Interaction method and device, electronic equipment and storage medium

Abstract

The invention discloses an interaction method and device, electronic equipment and a storage medium, and relates to the field of artificial intelligence, in particular to the field of intelligent search. According to the specific implementation scheme, intention recognition and content recognition are conducted on text information, input through an interactive interface, of an object, and an intention recognition result and a content recognition result are obtained; under the condition that the intention recognition result represents that the object has negative emotion and the content recognition result represents that the text information comprises preset content, displaying order selection information in an interactive interface according to multiple pieces of historical order information of the object; and determining a processing scheme of the to-be-processed order by performing multi-dimensional analysis on the to-be-processed order determined by the object on the interaction interface based on the order selection information.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, in particular to the field of intelligent search, and specifically to an interaction method, device, electronic device, and storage medium. Background Art

[0002] Currently, on major e-commerce platforms, when users operate items, they communicate with the supplier of the items or the platform customer service through an interactive interface. If the user encounters a bad experience during the operation, they usually initiate an order processing application, waiting for the supplier or the platform customer service to solve the relevant problems for them. Summary of the invention

[0003] The present disclosure provides an interaction method, an apparatus, an electronic device and a storage medium.

[0004] According to one aspect of the present disclosure, an interactive method is provided, which performs intent recognition and content recognition on text information input by an object through an interactive interface, respectively, to obtain intent recognition results and content recognition results; when the intent recognition result indicates that the object has negative emotions, and the content recognition result indicates that the text information includes preset content, order selection information is displayed in the interactive interface according to multiple historical order information of the object; and a processing plan for the pending orders determined by the object in the interactive interface based on the order selection information is determined by performing multi-dimensional analysis. .

[0005] According to another aspect of the present disclosure, an interactive device is provided, an intention recognition module, which is used to perform intention recognition and content recognition on text information input by an object via an interactive interface, respectively, to obtain an intention recognition result and a content recognition result;

[0006] A selection generation module is used to display order selection information in the interactive interface according to multiple historical order information of the object when the intention recognition result indicates that the object has negative emotions and the content recognition result indicates that the text information includes preset content;

[0007] The solution determination module is used to determine the processing solution for the pending orders by performing multi-dimensional analysis on the pending orders determined by the above-mentioned object in the above-mentioned interactive interface based on the above-mentioned order selection information.

[0008] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described above.

[0009] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described above.

[0010] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, and the computer program implements the method described above when executed by a processor.

[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0013] Figure 1 An exemplary system architecture to which the interactive method and device according to an embodiment of the present disclosure can be applied is schematically shown;

[0014] Figure 2 A flowchart of an interaction method according to an embodiment of the present disclosure is schematically shown;

[0015] Figure 3 A schematic diagram of an interface for order selection information according to an embodiment of the present disclosure is schematically shown;

[0016] Figure 4 A schematic diagram schematically shows a multi-dimensional analysis of pending orders according to an embodiment of the present disclosure;

[0017] Figure 5 A flowchart of an interaction method according to another embodiment of the present disclosure is schematically shown;

[0018] Fig. 6A The following schematically shows an interface diagram of platform intervention according to an embodiment of the present disclosure;

[0019] Figure 6B The following schematically shows an interface diagram of a reason selection item according to an embodiment of the present disclosure;

[0020] Figure 6C The following is a schematic diagram of an interface showing a processing state according to an embodiment of the present disclosure;

[0021] Figure 7 The flowchart of judging the cause of processing according to the embodiment of the present disclosure is schematically shown;

[0022] Figure 8A flowchart showing a processing state according to an embodiment of the present disclosure is schematically shown;

[0023] Fig. 9 A block diagram schematically shows an interaction device according to an embodiment of the present disclosure; and

[0024] Fig.10 A block diagram of an electronic device suitable for implementing an interaction method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0025] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0026] Figure 1 An exemplary system architecture to which the content processing method and apparatus according to an embodiment of the present disclosure can be applied is schematically shown.

[0027] It should be noted that Figure 1 The examples shown are only examples of system architectures to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, the exemplary system architecture to which the content processing method and apparatus can be applied may include a terminal device, but the terminal device may implement the content processing method and apparatus provided by the embodiments of the present disclosure without interacting with the server.

[0028] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0029] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients and / or social platform software, etc. (only as examples).

[0030] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0031] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for the content browsed by the user using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to the user request) to the terminal device.

[0032] It should be noted that the content processing method provided in the embodiment of the present disclosure can generally be executed by the terminal device 101, 102, or 103. Accordingly, the content processing apparatus provided in the embodiment of the present disclosure can also be set in the terminal device 101, 102, or 103.

[0033] Alternatively, the content processing method provided in the embodiment of the present disclosure may also be generally executed by the server 105. Accordingly, the content processing device provided in the embodiment of the present disclosure may generally be arranged in the server 105. The content processing method provided in the embodiment of the present disclosure may also be executed by a server or a server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the content processing device provided in the embodiment of the present disclosure may also be arranged in a server or a server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0034] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0035] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0036] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0037] Figure 2 The flowchart of the interaction method according to the embodiment of the present disclosure is schematically shown.

[0038] like Figure 2 As shown, the method includes operations S210 to S230.

[0039] In operation S210, intent recognition and content recognition are performed on the text information input by the object via the interactive interface to obtain intent recognition results and content recognition results.

[0040] In operation S220, when the intention recognition result indicates that the object has negative emotions and the content recognition result indicates that the text information includes preset content, order selection information is displayed in the interactive interface based on multiple historical order information of the object.

[0041] In operation S230, a processing plan for the orders to be processed is determined by performing a multi-dimensional analysis on the orders to be processed determined by the object in the interactive interface based on the order selection information.

[0042] According to the embodiments of the present disclosure, currently on major e-commerce platforms, when an object operates a target item, it will communicate with the supplier of the target item or the platform customer service through an interactive interface. For example, when a user trades a target item, he will consult the merchant for relevant information, or when a user is not satisfied with the target item obtained through the transaction, he will report the relevant problem to the merchant or the platform customer service to seek after-sales service.

[0043] According to the embodiments of the present disclosure, the subject may encounter negative experiences during the operation of the target item. For example, the user is not satisfied with the purchased target item and reports the relevant problems to the merchant, but the merchant fails to deal with the user's problem in time. Faced with the above situation, the subject usually provides feedback on the situation encountered through the interactive interface to seek a solution. By obtaining the text information input by the subject through the interactive interface, the text information is analyzed to provide a suitable solution for the subject.

