 5 One of the flow diagrams of the abnormal prompt generation method provided by the embodiment of the present disclosure;

[0032] Figure 6 The structural block diagram of an abnormal prompt generation device provided by the embodiment of the present disclosure;

[0033] Figure 7 The structural block diagram of an electronic device provided by the embodiment of the present disclosure. Detailed implementation manners

[0034] In order to be able to more clearly understand the above objects, features, and advantages of the present disclosure, the following will further describe the solutions of the present disclosure. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other.

[0035] Many specific details are set forth in the following description in order to fully understand the present disclosure, but the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all of the embodiments.

[0036] The terms "first", "second", etc. in the description and claims of the present disclosure are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are usually of the same category, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the description and claims means at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the associated objects before and after.

[0037] The electronic device in the embodiments of the present disclosure can be a mobile electronic device or a non-mobile electronic device. The mobile electronic device can be a mobile phone, a tablet computer, a notebook computer, a handheld computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc.; the non-mobile electronic device can be a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc.; the embodiments of the present disclosure do not make specific limitations.

[0038] The execution subject of the abnormal prompt generation method provided by the embodiments of the present disclosure can be the above-mentioned electronic device or a functional module and / or functional entity in the electronic device that can implement the abnormal prompt generation method, or a server or a functional module and / or functional entity in the server that can implement the abnormal prompt generation method. Specifically, it can be determined according to actual usage requirements, and the embodiments of the present disclosure do not make limitations.

[0039] Next, with reference to the accompanying drawings, the abnormal prompt generation method provided by the embodiments of the present disclosure will be described in detail through specific embodiments and their application scenarios.

[0040] As Figure 1 shown, the embodiments of the present disclosure provide an abnormal prompt generation method, which may include the following steps 101 to 102.

[0041] 101. Obtain input data.

[0042] Among them, the input data is obtained when the electronic device responds to an abnormal response event during an interaction operation on a target page, and the input data includes the target abnormal information.

[0043] Among them, the target page can be a page of a consumer application, an instant messaging application, a payment application, a financial management application, or a page of other applications, which is not limited here.

[0044] Among them, the interaction operation can be a trigger operation on a function control in the target page, a trigger operation on a jump link in the target page, or other operations, which is not limited here.

[0045] Among them, the response data can be interface return data obtained through interface calls or data obtained through SDK calls, which is not limited here. Among them, the interface can be a page rendering interface, a read / write interface, an interface that hits specific business rules, which is not limited here.

[0046] Among them, the target exception information can include page rendering interface error messages, read / write interface error messages, SDK call error messages, SDK call no response messages, information on hitting specific business rules, etc., which is not limited here.

[0047] Among them, the target exception information can specifically include interface error code information and / or detailed exception description information, which is not limited here. If the response data is interface return data obtained through interface calls, the target exception information can include interface error code information, or can include both interface error code information and detailed exception description information; if the response data is data obtained through SDK calls, the target exception information can include detailed exception description information.

[0048] 102. Input the input data into the exception handling model to output a target exception prompt.

[0049] Among them, the exception handling model is used to determine the target exception type to which the exception response event belongs based on the target exception information, determine the target prompt template corresponding to the target exception type based on the exception handling database, generate the target prompt text corresponding to the exception response event based on the target exception information, and fill the target prompt text into the text slot of the target prompt template to generate the target exception prompt; the exception handling database is used to indicate the correspondence between multiple exception types and multiple prompt templates.

[0050] In the embodiments of the present disclosure, the target exception type can be determined according to the interface error code information and / or the detailed exception description information, and the target prompt text can be determined according to the interface error code information and / or the detailed exception description information, which is not limited here.

[0051] Among them, the target exception type can include payment failure, out-of-stock of goods, page loading error, etc., which is not limited here.

[0052] Among them, the target prompt text can include "operation error", "insufficient product inventory", "payment information error", "network exception", etc., which are not limited here.

[0053] In some embodiments of the present disclosure, in the exception handling database, the multiple exception types and the multiple prompt templates can have a one-to-one correspondence or a one-to-many correspondence, which is not limited here.

