Intelligent response method, device, server and medium

Abstract

The embodiments of the present invention disclose an intelligent answering method, device, server, and medium. The method comprises: obtaining an item comparison question for a current item, determining preset attribute information corresponding to the current item based on a pre-established item entity vocabulary; determining an item to be compared based on the item comparison question, the preset attribute information, and the item entity vocabulary; wherein the item entity vocabulary stores attribute information of each item; comparing the item to be compared with the item information of the current item, and generating an answer to the item comparison question based on the comparison result. Through the technical solution of the embodiments of the present invention, it is possible to identify the item to be compared corresponding to the current item based on the item comparison question raised by the user, automatically generate an answer to the item comparison question based on the comparison result, and improve the matching degree of the item information comparison objects.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of information processing technology, and in particular to an intelligent response method, device, server, and medium. Background Art

[0002] With the continuous development of e-commerce, the number of people consulting customer service for item information during the shopping process is increasing. Many shopping platforms have adopted intelligent customer service systems to automatically respond to questions raised by consumers.

[0003] At present, the intelligent customer service system mainly responds through a knowledge base-based response system. All questions and answers are pre-set and stored in the knowledge base. When consumers ask questions stored in the knowledge base, corresponding answers are given.

[0004] However, in the process of implementing the present invention, the inventors discovered that there are at least the following technical problems in the prior art: in the preset answering system, it is impossible to enumerate all the information of all items, and only the question-answer pairs corresponding to the items that users frequently ask questions about are stored in the knowledge base in advance. However, there are many users, and the questions they ask often involve comparisons of different items. The answering system may not match the target answers to the questions asked by users, or may get wrong answers due to matching errors. Summary of the Invention

[0005] Embodiments of the present invention provide an intelligent response method, device, server, and medium to identify items to be compared corresponding to the current item based on item comparison questions raised by users, automatically generate answers to the item comparison questions based on the comparison results, and improve the matching degree of item information comparison objects.

[0006] In a first aspect, an embodiment of the present invention provides an intelligent response method, the method comprising:

[0007] Obtaining an item comparison question for a current item, and determining preset attribute information corresponding to the current item based on a pre-established item entity vocabulary;

[0008] Determining the items to be compared based on the item comparison question, the preset attribute information, and the item entity vocabulary; wherein the item entity vocabulary stores attribute information of each item;

[0009] The item information of the item to be compared is compared with the item information of the current item, and an answer to the item comparison question is generated according to the comparison result.

[0010] Optionally, the fields in the item entity word table include item code, item owner name, category name, entity word and entity word type; wherein the entity word type is the general attribute type of the item, and the entity word is the specific attribute content under the corresponding entity word type.

[0011] Optionally, determining preset attribute information corresponding to the current item according to a pre-established item entity vocabulary includes:

[0012] According to the item code of the current item, preset attribute information corresponding to the current item is searched in the item entity vocabulary, where the preset attribute information includes the name of the item owner and the category name.

[0013] Optionally, determining the items to be compared based on the item comparison question, the preset attribute information, and the item entity vocabulary includes:

[0014] Extracting, from the item entity word list, sub-item entity words of items having the same preset attribute information as the current item according to the preset attribute information;

[0015] Performing word segmentation on the item comparison question, and extracting target entity words that are identical to the entity words included in the sub-item entity word list from the word segmentation results;

[0016] Search the sub-item entity word table for an item corresponding to the target entity word as an item to be compared.

[0017] Optionally, when the number of the items to be compared is greater than one, comparing the item information of the items to be compared with the item information of the current item includes:

[0018] When the context of the item comparison question contains relevant information of any of the items to be compared, the item to be compared corresponding to the relevant information is used as the target comparison item;

[0019] The target comparison item is compared with the current item.

[0020] Optionally, when the context of the item comparison question does not include relevant information of any of the items to be compared, the method further includes:

[0021] When the item details page of the current item contains any of the items to be compared, the item to be compared contained in the item details page is used as a target comparison item;

[0022] The target comparison item is compared with the current item.

[0023] Optionally, when the item details page of the current item does not include any of the items to be compared, the method further includes:

[0024] sorting the items to be compared according to their resource requirements;

[0025] Select the items to be compared in the sorting results in sequence according to the preset number of feedback items for display;

[0026] The item to be compared selected by the user is used as a target comparison item for comparison with the current item.

[0027] Optionally, the comparison result includes a parameter comparison list of the current item and the item to be compared.

[0028] In a second aspect, an embodiment of the present invention further provides an intelligent response device, the device comprising:

[0029] A question acquisition module is used to acquire an item comparison question for a current item and determine preset attribute information corresponding to the current item based on a pre-established item entity vocabulary;

[0030] a question analysis module, configured to determine the items to be compared based on the item comparison question, the preset attribute information, and the item entity vocabulary; wherein the item entity vocabulary stores the attribute information of each item;

[0031] The question answering module is used to compare the item information of the item to be compared with the item information of the current item, and generate an answer to the item comparison question based on the comparison result.