[0044] According to an embodiment of the present disclosure, intent recognition and content recognition are performed on the text information input by the object. Among them, intent recognition is used to determine the emotion of the object when entering the text information. When facing a negative experience, the object may describe the problem encountered by expressing emotions. For example: the text message input by the user is "Why haven't you processed my after-sales order yet? I suspect you are delaying it deliberately." After identifying the presence of negative emotions in the text message, it is determined that the platform needs to intervene to solve the user's problem in a timely manner.

[0045] According to an embodiment of the present disclosure, content recognition of text information is used to determine whether the text information includes preset content. The preset content is that there is no order information associated with negative emotions. That is, after the user enters the text information, he only expresses his emotions through the text information, but does not explain the order in detail.

[0046] For example, a user has traded items in Merchant A. When the user seeks after-sales service for the transaction order, he directly consults through the "Contact Merchant" channel in the details page of Merchant A. Therefore, when the user only outputs text information expressing negative emotions, it is unclear which order the user is specifically consulting about.

[0047] According to an embodiment of the present disclosure, when it is determined that the subject has negative emotions and the text information includes preset content, since the text information does not include orders directly associated with the negative emotions, it is necessary to determine the orders associated with the subject's negative emotions from the subject's historical order information. Specifically, order selection information can be generated based on multiple historical order information, so that the order selection information can be displayed in the interactive interface. If the subject does not have historical order information within a preset time period, the text information can be determined to be invalid information, and the processing of the order is terminated. Among them, the preset time period can be set to three months from the current moment.

[0048] like Figure 3 As shown, the user inputs text information 301 through the text input box 304. After the text information 301 is respectively recognized for intent and content, order selection information 302 is displayed in the interactive interface. Among them, the order selection information 302 includes multiple historical order information. The user selects the pending order 303 associated with his negative emotions based on the displayed order selection information 302. Among them, the pending order 303 is the historical order information 1 among the multiple historical order information.

[0049] According to an embodiment of the present disclosure, in the process of determining pending orders, the pending orders can also be determined by asking the subject to fill in information. For example: after determining that the user has negative emotions and the text information does not include orders directly associated with negative emotions, an information filling box is output on the interactive interface to allow the user to fill in the necessary information in the information filling box. After determining that the user has completed filling in the information, the pending orders are determined based on the information filled in by the user.

[0050] According to the embodiments of the present disclosure, order selection information is generated based on historical order information to allow users to select pending orders, which reduces the complexity of the user operation process. The pending orders are determined by allowing users to fill in order information, making the determination process more accurate and efficient.

[0051] According to an embodiment of the present disclosure, after determining the pending orders, a multi-dimensional analysis is performed on the pending orders to determine whether the pending orders meet the conditions for rapid processing by the platform. Based on the results of the multi-dimensional analysis, a processing plan for the pending orders is determined. The processing plan may be a plan consistent with the requirements raised by the object in the text information, or a relatively appropriate processing plan determined based on the operation information of the pending orders.

[0052] According to the embodiments of the present disclosure, by performing intent recognition and content recognition on text information respectively, the problem can be solved in a timely manner when it is determined that the user has negative emotions, thereby effectively improving the user experience. When it is determined that the object has negative emotions and the text information includes preset content, it means that it is currently difficult to directly know the cause of the object's negative emotions. Therefore, it is necessary to generate order selection information based on multiple historical order information of the object and display it, so that the user can determine the pending orders where the problem is in the interactive interface, so as to solve the problem in a timely manner. Multi-dimensional analysis of the pending orders is performed to determine the processing plan. By interacting with the object during the determination process, the efficiency of determining the processing plan is effectively improved, making it faster and more efficient to solve the problems raised by the object.

[0053] According to an embodiment of the present disclosure, intent recognition and content recognition are performed on text information input by an object via an interactive interface to obtain intent recognition results and content recognition results, including: matching keywords extracted from the text information with multiple regular expressions to obtain intent recognition results, wherein the regular expressions are obtained based on keywords of negative emotions; performing order identification on the text information to obtain content recognition results, wherein, when the content identification result indicates that there is no order identification in the text information, it is determined that the text information includes preset content.

[0054] According to an embodiment of the present disclosure, keywords are extracted from text information. Specifically, natural language processing tools can be used to extract keywords, and machine learning can also be used to predict keywords. After obtaining the keywords of the text information, the keywords are matched with regular expressions in a regular library. Among them, the regular library stores multiple regular expressions, each of which is written based on keywords of the user's negative emotions.

[0055] According to the embodiments of the present disclosure, the negative emotions of users generally refer to those emotions that make people feel unhappy, depressed or negative. Keywords associated with negative emotions may include words such as irritability, suspicion, bad, disappointment, etc. In addition, since the negative emotions in the embodiments of the present disclosure are caused by problems after the user trades the items, the keywords associated with negative emotions may also include words that indicate a bad experience, such as delay, failure, bad, dissatisfaction, etc.

[0056] According to an embodiment of the present disclosure, a regular expression is written according to the defined keywords. For example, the regular expression may be as follows: "(unsatisfied|bad|disappointed|bad)". The text information is matched using the regular expression. If the text information contains the keywords in the regular expression, it is considered that the object has negative emotions. Among them, the regular expressions in the regular library are continuously updated and optimized according to actual conditions to cover more expressions of negative emotions. By using regular expressions to identify intent, the identification process is relatively simple, and it is also convenient to update and optimize it in real time according to the current trading environment.

[0057] According to an embodiment of the present disclosure, after the intent of the text information is recognized, if it is determined that the user has negative emotions, the order identification of the text information is performed to determine whether the text information contains orders associated with negative emotions. The order identification can be an order number that uniquely corresponds to the order. By identifying the order identification, it is determined whether the object brings the relevant order into the interactive interface during the process of entering the text information.

[0058] For example, a user has traded items with merchant A. When seeking after-sales service for a transaction order, the user clicks the "Contact Merchant" icon on the order details page to enter the after-sales service channel. In the above consultation method, when the user enters text information in the interactive interface, the entered text information is associated with the transaction order, so the corresponding order icon will be brought into the dialog box of the interactive interface.

[0059] According to the embodiments of the present disclosure, in the process of identifying the order identifier, the text information itself can also be directly identified to check whether the content of the text information includes the order identifier. For example, the content entered by the user in the interactive interface is "I want to return order 100000xxx". By directly determining the order identifier in the text information, the corresponding pending order can be obtained.

[0060] According to the embodiments of the present disclosure, by performing intent recognition and content recognition on text information, the problem can be solved in a timely manner when it is determined that the user has negative emotions. At the same time, the problem can also be accurately determined based on the content recognition results, making the solution process more efficient and improving the user experience.