[0054] Among them, the exception handling model can be a pre-trained model for generating exception prompts for exception response events, or a large-scale language model with logical reasoning ability, based on the Transformer architecture, which learns knowledge of grammar, semantics, and application of language through unsupervised learning on a large amount of text data, so as to be able to generate natural and fluent text, understand and process various natural language tasks.

[0055] In the embodiments of the present disclosure, when there is target exception information in the response data of the interaction operation on the target page that can determine an exception response event, the target exception information is used as input data and input into the exception handling model, so that the exception handling model can determine the target exception type to which the exception response event belongs based on the target exception information, then determine the target prompt template corresponding to the target exception type based on the exception handling database, and generate a target prompt text based on the target exception information, and fill the target prompt text into the text slot of the target prompt template to generate the target exception prompt. In this way, the target exception prompt matching the exception response event can be determined, the diversity of the exception prompt can be improved, and the user experience can be improved.

[0056] In some embodiments of the present disclosure, the input data further includes interaction-related information, and the interaction-related information is used to indicate the interaction page corresponding to the interaction operation; before determining the target prompt template corresponding to the target exception type based on the exception handling database, it further includes: determining the target business scenario to which the interaction page belongs based on the interaction-related information; determining the target prompt template corresponding to the target exception type based on the exception handling database includes: determining the target prompt template corresponding to the target exception type and the target business scenario based on the exception handling database; wherein, the exception handling database is used to indicate the corresponding relationship between the multiple exception types, multiple business scenarios and the multiple prompt templates.

[0057] Among them, the interaction-related information can include information about the target page and information about the interaction operation, or can be information about the interaction page, which can be specifically determined according to the actual situation and is not limited here.

[0058] Among them, the information of the page can include the identifier of the page, the link of the page, the thumbnail of the page, etc., which can be specifically determined according to the actual situation and is not limited here.

[0059] Among them, the information of the interaction operation may include the information of the operation object (function control or jump link) corresponding to the interaction operation, which is not limited here.

[0060] In some embodiments of the present disclosure, the exception handling database is used to indicate multiple exception types and multiple corresponding relationships corresponding to each exception type, and the multiple corresponding relationships corresponding to each exception type are used to indicate multiple first service scenarios and the prompt templates corresponding to each first service scenario. That is, under each exception type, there are corresponding relationships between multiple first service scenarios and multiple first prompt templates.

[0061] In the embodiments of the present disclosure, by combining the exception type and the service scenario, a prompt template that better matches the exception response event can be determined, and then a more matching exception prompt can be generated.

[0062] In some embodiments of the present disclosure, generating the target prompt copy based on the target exception information specifically includes: obtaining the page information corresponding to the interaction page from the service database, where the service database includes the page information corresponding to multiple pages, and the multiple pages include the interaction page; determining the target service characteristics of the target service scenario based on the page information corresponding to the interaction page; and determining the target prompt copy based on the target exception information and the target service characteristics.

[0063] Among them, the page information corresponding to the interaction page is the page information of a normal interaction page, which may be a thumbnail of a normal interaction page or the page description information of a normal interaction page, which is not limited here.

[0064] Among them, the target service characteristics may include service types, service features, etc., which are not limited here. Among them, the service types may include communication, insurance, consumption, wealth management, etc., which are not limited here; the service features may include registration, payment, viewing user agreements, purchasing products, etc., which are not limited here.

[0065] In the embodiments of the present disclosure, by combining the service characteristics of the interaction page and the target exception information, a more matching target prompt copy can be determined, which can improve the accuracy of the exception prompt and the user experience.

[0066] In some embodiments of the present disclosure, determining the target prompt copy based on the target exception information and the target service characteristics specifically includes: determining the target prompt copy that matches the target exception information and the target service characteristics based on the corpus, where the corpus is used to indicate multiple prompt copies.