[0032] Optionally, the fields in the item entity word table include item code, item owner name, category name, entity word and entity word type; wherein the entity word type is the general attribute type of the item, and the entity word is the specific attribute content under the corresponding entity word type.

[0033] Optionally, the question acquisition module is specifically used to:

[0034] According to the item code of the current item, preset attribute information corresponding to the current item is searched in the item entity vocabulary, where the preset attribute information includes the name of the item owner and the category name.

[0035] Optionally, the problem analysis module is specifically used to:

[0036] Extracting, from the item entity word list, sub-item entity words of items having the same preset attribute information as the current item according to the preset attribute information;

[0037] Performing word segmentation on the item comparison question, and extracting target entity words that are identical to the entity words included in the sub-item entity word list from the word segmentation results;

[0038] Search the sub-item entity word table for an item corresponding to the target entity word as an item to be compared.

[0039] Optionally, when the number of the items to be compared is greater than one, the question answering module is specifically configured to:

[0040] When the context of the item comparison question contains relevant information of any of the items to be compared, the item to be compared corresponding to the relevant information is used as the target comparison item;

[0041] The target comparison item is compared with the current item.

[0042] Optionally, when the context of the item comparison question does not include relevant information of any of the items to be compared, the question answering module is further configured to:

[0043] When the item details page of the current item contains any of the items to be compared, the item to be compared contained in the item details page is used as a target comparison item;

[0044] The target comparison item is compared with the current item.

[0045] Optionally, when the item details page of the current item does not include any of the items to be compared, the question answering module is further configured to:

[0046] sorting the items to be compared according to their resource requirements;

[0047] Select the items to be compared in the sorting results in sequence according to the preset number of feedback items for display;

[0048] The item to be compared selected by the user is used as a target comparison item for comparison with the current item.

[0049] Optionally, the comparison result includes a parameter comparison list of the current item and the item to be compared. Optionally, the comparison result includes a parameter comparison list of the current item and the item to be compared.

[0050] In a third aspect, an embodiment of the present invention further provides a server, comprising:

[0051] one or more processors;

[0052] a memory for storing one or more programs;

[0053] When the one or more programs are executed by the one or more processors, the one or more processors implement the intelligent response method provided by any embodiment of the present invention.

[0054] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent response method provided by any embodiment of the present invention.

[0055] The embodiments of the above invention have the following advantages or beneficial effects:

[0056] By obtaining an item comparison question for the current item, the preset attribute information corresponding to the current item is determined in a pre-established item entity vocabulary; then, the item to be compared in the item comparison question is determined based on the item comparison question, the preset attribute information and the item entity vocabulary; finally, the item to be compared is compared with the item information of the current item, and an answer to the item comparison question is generated based on the comparison result. This supports the comparison of any two items in the item library, and is no longer limited to the items in the high-frequency questions asked by users, and also improves the matching degree of the items to be compared. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a flow chart of an intelligent response method provided by Example 1 of the present invention;

[0058] Figure 2 is a schematic diagram of a comparison result provided in Example 1 of the present invention;

[0059] Figure 3 This is a flow chart of an intelligent response method provided by Embodiment 2 of the present invention;

[0060] Figure 4 This is a schematic diagram of the structure of an intelligent response device provided in the third embodiment of the present invention;

[0061] Figure 5 This is a structural diagram of a server provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0062] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0063] Example 1

[0064] Figure 1This is a flow chart of an intelligent response method provided in Example 1 of the present invention. This embodiment is applicable to analyzing user questions and answering item comparison questions. This method can be implemented using an intelligent response device, which is configured in a server and can be implemented using software and / or hardware in the server.

[0065] like Figure 1 As shown, the intelligent response method specifically includes the following contents:

[0066] S110 , obtaining an item comparison question for the current item, and determining preset attribute information corresponding to the current item according to a pre-established item entity vocabulary.

[0067] Specifically, if the current item is one that the user is interested in, the user can enter keywords or specific content through a response system or search engine to learn about the current item. For example, if the current item is a red apple, the user can ask questions such as the nutritional value of red apples, how to use red apples, the market price of red apples, or the difference between red apples and yellow apples.

[0068] The item entity word table is a pre-established table containing attribute information for each item. To learn about an item's attributes, we can query the table based on the item's code or other identifying information. Fields in the item entity word table include the item code, the name of the item's owner, the category name, the entity word, and the entity word type. The entity word type represents the general attribute type of an item within its corresponding category, while the entity word represents the specific attribute content within the entity word type. For example, if a red apple is red, then "color" is the corresponding entity word type, and "red" is the entity word corresponding to the entity word type "color." It's understandable that different types of items may have different attribute information categorized differently depending on their characteristics. For example, the entity word types for medications include attributes such as efficacy, and the entity word types for weight scales include attributes such as weighing range. For items sold on a commercial platform, the entity word types for each item may include at least one of price, color, model, function, and item description.