[0061] According to an embodiment of the present disclosure, a processing plan for the pending orders is determined by performing a multi-dimensional analysis on the pending orders determined by the object in the interactive interface based on the order selection information, including: analyzing the pending orders from the item dimension, the order dimension and the object dimension according to the operation information generated when the target items in the pending orders are operated to obtain analysis results; determining the type of processing channel used when processing the pending orders based on the analysis results, wherein the types of processing channels include fast processing channels and ordinary processing channels; determining the processing plan for the pending orders according to the type of processing channel and the operation information.

[0062] According to an embodiment of the present disclosure, operation information generated when an object operates a target item is obtained. The operation information includes information associated with the target item itself, order information of the pending order, and object portrait information of the object. The pending order is analyzed from the item dimension, order dimension, and object dimension to obtain analysis results. The analysis results are used to characterize whether the pending order can be processed using a fast processing channel.

[0063] According to an embodiment of the present disclosure, the type of processing channel used when processing pending orders is determined based on the analysis results, wherein the types of processing channels include fast processing channels and ordinary processing channels. The fast processing channel refers to platform intervention processing, and when processing pending orders, there is no need to wait for the response of the target item supplier and the indication of whether to agree to the processing. The processing platform can directly determine the corresponding plan based on the operation information of the pending order to achieve fast processing of the order.

[0064] According to the embodiments of the present disclosure, the common processing channel is that after the object initiates the processing application, it needs to wait for the instruction of the supply object. After the supply object agrees to the processing, the pending order is processed according to the processing plan agreed upon by the two parties. If the supply object disagrees with the processing plan in the processing application, it is necessary to continue to interact with the supply object through the interactive interface until an agreement is reached, so as to determine the corresponding processing plan.

[0065] According to an embodiment of the present disclosure, after determining the type of processing channel, the corresponding processing scheme is determined according to the operation information. For the type of fast processing channel, since the platform intervenes in the processing, the processing scheme is relatively intuitive and single, and can be processed quickly. However, since the ordinary processing channel needs to interact repeatedly with the supply object, the corresponding processing scheme is more diverse and complex. By determining the processing scheme according to the type of processing channel and the operation information, the processing scheme is more targeted, and can meet the needs of the object while improving efficiency.

[0066] Figure 4A schematic diagram of performing multi-dimensional analysis on pending orders according to an embodiment of the present disclosure is schematically shown.

[0067] According to an embodiment of the present disclosure, according to the operation information generated when the target item in the pending order is operated, the pending order is analyzed from the item dimension, the order dimension and the object dimension respectively to obtain analysis results, including: matching the item identifier of the target item with the identifiers of multiple negative items in the negative item set to obtain a first analysis result, wherein the negative items in the negative item set are obtained by screening multiple items using the item filtering rules corresponding to the fast processing channel; analyzing the order information in the operation information according to the order analysis rules corresponding to the fast processing channel to obtain a second analysis result, wherein the order analysis rules respectively include analysis rules corresponding to at least one of the resource value, order type, order status and processing period in the order information; analyzing the object portrait information of the object according to the object analysis rules corresponding to the fast processing channel to obtain a third analysis result, wherein the object analysis rules include analysis rules corresponding to the remaining number of uses of the fast processing channel in the object portrait information and the object evaluation value respectively; determining the analysis result of the pending order according to the first analysis result, the second analysis result and the third analysis result.

[0068] According to the embodiments of the present disclosure, the order to be processed is analyzed from the item dimension, order dimension and object dimension. For the item dimension, the item ID of the target item is determined. Each item ID is uniquely corresponding to the target item and can be in the form of numbers or letters. Figure 4 As shown, the item identifier 402 of the target item in the pending order 401 is matched with the identifiers of multiple negative items in the negative item set 405 to obtain a first analysis result 408 .

[0069] According to an embodiment of the present disclosure, negative items are obtained by screening multiple items using item filtering rules corresponding to the fast processing channel. The item filtering rules include filtering rules corresponding to at least one of the item quality return rate, output rate, consumer negative feedback index, and net recommendation value of the item supply object. Negative items refer to items whose multiple indicators in the item filtering rules do not meet the preset conditions, or items whose at least one indicator does not meet the preset conditions. The preset conditions may include thresholds corresponding to each indicator.

[0070] For example, for an item on an e-commerce platform, if it is determined that the quality return rate of the item is high and the output rate is low, the item is determined to be a negative item. In the process of screening items, multiple items on the e-commerce platform can be screened one by one based on a scheduled task and using item filtering rules to update the negative item set in a timely manner.

[0071] According to an embodiment of the present disclosure, during the analysis of the pending order, if it is determined that the item identifier of the target item is in the negative item set, then the first analysis result is determined to be that the pending order cannot be processed using the fast processing channel.

[0072] According to an embodiment of the present disclosure, for the order dimension, the order information of the pending order is determined, wherein the order information includes the resource value of the target item, the order type, the order status, the processing reason and the processing period. The order type is determined according to the processing solution applied by the object, for example: if the processing solution applied by the user is return, the order type is determined to be a return type, and if the processing solution applied by the user is exchange, the order type is determined to be an exchange type.

[0073] According to an embodiment of the present disclosure, the order status is used to characterize the processing status of a pending order before it enters the fast processing channel. For example, before the platform intervenes, the merchant has agreed to the user's application, and the pending order is currently in the processing process, then the current status of the pending order can be determined as being in processing.

[0074] According to the embodiment of the present disclosure, the processing reason is the reason marked by the user when applying for the processing solution, and the processing period is the processing period for the order to be processed. Figure 4 As shown, the order information 403 in the operation information of the order to be processed 401 is analyzed according to the order analysis rule 406 to determine the second analysis result 409.

[0075] According to an embodiment of the present disclosure, during the analysis process, the order analysis rules respectively include analysis rules corresponding to at least one of the resource value, order type, order status, and processing period in the order information. Specifically, the analysis process is performed according to the criteria of each analysis rule. For example, for the order type, it is determined that orders of the exchange type do not meet the analysis rules; for the processing period, it is determined that orders that exceed the processing period do not meet the analysis rules. If the order information does not meet any of the analysis rules in the order analysis rules, it is determined that the second analysis result is that the pending order cannot be processed using the fast processing channel.

[0076] According to an embodiment of the present disclosure, object portrait information of an object is obtained for an object dimension. The object portrait information includes the remaining number of uses of the fast processing channel and the object evaluation value. For the number of uses of the fast channel, it can be stipulated that the number of times each object uses the fast processing channel is 5 times per month. The remaining number of uses is determined based on the use of the fast processing channel by the object in the current month.