[0067] Among them, the corpus may include various prompt texts. The exception handling model can generate the target prompt text that matches the target exception information and the target business feature by learning various prompt texts. The corpus may include various rules for generating texts, and each rule for generating texts corresponds to a prompt text. The exception handling model generates the target prompt text that matches the target exception information and the target business feature by learning various rules for generating texts. The corpus may also include the corresponding relationships between various exception information, various business features, and various text templates. The exception handling model can first determine the target text template that matches the target exception information and the target business feature, and then generate the target prompt text based on the target text template, the target exception information, and the target business feature. Specifically, it can be determined according to the actual situation and is not limited here.

[0068] In the embodiments of the present disclosure, a more matching target prompt text can be determined in combination with the corpus, which can improve the accuracy of exception prompts and improve the user experience.

[0069] In some embodiments of the present disclosure, the target exception prompt generated by the exception handling model based on the input data can be a toast that only includes the prompt text, or a pop-up window form prompt that includes the prompt text and the recommended solution, or a baffle page form prompt that includes the prompt text and the recommended solution, which is not limited here.

[0070] In some embodiments of the present disclosure, when the target exception prompt is a pop-up window form prompt or a baffle page form prompt, the target prompt template may include a fixed recommended solution or a recommended function slot for filling the recommended solution, which is not limited here.

[0071] In some embodiments of the present disclosure, the target prompt template further includes a recommended function slot; after determining the target business feature of the target business scenario based on the page information corresponding to the interaction page, it further includes: determining at least one recommended solution that matches the target business feature; and filling the target prompt text into the text slot of the target prompt template to generate the target exception prompt, including: filling the target prompt text into the text slot, and filling the at least one recommended solution into the recommended function slot to generate the target exception prompt.

[0072] Among them, the recommended solution may be a recommended function control or a jump link, or other solutions, which is not limited here.

[0073] In the embodiments of the present disclosure, at least one recommended solution is determined based on the business feature of the interaction page, so that a recommended solution related to the interaction page can be recommended to the user, and a more interesting recommended solution can be provided to the user, which can improve the user experience.

[0074] In some embodiments of the present disclosure, the input data further includes recommendation auxiliary information, which includes at least one of the following: relevant operation information within a preset duration before the interaction operation, source path information corresponding to the target page, and user characteristic information; the target prompt template further includes a recommendation function slot; filling the target prompt copy into the copy slot of the target prompt template to generate the target exception prompt specifically includes: determining at least one recommendation scheme that matches the recommendation auxiliary information; filling the target prompt copy into the copy slot, and filling the at least one recommendation scheme into the recommendation function slot to generate the target exception prompt.

[0075] Among them, the preset duration can be determined according to the actual situation and is not limited here.

[0076] Among them, the relevant operation information within the preset duration before the interaction operation may include operation behaviors such as products browsed, links clicked, and residence time within the preset duration, which is not limited here.

[0077] Among them, the source path information corresponding to the target page may include entering the target page through the live broadcast room, entering the target page through the advertisement link, entering the target page through the recommendation page, entering the target page through the SMS delivery, etc., which is not limited here.

[0078] Among them, the user characteristic information can be preset and can be determined according to the user's settings, which is not limited here.

[0079] In the embodiments of the present disclosure, at least one recommendation scheme determined according to the recommendation auxiliary information can better meet the user's needs, is a recommendation scheme that the user is more interested in, and can improve the user experience.

[0080] In some embodiments of the present disclosure, the input data may include target exception information, interaction-related information, and recommendation auxiliary information. The exception handling model can determine the target exception type to which the exception response event belongs based on the target exception information, determine the target business scenario to which the interaction page belongs based on the interaction-related information, determine the target prompt template corresponding to the target exception type based on the exception handling database, determine the business characteristics based on the interaction-related information, determine the target prompt copy based on the target exception information, business characteristics, and corpus, determine at least one recommendation scheme based on the business characteristics and recommendation auxiliary information, and then fill the target prompt copy into the copy slot, and fill the at least one recommendation scheme into the recommendation function slot to generate the target exception prompt.