[0077] According to the embodiments of the present disclosure, the object evaluation value can be obtained by analyzing and calculating the historical operation records of the object on various e-commerce platforms. Specifically, it can be evaluated using a relevant deep learning model, or it can be determined based on a certain indicator of the object. For example, the object evaluation value of a user is determined based on the user's return rate. Figure 4 As shown, the object portrait information 404 of the object of the order 401 to be processed is analyzed according to the object analysis rule 407 to determine the third analysis result 410.

[0078] According to an embodiment of the present disclosure, during the analysis process, the object analysis rules include analysis rules corresponding to the remaining number of uses and the object evaluation value of the fast processing channel in the object portrait information. Specifically, the analysis process is performed based on the limit thresholds of the remaining number of uses and the object evaluation value. For example: objects with a remaining number of uses of 0 or an object evaluation value of less than 60 points are filtered. If the object portrait information does not satisfy any of the analysis rules in the object analysis rules, it is determined that the third analysis result is that the pending order cannot be processed using the fast processing channel.

[0079] According to an embodiment of the present disclosure, the first analysis result, the second analysis result, and the third analysis result are integrated. If all three results indicate that the pending order can be processed using the fast processing channel, the analysis result is determined to be processed using the fast processing channel. If at least one of the three results indicates that the pending order cannot be processed using the fast processing channel, the analysis result is determined to be processed using the ordinary processing channel.

[0080] According to the embodiments of the present disclosure, by performing multi-dimensional analysis on the orders to be processed, the orders can be filtered from multiple aspects, so that when using the fast processing channel, no processing exceptions and unresolvable order problems will occur, thereby effectively ensuring the rationality of order processing while improving processing efficiency.

[0081] According to an embodiment of the present disclosure, a processing plan for an order to be processed is determined according to the type of processing channel and operation information, including: when the type of processing channel is a fast processing channel, determining the item category and resource value of the target item based on the operation information; when it is determined that the item category is a preset category and the resource value is less than a first preset resource value, or when the item category is not a preset category and the resource value is less than or equal to a second preset resource value, determining the processing plan to be a service of returning only resources, wherein the first preset resource value is greater than the second preset resource value; when it is determined that the item category is a preset category and the resource value is greater than or equal to the first preset resource value, or when the item category is not a preset category and the resource value is greater than the second preset resource value, determining the processing plan to be a service of returning resources after the object returns the target item.

[0082] According to an embodiment of the present disclosure, when the type of the processing channel is a fast processing channel, the item category and resource value of the target item are determined based on the operation information. Among them, the item category can be divided into fresh food and non-fresh food, and specifically, the fresh food category is a preset category. When the item category and resource value meet any of the following rules, a service of returning only resources is provided.

[0083] (a) Item category = fresh food & resource value < 50 (the first preset resource value).

[0084] (b) Item category = non-fresh food & resource value ≤ 20 (second preset resource value).

[0085] According to the embodiment of the present disclosure, for non-fresh items with a resource value in the range of 20 to 200 and fresh items with a resource value in the range of 50 to 200, a service of returning resources after the object returns the target item is provided. If, after the pending order enters the fast processing channel, it is determined that the processing solution applied by the object is to provide a service of returning resources after returning the target item, even if the target item meets any of the above rules (a) and (b), the processing solution will not be changed, and the processing solution applied by the user will still be retained.

[0086] According to the embodiment of the present disclosure, since the process of multi-dimensional analysis of pending orders involves the analysis of the resource value of the target item, the specific analysis rule is to filter orders whose item resource value is greater than 200. Therefore, after the pending orders are analyzed, the resource values ​​of the orders entering the fast processing channel are all items with a resource value less than 200, and there will be no case where the resource value is greater than 200. Therefore, the processing solution of the fast processing channel does not include a processing solution for items with a resource value greater than 200.

[0087] According to the embodiments of the present disclosure, by distinguishing between fresh food and non-fresh food, it is more reasonable to determine the processing plan, which can protect the rights and interests of users and improve user experience.

[0088] Figure 5 The flowchart of an interaction method according to another embodiment of the present disclosure is schematically shown.

[0089] like Figure 5 As shown, the method includes operations S510 to S580.

[0090] In operation S510, intent recognition and content recognition are performed on the text information.

[0091] In operation S520, it is determined whether the subject has negative emotions and the text information includes preset content. If it is determined that the subject has negative emotions and the text information includes preset content, operation S530 is performed.

[0092] In operation S530, it is determined whether the quantity of the object historical order information is greater than a preset quantity. If it is determined to be greater than the preset quantity, operation S540 is performed. If it is determined to be less than or equal to the preset quantity, operation S570 is performed.

[0093] According to an embodiment of the present disclosure, if the number of historical order information is greater than a preset number, it means that the current number of historical order information is large. If all of them are presented to the object in the form of order selection information, the object experience will be poor, and it will be difficult for the object to quickly select the order to be processed in the interactive interface. Therefore, when the number of historical order information is greater than the preset number, the historical order information needs to be filtered.

[0094] In operation S540, by performing multi-dimensional analysis on a plurality of historical order information of the object, candidate order information that can be used for order processing in the fast channel is screened out.

[0095] In operation S550, order selection information including a plurality of candidate order information is displayed on the interactive interface.

[0096] In operation S560, when receiving the pending order determined by the object according to the order selection information, a processing plan for the pending order is determined based on the operation information of the pending order.

[0097] According to an embodiment of the present disclosure, by screening the alternative order information that can be processed using the fast channel, the processing of the order enters the fast processing channel in advance. If it is determined after screening that there is only one alternative order information, the corresponding processing solution can be directly determined. If there are multiple alternative order information after screening, order selection information is generated. The method of generating the order selection information here is the same as the above method and is not repeated here.

[0098] According to an embodiment of the present disclosure, if no alternative order information is obtained after screening, it means that the problem cannot be processed using the fast processing channel at present, so the processing of the pending order is terminated and it continues to be processed using the ordinary processing channel.

[0099] In operation S570, order selection information is displayed in the interactive interface according to the plurality of historical order information of the object.

[0100] In operation S580, a processing plan for the orders to be processed is determined by performing a multi-dimensional analysis on the orders to be processed determined by the object in the interactive interface based on the order selection information.

[0101] According to the embodiment of the present disclosure, in order to improve the user experience, the processing of issuing order selection information within one day can be set to 3 times. After the order to be processed is determined, the order card of the order is displayed on the interactive interface, and the supply object can also be informed of this event while informing the object. Setting different order processing processes according to the amount of historical order information can improve the user experience and improve the order processing efficiency.

[0102] Fig. 6A The following schematically shows an interface diagram of platform intervention according to an embodiment of the present disclosure.

[0103] like Fig. 6A As shown, after performing a multi-dimensional analysis on the pending orders, it is determined that the pending orders can be processed using the fast processing channel, and the platform intervention card 601 is displayed on the interactive interface. The platform intervention card 601 is used to ask the object whether it agrees to enter the fast processing channel for processing. When the user clicks the "Agree" option of the platform intervention card 601, the corresponding processing plan is determined according to the operation information of the pending order.

[0104] According to the embodiment of the present disclosure, since the processing solution of the fast processing channel is relatively simple, in order to seek a more targeted processing solution, the subject will also click the "reject" option of the platform intervention card 601 in the interactive interface to refuse to use the fast processing channel for processing. By displaying the platform intervention card, the user's willingness can be solicited, so that the final processing solution is more in line with the user's needs.

[0105] According to an embodiment of the present disclosure, the interaction method also includes: determining the number of times the object inputs text information representing the presence of negative emotions within a preset time period; and refusing to display the order selection information in the interaction interface when it is determined that the number of inputs is greater than the preset number.

[0106] According to an embodiment of the present disclosure, in order to improve the user experience, the preset number of interactions with the object on the interactive interface in one day can be set to 5 times. If the number of times the object inputs text information representing negative emotions in one day is greater than 5 times, it means that in the first 5 processings, the processing platform initiated the processing flow through the interactive interface, but the object did not adopt it. Therefore, in the case where the number of inputs is greater than the preset number, in order to avoid displaying repeated content on the interactive interface, the order selection information is refused to be displayed.

[0107] Figure 6B The following schematically shows an interface diagram of a reason selection item according to an embodiment of the present disclosure.

[0108] According to an embodiment of the present disclosure, the interaction method also includes: when it is determined that the operation information of the order to be processed does not include a processing reason, a reason selection item corresponding to the order to be processed is displayed in the interaction interface; when a processing reason determined by the object based on the reason selection item is received, a corresponding processing plan is executed based on the processing reason.

[0109] According to an embodiment of the present disclosure, the operation information is detected to determine whether there is a processing reason in the operation information. Since the object may not have initiated an order processing application when entering text information, there is no processing reason in the operation information, and the processing reason needs to be re-determined. A reason tab corresponding to the pending order is displayed in the interactive interface, wherein the reason tab includes multiple processing reasons to be selected. The object determines the processing reason by selecting the processing reason in the reason tab in the interactive interface.

[0110] like Figure 6B As shown, after determining that there is no processing reason in the operation information, a reason tab 603 is displayed in the interactive interface. Among them, the reason tab 603 includes multiple processing reasons. The user selects the processing reason according to the reason tab 603 to obtain the processing reason 604 of the pending order. Among them, the processing reason 604 of the pending order is the processing reason 2 among the multiple processing reasons.

[0111] According to an embodiment of the present disclosure, in the process of determining the processing reason, the processing reason can also be determined by allowing the object to fill in. For example: after determining that there is no processing reason in the operation information, an information filling box is output on the interactive interface to allow the user to fill in the processing reason in the information filling box.

[0112] According to an embodiment of the present disclosure, after determining the processing reason, the corresponding processing plan is executed based on the processing reason. If the processing reason is caused by the object itself, the processing plan will not be executed. In the case where there is a processing reason in the operation information, since in the process of multi-dimensional analysis of the orders to be processed, the orders caused by the object itself will be filtered according to the order analysis rules. Therefore, if there is a processing reason in the operation information, it must not be caused by the object itself, and the processing plan can be directly executed. By displaying the reason selection items in the interactive interface and executing the processing plan based on the processing reason, the processing process is more flexible and efficient.

[0113] Figure 7 The flowchart of determining the cause of processing according to an embodiment of the present disclosure is schematically shown.

[0114] According to an embodiment of the present disclosure, the interactive method also includes: when it is determined that the processing reason is that the resource value of the target item does not match the target item, the order to be processed is sent to the server, so that the server performs a judgment on the order to be processed, wherein the judgment is used to determine the authenticity of the processing reason; when a judgment result returned by the server, which indicates that the resource value matches the target item, is received, a rejection item for rejecting the processing of the order to be processed is displayed in the interactive interface.

[0115] According to an embodiment of the present disclosure, if the processing reason is that the resource value of the target item does not match the target item, the platform cannot directly determine the authenticity of the processing reason, so it is necessary to send the pending order to the server so that the server can judge the processing reason. In the process of analyzing the processing reason, the interaction between the platform processing end, the order middle end and the server end is involved. Among them, the platform processing end is used to analyze the text information input by the object and the pending order. The order middle end integrates the order data to uniformly manage multiple orders. The server end, as the platform customer service end, is used to manually check related issues.

[0116] like Figure 7 As shown, the method includes operations S710~S790.

[0117] In operation S710, it is determined that the processing reason is that the resource value of the target item does not match the target item.

[0118] In operation S720, a judgment process is performed.

[0119] According to the embodiment of the present disclosure, after receiving the processing reason, the server will obtain the target item in the pending order and its corresponding resource value. The platform customer service of the server will give the judgment result based on experience and generate a processing work order, and send the judgment result to the order middle station. The order middle station will save the judgment result and feedback it to the platform processing end.

[0120] In operation S730, a fast processing channel is entered.

[0121] According to the embodiment of the present disclosure, after the order center obtains the judgment result, it will determine whether the pending order is processed using the fast processing channel based on the information of the pending order stored in the order center. If so, it will enter the fast processing channel and feed back the judgment result to the platform processing end.

[0122] In operation S740, a processing solution is determined according to the judgment result.

[0123] In operation S750, only resources are returned. In operation S760, resources are returned after the target item is returned. In operation S770, it is rejected.

[0124] According to the embodiment of the present disclosure, after receiving the judgment result, the platform processing end will analyze the judgment result. If the judgment result indicates that the processing reason is recognized, the initially determined processing plan is still maintained and the processing plan is executed. If the judgment result indicates that the processing reason is not recognized, the processing plan for the pending order is rejected and it is not processed.

[0125] In operation S780, the cause is changed.

[0126] In operation S790, the accountability process ends.

[0127] According to an embodiment of the present disclosure, during the judgment and processing of the server, the object may modify the processing reason. If the object modifies the processing reason, and the processing reason is no longer that the resource value of the target item does not match the target item, the order center saves the modified processing reason and informs the server at the same time. After receiving the message that the processing reason has changed, the server ends the judgment and processing and closes the corresponding processing work order. By using the server to determine the authenticity of the processing reason, the rationality of the order processing can be guaranteed when executing the processing plan.