[0081] Exemplarily, assume that the abnormal response event is a new user operation exception. Then the prompt text can be "View more guidance and help"; the recommended solutions can be "Provide a button click to jump to the video tutorial or graphic tutorial" and / or "Provide a button click to jump to customer service consultation". Assume that the abnormal response event is a payment failure. Then the prompt text can be "Prompt the user to check whether the payment information is correct"; the recommended solution can be "If the user comes from the live broadcast room, provide an exclusive payment coupon code to encourage the user to pay again". Assume that the abnormal response event is out-of-stock of goods. Then the prompt text can be "The current inventory of the product has changed. It is recommended to look at similar products"; the recommended solutions can be one or more of "Provide recommendations for similar products", "Provide an out-of-stock notification function, and the user can choose to receive a notification after the product is restocked", "If the user comes from the live broadcast room, provide links to other recommended products in the live broadcast room", etc. Assume that the abnormal response event is a network exception. Then the prompt text can be "Prompt the user to check the network connection"; the recommended solution can be "Provide other entrances for the user to re-enter the product home page". Assume that the abnormal response event is a non-whitelisted user accessing the business system. Then the prompt text can be "The service is gradually being opened. Please wait and see"; the recommended solution can be "Provide a reservation for the online notification".

[0082] Exemplarily, as Figure 2 shown is the abnormal prompt in the form of a baffle page. As Figure 3 shown is the abnormal prompt in the form of a pop-up window. As Figure 4 shown is the abnormal prompt that only includes the prompt text.

[0083] In the embodiments of the present disclosure, in the case where there is an abnormality in the response of the interaction operation, the abnormality handling model can dynamically generate an abnormal prompt that matches the abnormal response event according to the abnormal information, interaction-related information, recommended auxiliary information, and in combination with the corpus, abnormality handling database, business database, etc., which can improve the user experience.

[0084] In some embodiments of the present disclosure, in combination with Figure 1 , as Figure 5 shown, after the above step 102, the abnormal prompt generation method provided by the embodiments of the present disclosure may further include the following step 103 and step 104.

[0085] 103. Obtain the target operation information for the target abnormal prompt.

[0086] 104. Use the target operation information, the target abnormal prompt, and the input data as feedback training data to perform feedback training on the abnormality handling model, so as to determine the feedback type of the feedback training data according to the target operation information, and adjust the target loss function according to the feedback type, and adjust the abnormality handling model according to the adjusted target loss function.

[0087] In some embodiments of the present disclosure, after the electronic device presents a target exception prompt to the user, the user will make further interactions. We classify the user interactions at this time into two categories: one is positive feedback: the user may choose to continue staying on the target page, may also initiate an interaction operation again, or may choose to receive the recommended solution in the target exception prompt (such as contacting customer service, viewing product instructions, participating in a questionnaire survey, receiving a coupon), etc.; the other is negative feedback, where the user exits the target page or closes the target exception prompt. According to whether the target operation information belongs to positive feedback or negative feedback, the target loss function is adjusted, and then the exception handling model is adjusted to obtain an exception handling model that can generate more accurate exception prompts.

[0088] In the embodiments of the present disclosure, feedback training is reinforcement learning training. By means of feedback training, the best decision for a certain exception response event is learned, and its core lies in optimizing the behavior strategy by strengthening positive feedback and reducing negative feedback.

[0089] In some embodiments of the present disclosure, the execution subject is a server or a functional module or functional entity in the server that can implement the functions of generating and sending the exception prompt provided in the embodiments of the present disclosure. The above step 101 can be specifically implemented through the following step 101a. After the above step 102, the method for generating an exception prompt provided in the embodiments of the present disclosure may further include the following step 105.

[0090] 101a. Receive an exception prompt request from the electronic device.

[0091] Wherein, the exception prompt request carries the input data, and the exception prompt request is used to request the server to obtain an exception prompt corresponding to the input data.

[0092] 105. Send the target exception prompt to the electronic device so that the electronic device presents the target exception prompt on the target page.

[0093] In some embodiments of the present disclosure, if the execution subject is a server or a functional module or functional entity in the server that can implement the functions of generating and sending the exception prompt provided in the embodiments of the present disclosure, then the above step 103 is specifically to obtain target operation information about the target exception prompt from the electronic device.