[0128] According to an embodiment of the present disclosure, the interaction method also includes: for pending orders whose processing channel is a fast processing channel, determining the processing status of the pending orders on at least one processing node according to the processing progress of the pending orders; and displaying corresponding status items in the interactive interface according to different processing statuses.

[0129] According to the embodiment of the present disclosure, the platform processing end subscribes to the processing progress of pending orders in the order center. Among them, the order center not only integrates the order information, but also integrates the logistics distribution management information. By capturing order, payment and logistics information in real time, real-time information interaction with logistics companies is realized, which improves the transparency and efficiency of logistics tracking. The order center can also monitor the order status and delivery status in real time, detect abnormal situations in time and handle them, and improve the accuracy and reliability of order delivery.

[0130] Figure 8 The flowchart for displaying the processing status according to an embodiment of the present disclosure is schematically shown.

[0131] As shown in FIG8 , the method includes operations S810 to S870 .

[0132] In operation S810, a processing progress is determined.

[0133] In operation S820, a processing status is determined.

[0134] According to an embodiment of the present disclosure, the order middle platform sends the processing progress of the pending order to the platform processing end, and the platform processing end determines the processing status of the pending order on at least one processing node. The processing nodes include solution execution nodes, item return nodes, resource return nodes, etc.

[0135] In operation S830, it is determined whether the order is processed by a fast processing channel.

[0136] According to an embodiment of the present disclosure, the platform processing end determines whether the order to be processed is an order processed by the fast processing channel. For orders processed by the fast processing channel, since the processing solution is relatively simple, the number of processing states displayed on the processing node is also relatively small, and it also avoids pushing a large amount of relevant information to users, which reduces the user experience. For orders in ordinary processing channels, since there are a lot of uncertainties in the processing process, each processing node needs to display the corresponding processing status on the interactive interface. For example: the node where communication with the supply object is completed, the node where the supply object agrees to the processing solution, etc.

[0137] In operation S840, corresponding status items are displayed on the interactive interface according to different processing statuses.

[0138] In operation S850, the resource return is displayed successfully. In operation S860, the resource return is displayed failed. In operation S870, the processing information to be filled in is displayed.

[0139] In operation S880, no processing is performed.

[0140] According to an embodiment of the present disclosure, the status items displayed in the interactive interface may be displayed in the form of cards, which specifically include the processing status at each processing node, for example, whether the resource return is successful. If the user needs to return the item, the item return node will display the status items such as appointment for pickup and successful pickup.

[0141] Figure 6C An interface diagram of the processing status according to an embodiment of the present disclosure is schematically shown.

[0142] like Figure 6C As shown, when it is determined that the pending order is an order processed by the fast processing channel, the processing solution 605 is displayed on the interactive interface to inform the object. Then, in the process of executing the processing solution 605, the processing status 606 on multiple processing nodes is displayed. For example, as the processing flow progresses, the processing status 1 and the processing status 2 are displayed respectively. By timely determining and displaying the processing status, it is convenient for users to know the processing status of the current order, and at the same time, it can also promote the processing progress of the order and improve the processing efficiency of the order.

[0143] Fig. 9A block diagram of a content processing device according to an embodiment of the present disclosure is schematically shown.

[0144] like Fig. 9 As shown, the interactive device 900 of this embodiment includes an intention recognition module 910 , a selection generation module 920 and a solution determination module 930 .

[0145] The intention recognition module 910 is used to perform intention recognition and content recognition on the text information input by the object through the interactive interface, and obtain intention recognition results and content recognition results.

[0146] The selection generation module 920 is used to display order selection information in the interactive interface based on multiple historical order information of the object when the intention recognition result indicates that the object has negative emotions and the content recognition result indicates that the text information includes preset content.

[0147] The solution determination module 930 determines a processing solution for the orders to be processed by performing a multi-dimensional analysis on the orders to be processed determined by the object in the interactive interface based on the order selection information.

[0148] According to an embodiment of the present disclosure, the intention recognition module 910 includes a regular matching submodule and a logo recognition submodule.

[0149] The regular matching submodule is used to match the keywords extracted from the text information with multiple regular expressions to obtain the intent recognition result, wherein the regular expressions are obtained based on the keywords of negative emotions.

[0150] The identification recognition submodule is used to perform order identification on the text information to obtain a content identification result, wherein when the content identification result indicates that there is no order identification in the text information, it is determined that the text information includes preset content.

[0151] According to an embodiment of the present disclosure, the solution determination module 930 includes an order analysis submodule, a channel determination submodule and a solution determination submodule.

[0152] The order analysis submodule is used to analyze the pending orders from the item dimension, order dimension and object dimension according to the operation information generated when the target items in the pending orders are operated, and obtain the analysis results.

[0153] The channel determination submodule is used to determine the type of processing channel used when processing the pending order based on the analysis result, wherein the types of processing channels include fast processing channels and ordinary processing channels.

[0154] The solution determination submodule is used to determine the processing solution for the order to be processed according to the type of processing channel and operation information.

[0155] According to an embodiment of the present disclosure, the order analysis submodule includes an item matching unit, an order filtering unit, an object analysis unit and a result determination unit.

[0156] The item matching unit is used to match the item identifier of the target item with the identifiers of multiple negative items in the negative item set to obtain a first analysis result, wherein the negative items in the negative item set are obtained by screening multiple items using an item filtering rule corresponding to the fast processing channel.

[0157] An order filtering unit is used to analyze the order information in the operation information according to the order analysis rules corresponding to the fast processing channel to obtain a second analysis result, wherein the order analysis rules respectively include analysis rules corresponding to at least one of the resource value, order type, order status and processing period in the order information.

[0158] The object analysis unit is used to analyze the object portrait information of the object according to the object analysis rules corresponding to the fast processing channel to obtain a third analysis result, wherein the object analysis rules include analysis rules corresponding to the remaining usage times of the fast processing channel and the object evaluation value in the object portrait information respectively.

[0159] The result determination unit is used to determine the analysis result of the order to be processed according to the first analysis result, the second analysis result and the third analysis result.

[0160] According to an embodiment of the present disclosure, the solution determination submodule includes an operation analysis unit, a first solution unit and a second solution unit.

[0161] The operation analysis unit is used to determine the item category and resource value of the target item based on the operation information when the type of the processing channel is a fast processing channel.

[0162] The first solution determination unit is used to determine the processing solution as providing a service of returning only resources when it is determined that the item category is a preset category and the resource value is less than a first preset resource value, or when the item category is not a preset category and the resource value is less than or equal to a second preset resource value, wherein the first preset resource value is greater than the second preset resource value.

[0163] The second solution determination unit is used to determine that the processing solution is to provide a service for returning resources after the object returns the target item when it is determined that the item category is a preset category and the resource value is greater than or equal to the first preset resource value, or when the item category is not a preset category and the resource value is greater than the second preset resource value.

[0164] According to an embodiment of the present disclosure, the interactive device 900 includes an order screening module, a screening display module and a processing determination module.

[0165] The order screening module is used to screen out alternative order information that can be used for order processing in a fast processing channel by performing multi-dimensional analysis on multiple historical order information of the object when it is determined that the number of historical order information is greater than a preset number.

[0166] The screening and display module is used to display order selection information including multiple alternative order information on the interactive interface.

[0167] The processing determination module is used to determine a processing plan for the order to be processed based on the operation information of the order to be processed when receiving the order to be processed determined by the object according to the order selection information.

[0168] According to an embodiment of the present disclosure, the interactive device 900 includes a number determination module and a rejection display module.

[0169] The number determination module is used to determine the number of times the subject inputs text information representing the presence of negative emotions within a preset time period.

[0170] The display rejection module is used to refuse to display the order selection information in the interactive interface when it is determined that the number of input times is greater than the preset number of times.

[0171] According to an embodiment of the present disclosure, the interactive device 900 includes a cause display module and a solution execution module.

[0172] The reason display module is used to display the reason selection items corresponding to the pending order in the interactive interface when it is determined that the operation information of the pending order does not include the processing reason.

[0173] The solution execution module is used to execute the corresponding processing solution based on the processing reason when receiving the processing reason determined by the object based on the reason selection item.

[0174] According to an embodiment of the present disclosure, the interactive device 900 includes an order sending module and a processing rejection module.

[0175] The order sending module is used to send the pending order to the server when it is determined that the processing reason is that the resource value of the target item does not match the target item, so that the server can perform a judgment on the pending order, wherein the judgment is used to determine the authenticity of the processing reason.

[0176] The rejection processing module is used to display the rejection item of the pending order processing rejection in the interactive interface when receiving the judgment result returned by the server, which represents that the resource value matches the target item.

[0177] According to an embodiment of the present disclosure, the interaction device 900 includes a state determination module and a state display module.

[0178] The status determination module is used to determine the processing status of the pending orders on at least one processing node according to the processing progress of the pending orders whose processing channel is a fast processing channel.

[0179] The status display module is used to display corresponding status items in the interactive interface according to different processing statuses.

[0180] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0181] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above method.

[0182] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the above method.

[0183] According to an embodiment of the present disclosure, a computer program product includes a computer program, and the computer program implements the above method when executed by a processor.

[0184] Fig.10 A block diagram of an electronic device suitable for implementing an interactive method according to an embodiment of the present disclosure is schematically shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0185] like Fig.10 As shown, the device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0186] A number of components in the device 1000 are connected to the I / O interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; a storage unit 1008, such as a disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0187] The computing unit 1001 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1001 performs the various methods and processes described above, such as the interactive method. For example, in some embodiments, the interactive method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the interactive method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform the interactive method in any other appropriate manner (e.g., by means of firmware).

[0188] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0189] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0190] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0191] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0192] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0193] A computer system may include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises through computer programs running on respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server combined with a blockchain.

[0194] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0195] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An interactive method, comprising: Performing intent recognition and content recognition on the text information input by the object through the interactive interface, respectively, to obtain intent recognition results and content recognition results; When the intention recognition result indicates that the subject has negative emotions, and the content recognition result indicates that the text information includes preset content, displaying order selection information in the interactive interface according to the multiple historical order information of the subject; By performing a multi-dimensional analysis on the pending orders determined by the object on the interactive interface based on the order selection information, a processing plan for the pending orders is determined.

2. The method according to claim 1, wherein: The performing intention recognition and content recognition on the text information input by the object through the interactive interface to obtain intention recognition results and content recognition results respectively includes: Matching the keywords extracted from the text information with a plurality of regular expressions to obtain the intention recognition result, wherein the regular expressions are obtained based on keywords of negative emotions; The order identification is performed on the text information to obtain the content identification result, wherein when the content identification result indicates that the order identification does not exist in the text information, it is determined that the text information includes the preset content.

3. The method according to claim 1, wherein: The step of performing a multi-dimensional analysis on the pending orders determined by the object on the interactive interface based on the order selection information to determine a processing plan for the pending orders includes: According to the operation information generated when the target item in the pending order is operated, the pending order is analyzed from the item dimension, the order dimension and the object dimension to obtain the analysis result; Determining the type of processing channel used when processing the pending order based on the analysis result, wherein the type of processing channel includes a fast processing channel and a normal processing channel; A processing plan for the order to be processed is determined according to the type of the processing channel and the operation information.

4. The method according to claim 3, wherein: According to the operation information generated when the target item in the pending order is operated, the pending order is analyzed from the item dimension, the order dimension and the object dimension to obtain the analysis results, including: Matching the item identifier of the target item with identifiers of multiple negative items in a negative item set to obtain a first analysis result, wherein the negative items in the negative item set are obtained by screening multiple items using an item filtering rule corresponding to the fast processing channel; Analyzing the order information in the operation information according to the order analysis rule corresponding to the fast processing channel to obtain a second analysis result, wherein the order analysis rule includes an analysis rule corresponding to at least one of a resource value, an order type, an order status, and a processing period in the order information; Analyzing the object portrait information of the object according to the object analysis rule corresponding to the fast processing channel to obtain a third analysis result, wherein the object analysis rule includes analysis rules corresponding to the remaining number of uses of the fast processing channel and the object evaluation value in the object portrait information respectively; An analysis result of the order to be processed is determined according to the first analysis result, the second analysis result and the third analysis result.

5. The method according to claim 3, wherein: Determining a processing plan for the pending order according to the type of the processing channel and the operation information includes: In a case where the type of the processing channel is the fast processing channel, determining the item category and resource value of the target item based on the operation information; In the case where it is determined that the item category is a preset category and the resource value is less than a first preset resource value, or the item category is not the preset category and the resource value is less than or equal to a second preset resource value, determining that the processing solution is to provide a service of returning only resources, wherein the first preset resource value is greater than the second preset resource value; When it is determined that the item category is a preset category and the resource value is greater than or equal to the first preset resource value, or, when the item category is not the preset category and the resource value is greater than the second preset resource value, the processing solution is determined to provide a service for returning resources after the object returns the target item.