[0094] In the embodiments of the present disclosure, deploying the exception handling model on the server side can reduce the operating pressure on the electronic device side, and the server side can use a more accurate exception handling model with good algorithm effects, which can improve the accuracy and generation speed of the exception prompt.

[0095] Figure 6 is a structural block diagram of an exception prompt generating device shown in the embodiments of the present disclosure, as Figure 6As shown, it includes: an acquisition module 601, configured to acquire input data, which is acquired when the electronic device responds to an abnormal response event during an interaction operation on a target page, and the input data includes the target abnormal information; an output module 602, configured to input the input data into an abnormal processing model and output a target abnormal prompt. The abnormal processing model is used to determine the target abnormal type to which the abnormal response event belongs based on the target abnormal information, determine the target prompt template corresponding to the target abnormal type based on an abnormal processing database, generate a target prompt text corresponding to the abnormal response event based on the target abnormal information, and fill the target prompt text into the text slot of the target prompt template to generate the target abnormal prompt; the abnormal processing database is used to indicate the corresponding relationship between multiple abnormal types and multiple prompt templates.

[0096] In some embodiments of the present disclosure, the input data further includes interaction-related information, which is used to indicate the interaction page corresponding to the interaction operation; before determining the target prompt template corresponding to the target abnormal type based on the abnormal processing database, it further includes: determining the target business scenario to which the interaction page belongs based on the interaction-related information; determining the target prompt template corresponding to the target abnormal type based on the abnormal processing database includes: determining the target prompt template corresponding to the target abnormal type and the target business scenario based on the abnormal processing database; wherein, the abnormal processing database is used to indicate the corresponding relationship between the multiple abnormal types, multiple business scenarios and the multiple prompt templates.

[0097] In some embodiments of the present disclosure, generating the target prompt text based on the target abnormal information includes: obtaining the page information corresponding to the interaction page from a business database, the business database includes page information corresponding to multiple pages, and the multiple pages include the interaction page; determining the target business characteristics of the target business scenario based on the page information corresponding to the interaction page; determining the target prompt text based on the target abnormal information and the target business characteristics.

[0098] In some embodiments of the present disclosure, determining the target prompt text based on the target abnormal information and the target business characteristics includes: determining the target prompt text that matches the target abnormal information and the target business characteristics based on a corpus, and the corpus is used to indicate multiple prompt texts.

[0099] In some embodiments of the present disclosure, the target prompt template further includes a recommendation function slot; after determining the target business feature of the target business scenario based on the page information corresponding to the interaction page, it further includes: determining at least one recommendation solution that matches the target business feature; filling the target prompt copy into the copy slot of the target prompt template to generate the target exception prompt, including: filling the target prompt copy into the copy slot, and filling the at least one recommendation solution into the recommendation function slot to generate the target exception prompt.

[0100] In some embodiments of the present disclosure, the input data further includes recommendation auxiliary information, and the recommendation auxiliary information includes at least one of the following: relevant operation information within a preset duration before the interaction operation, source path information corresponding to the target page, and user feature information; the target prompt template further includes a recommendation function slot; filling the target prompt copy into the copy slot of the target prompt template to generate the target exception prompt, including: determining at least one recommendation solution that matches the recommendation auxiliary information; filling the target prompt copy into the copy slot, and filling the at least one recommendation solution into the recommendation function slot to generate the target exception prompt.

[0101] In some embodiments of the present disclosure, after inputting the input data into the exception handling model and outputting the target exception prompt, the method further includes: obtaining target operation information for the target exception prompt; using the target operation information, the target exception prompt, and the input data as feedback training data to perform feedback training on the exception handling model, so as to determine the feedback type of the feedback training data based on the target operation information, and adjust the target loss function according to the feedback type, and adjust the exception handling model according to the adjusted target loss function.

[0102] In some embodiments of the present disclosure, when applied to a server, the obtaining module 601 is specifically configured to receive an exception prompt request from the electronic device, where the exception prompt request carries the input data, and the exception prompt request is used to request the server to obtain an exception prompt corresponding to the input data; the apparatus further includes: a sending module, configured to send the target exception prompt to the electronic device after inputting the input data into the exception handling model and outputting the target exception prompt, so that the electronic device displays the target exception prompt on the target page.

[0103] In the embodiments of the present disclosure, each module can implement the exception prompt generation method provided in the above method embodiments and achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0104] Figure 7A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is used to exemplarily illustrate the electronic device for implementing any abnormal prompt generation method in the embodiments of the present disclosure, and should not be construed as a specific limitation to the embodiments of the present disclosure.

[0105] As Figure 7 shown, the electronic device 700 may include a processor (such as a central processing unit, a graphics processing unit, etc.) 701, which may perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 702 or the program loaded from the storage device 708 into the random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 are also stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. The input / output (I / O) interface 705 is also connected to the bus 704.

[0106] Generally, the following devices may be connected to the I / O interface 705: an input device 706 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 708 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 709. The communication device 709 may allow the electronic device 700 to communicate with other devices wirelessly or wiredly to exchange data. Although the electronic device 700 with various devices is shown, it should be understood that it is not required to implement or include all the shown devices. More or fewer devices may be implemented or included alternatively.

[0107] Particularly, according to the embodiments of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program codes for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device 709, or installed from the storage device 708, or installed from the ROM 702. When the computer program is executed by the processor 701, the functions defined in any abnormal prompt generation method provided by the embodiments of the present disclosure may be executed.

[0108] It should be noted that the computer-readable medium described above in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which the computer-readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0109] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0110] The above computer-readable medium can be included in the above electronic device; it can also exist separately without being assembled into the electronic device.

[0111] The above computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: obtain input data, which is obtained when the electronic device responds to an abnormal response event during an interaction operation on a target page, and the input data includes the target abnormal information; input the input data into an abnormal processing model to output a target abnormal prompt. The abnormal processing model is used to determine the target abnormal type to which the abnormal response event belongs based on the target abnormal information, determine the target prompt template corresponding to the target abnormal type based on an abnormal processing database, generate a target prompt text corresponding to the abnormal response event based on the target abnormal information, and fill the target prompt text into the text slot of the target prompt template to generate the target abnormal prompt; the abnormal processing database is used to indicate the corresponding relationship between multiple abnormal types and multiple prompt templates.

[0112] In the embodiments of the present disclosure, computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The above programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, and C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the computer, partially on the computer, executed as an independent software package, partially on the computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0113] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0114] The units involved in the embodiments of the present disclosure can be implemented in software or in hardware. In some cases, the name of a unit does not constitute a limitation on the unit itself.

[0115] The functions described above herein can be performed, at least in part, by one or more hardware logic components. By way of example and not limitation, the types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0116] In the context of the present disclosure, a computer-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable medium may be either a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a computer-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0117] The above description is only of the preferred embodiments of the present disclosure and an illustration of the technical principles applied. Those skilled in the art should understand that the scope of the disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features having similar functions disclosed in the present disclosure.

[0118] In addition, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments may also be implemented combinatorially in a single embodiment. Conversely, the various features described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0119] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. On the contrary, the specific features and acts described above are merely example forms for implementing the claims.

Claims

1. A method for generating an abnormal prompt, characterized in that: The method comprises: Acquiring input data, wherein the input data is acquired when an abnormal response event occurs in response to an interactive operation on a target page by the electronic device, and the input data includes target abnormality information; The input data is input into an exception handling model, and a target exception prompt is output. The exception handling model is used to determine a target exception type to which the exception response event belongs based on the target exception information, determine a target prompt template corresponding to the target exception type based on an exception handling database, generate a target prompt text corresponding to the exception response event based on the target exception information, fill the target prompt text into a text slot of the target prompt template, and generate the target exception prompt; the exception handling database is used to indicate the correspondence between multiple exception types and multiple prompt templates.