6. The method according to claim 3, further comprising: When it is determined that the number of the historical order information is greater than the preset number, by performing a multi-dimensional analysis on the multiple historical order information of the object, candidate order information that can be used for order processing in the fast processing channel is screened out; Displaying order selection information including a plurality of the candidate order information on the interactive interface; When receiving the pending order determined by the object according to the order selection information, a processing plan for the pending order is determined based on the operation information of the pending order.

7. The method according to claim 1, further comprising: Determine the number of times the subject inputs text information representing the presence of the negative emotion within a preset time period; When it is determined that the input number is greater than the preset number, the order selection information is refused to be displayed in the interactive interface.

8. The method according to claim 1, further comprising: When it is determined that the operation information of the pending order does not include a processing reason, displaying a reason selection item corresponding to the pending order in the interactive interface; When receiving the processing reason determined by the object based on the reason selection item, a corresponding processing solution is executed based on the processing reason.

9. The method according to claim 8, further comprising: When it is determined that the processing reason is that the resource value of the target item does not match the target item, the pending order is sent to the server so that the server performs a judgment process on the pending order, wherein the judgment process is used to determine the authenticity of the processing reason; When receiving the judgment result returned by the server, which indicates that the resource value matches the target item, a rejection item for rejecting the processing of the pending order is displayed in the interactive interface.

10. The method according to claim 3, further comprising: For the pending orders whose processing channel is the fast processing channel, determining the processing status of the pending orders on at least one processing node according to the processing progress of the pending orders; According to different processing states, corresponding status items are displayed in the interactive interface.

11. An interactive device, comprising: The intention recognition module is used to perform intention recognition and content recognition on the text information input by the object through the interactive interface, and obtain intention recognition results and content recognition results; A selection generation module, configured to display order selection information in the interactive interface based on a plurality of historical order information of the object, when the intention recognition result indicates that the object has negative emotions and the content recognition result indicates that the text information includes preset content; A solution determination module is used to determine a processing solution for the pending orders by performing a multi-dimensional analysis on the pending orders determined by the object in the interactive interface based on the order selection information.

12. The device according to claim 11, wherein The intention recognition module includes: A regular matching submodule, used for matching the keywords extracted from the text information with a plurality of regular expressions to obtain the intention recognition result, wherein the regular expressions are obtained based on the keywords of negative emotions; The identification recognition submodule is used to perform order identification on the text information to obtain the content identification result, wherein when the content identification result indicates that the order identification does not exist in the text information, it is determined that the text information includes the preset content.

13. The device according to claim 11, wherein: The scheme determination module includes: An order analysis submodule, configured to analyze the pending order from the item dimension, order dimension and object dimension respectively according to the operation information generated when the target item in the pending order is operated, and obtain an analysis result; A channel determination submodule, used to determine the type of processing channel used when processing the pending order based on the analysis result, wherein the type of processing channel includes a fast processing channel and a normal processing channel; The solution determination submodule is used to determine the processing solution for the to-be-processed order according to the type of the processing channel and the operation information.

14. The device according to claim 13, wherein: The order analysis submodule includes: an item matching unit, configured to match the item identifier of the target item with identifiers of multiple negative items in a negative item set to obtain a first analysis result, wherein the negative items in the negative item set are obtained by screening multiple items using an item filtering rule corresponding to the fast processing channel; an order filtering unit, configured to analyze the order information in the operation information according to an order analysis rule corresponding to the fast processing channel to obtain a second analysis result, wherein the order analysis rule includes an analysis rule corresponding to at least one of a resource value, an order type, an order status, and a processing period in the order information; an object analysis unit, configured to analyze the object portrait information of the object according to an object analysis rule corresponding to the fast processing channel to obtain a third analysis result, wherein the object analysis rule includes analysis rules corresponding to the remaining number of uses of the fast processing channel and the object evaluation value in the object portrait information respectively; A result determination unit is used to determine an analysis result of the to-be-processed order according to the first analysis result, the second analysis result and the third analysis result.

15. The device according to claim 13, wherein: The scheme determination submodule includes: an operation analysis unit, configured to determine, when the type of the processing channel is the fast processing channel, an item category and a resource value of the target item based on the operation information; a first solution determination unit, configured to determine that the processing solution is to provide a service of returning only resources when it is determined that the item category is a preset category and the resource value is less than a first preset resource value, or when the item category is not the preset category and the resource value is less than or equal to a second preset resource value, wherein the first preset resource value is greater than the second preset resource value; The second solution determination unit is used to determine that the processing solution is to provide a service for returning resources after the object returns the target item when it is determined that the item category is a preset category and the resource value is greater than or equal to the first preset resource value, or when the item category is not the preset category and the resource value is greater than a second preset resource value.

16. The apparatus according to claim 13, further comprising: An order screening module, for screening out candidate order information that can be used for order processing in the fast processing channel by performing multi-dimensional analysis on the multiple historical order information of the object when it is determined that the number of the historical order information is greater than a preset number; A screening and display module, used for displaying order selection information including a plurality of candidate order information on the interactive interface; The processing determination module is used to determine a processing plan for the pending order based on the operation information of the pending order when receiving the pending order determined by the object according to the order selection information.

17. The apparatus according to claim 11, further comprising: A number determination module, used to determine the number of times the subject inputs text information representing the presence of the negative emotion within a preset time period; The display rejection module is used to refuse to display the order selection information in the interactive interface when it is determined that the input number is greater than a preset number.

18. The apparatus according to claim 11, further comprising: A reason display module, configured to display a reason selection item corresponding to the order to be processed in the interactive interface when it is determined that the operation information of the order to be processed does not include a processing reason; The solution execution module is used to execute the corresponding processing solution based on the processing reason when receiving the processing reason determined by the object based on the reason selection item.

19. The apparatus according to claim 18, further comprising: An order sending module, for sending the pending order to a server when it is determined that the processing reason is that the resource value of the target item does not match the target item, so that the server performs a judgment process on the pending order, wherein the judgment process is used to determine the authenticity of the processing reason; A processing rejection module is used to display a rejection item for rejecting the processing of the pending order in the interactive interface when receiving a judgment result returned by the server indicating that the resource value matches the target item.

20. The apparatus of claim 13, further comprising: A status determination module, for determining, for a pending order whose processing channel is the fast processing channel, a processing status of the pending order on at least one processing node according to a processing progress of the pending order; The status display module is used to display corresponding status items in the interactive interface according to different processing states.

21. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-11.

23. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images