2. The method according to claim 1, characterized in that The input data also includes interaction related information, where the interaction related information is used to indicate an interaction page corresponding to the interaction operation; Before determining the target prompt template corresponding to the target exception type based on the exception handling database, the method further includes: Determining a target business scenario to which the interaction page belongs based on the interaction related information; The determining the target prompt template corresponding to the target exception type based on the exception handling database includes: Determine the target prompt template corresponding to the target exception type and the target business scenario based on the exception handling database; The exception handling database is used to indicate the corresponding relationship between the multiple exception types, the multiple business scenarios and the multiple prompt templates.

3. The method according to claim 2, characterized in that The generating of a target prompt text based on the target abnormal information includes: Acquire page information corresponding to the interactive page from a business database, wherein the business database includes page information corresponding to a plurality of pages, and the plurality of pages includes the interactive page; Determining target business characteristics of the target business scenario based on page information corresponding to the interactive page; The target prompt text is determined based on the target abnormality information and the target business characteristics.

4. The method according to claim 3, characterized in that: The determining the target prompt text based on the target abnormal information and the target business characteristics includes: The target prompt text that matches the target abnormal information and the target business feature is determined based on a corpus, wherein the corpus includes correspondences between a variety of abnormal information, a variety of business features, and a variety of text templates.

5. The method according to claim 3, characterized in that: The target prompt template also includes a recommended function slot; after determining the target business features of the target business scenario based on the page information corresponding to the interactive page, it also includes: Determining at least one recommended solution matching the target service characteristics; The step of filling the target prompt text into the text slot of the target prompt template to generate the target abnormality prompt includes: The target prompt text is filled into the text slot, and the at least one recommended solution is filled into the recommended function slot to generate the target abnormality prompt.

6. The method according to claim 1, characterized in that The input data also includes recommendation auxiliary information, and the recommendation auxiliary information includes at least one of the following: relevant operation information within a preset time period before the interactive operation, source path information corresponding to the target page, and user feature information; The target prompt template also includes a recommended function slot; the step of filling the target prompt text into the text slot of the target prompt template to generate the target abnormality prompt includes: Determining at least one recommendation scheme matching the recommendation auxiliary information; The target prompt text is filled into the text slot, and the at least one recommended solution is filled into the recommended function slot to generate the target abnormality prompt.

7. The method according to claim 1, characterized in that After inputting the input data into the exception processing model and outputting the target exception prompt, the method further includes: Obtain target operation information indicating abnormality of the target; The target operation information, the target exception prompt and the input data are used as feedback training data, and feedback training is performed on the exception handling model to determine the feedback type of the feedback training data according to the target operation information, and adjust the target loss function according to the feedback type, and adjust the exception handling model according to the adjusted target loss function.

8. The method according to any one of claims 1 to 7, applied to a server, characterized in that: The obtaining of input data comprises: receiving an abnormal prompt request from the electronic device, the abnormal prompt request carrying the input data, and the abnormal prompt request being used to request the server to obtain an abnormal prompt corresponding to the input data; After inputting the input data into the exception processing model and outputting the target exception prompt, the method further includes: The target abnormality prompt is sent to the electronic device, so that the electronic device displays the target abnormality prompt on the target page.

9. An abnormality prompt generating device, characterized in that: include: An acquisition module, used to acquire input data, wherein the input data is acquired when an abnormal response event occurs when the electronic device responds to an interactive operation on a target page, and the input data includes target abnormality information; An output module is used to input the input data into an exception handling model and output a target exception prompt, wherein the exception handling model is used to determine the target exception type to which the exception response event belongs based on the target exception information, determine the target prompt template corresponding to the target exception type based on an exception handling database, generate a target prompt text corresponding to the exception response event based on the target exception information, fill the target prompt text into the text slot of the target prompt template, and generate the target exception prompt; The exception handling database is used to indicate the corresponding relationship between multiple exception types and multiple prompt templates.

10. An electronic device, characterized in that: include: A memory and a processor, the memory is used to store a computer program; the processor is used to execute the abnormal prompt generation method described in any one of claims 1 to 8 when calling the computer program.

11. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the abnormal prompt generating method according to any one of claims 1 to 8 is implemented.

12. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the abnormality prompt generating method according to any one of claims 1 to 8 is implemented.

Images