[0069] The process of constructing the entity word list of an item can be a combination of automatic mining and manual filling. The manual filling method is to directly fill in the corresponding information into the table of the entity word list through manual operation. The process of automatically mining entity words for each item can refer to the following steps: Taking the item in Table 1 (item code is 100007967988) as an example, the functional module that performs entity word mining can directly put the common attribute words such as price, color, model and main function words of each item directly into its corresponding entity word list. When the owner of the item describes the item, the main functional features of the item are usually written in the title, and are distinguished by punctuation such as spaces, commas, and brackets. The functional module that performs entity word mining can segment the item title according to spaces, commas, and brackets, and after obtaining the segmentation results, the segmentation results are also placed in the entity word list. For example, the title of the item in Table 1 is "Haier 1.5 HP Inverter Wall-mounted Bedroom Air Conditioner Little Dragon Girl Self-cleaning Fast Cooling and Heating PMV One-button Comfort Silent KFR-35GW / 03JDM83A". After word segmentation by spaces and brackets, we can get: "Haier", "Haier", "1.5 HP", "Inverter Wall-mounted Bedroom Air Conditioner", "Self-cleaning", "Fast Cooling and Heating", "One-button Comfort", "Silent", "KFR-35GW / 03JDM83A" and other entity words are also put into the entity word table of the product. In addition, the functional module that performs entity word mining can also perform entity word mining on descriptive content such as subtitles and slogans of items. Specifically, the mined entity word table may include the content shown in the following table:

[0070] Table 1 Entity vocabulary of an item

[0071] Item Code Name of the party to whom the item belongs Category Name Entity words Entity word type 100007967988 Haier flagship store air conditioner 1999 price 100007967988 Haier flagship store air conditioner White color 100007967988 Haier flagship store air conditioner 03JDM83A model 100007967988 Haier flagship store air conditioner frequency conversion Function 100007967988 Haier flagship store air conditioner Level 3 energy efficiency Function 100007967988 Haier flagship store air conditioner Little Dragon Girl title 100007967988 Haier flagship store air conditioner Self-cleaning title

[0072] Furthermore, for the intelligent answering system, the item code of the current item is known, so the item code can be used to find other attribute information corresponding to the item in the item entity vocabulary, and the attribute information needed can be found from the entity vocabulary as the preset attribute information. The preset attribute information can be the attribute information under each field in the item entity vocabulary, or it can be the attribute information corresponding to each type under the entity sub-type. For example, when the item is an opinion product on a shopping platform, the preset attribute information can include the name of the owner of the item and the name of the category. Determining the preset attribute information of an item is to determine which store and category the item belongs to, so as to facilitate the search and comparison of item objects. It should be noted here that the preset attribute information can be set according to the response usage scenario and / or the category of the current item. The specific type and quantity may be different in different scenarios, and are not limited in this embodiment.

[0073] S120 , determining the items to be compared based on the item comparison question, the preset attribute information, and the item entity word list; wherein the item entity word list stores attribute information of each item.

[0074] Specifically, the process of determining the items to be compared begins by narrowing down the search for items to be compared. Based on the preset attribute information, the item entity vocabulary contains child item entity vocabulary items that have the same preset attribute information as the current item. For example, this involves finding items with the same owner and category, or items of the same category or color.

[0075] Next, the item comparison question is segmented and target entity words that are identical to those in the sub-item entity word list are extracted. This means determining which entity words are included in the user's question and using them as keywords to search for the items to be compared. For example, if the question is "What is the difference between this air conditioner and the one that costs 1999 yuan?", where "1999" is an entity word in Table 1, then the items to be compared are determined to be those priced at "1999 yuan."

[0076] Finally, we can link the items and find the items corresponding to the target entity words in the sub-item entity word list as the items to be compared.

[0077] S130: Compare the item information of the item to be compared with the item information of the current item, and generate an answer to the item comparison question based on the comparison result.

[0078] After finding the item to be compared, the attribute information of the current item and the item to be compared can be compared. The comparison result can be presented in the form of a parameter comparison list of the current item and the item to be compared. For example, Figure 2 The comparison results of the items shown. Figure 2 In the comparison, two items are compared in terms of item title, item owner name (store), evaluation, brand, origin, after-sales service, and packaging specifications. It also provides selection keys to highlight different items and hide identical items. The technical solution of this embodiment obtains an item comparison question for the current item and determines the preset attribute information corresponding to the current item in a pre-established item entity vocabulary; then, based on the item comparison question, the preset attribute information, and the item entity vocabulary, the item to be compared in the item comparison question is determined; finally, the item information of the item to be compared is compared with the item information of the current item, and the answer to the item comparison question is generated based on the comparison result. This supports the comparison of any two items in the item library, and is no longer limited to items in the high-frequency questions asked by users. It also improves the matching degree of the items to be compared.

[0079] Example 2

[0080] Figure 3 This is a flowchart of an intelligent response method provided in Example 2 of the present invention. This example further illustrates the process of determining items to be compared in the intelligent response method based on the above examples. Explanations of terms that are identical or corresponding to those in the above examples are not repeated here.

[0081] See also Figure 3 The intelligent response method provided in this embodiment specifically includes the following steps:

[0082] S210: Obtain an item comparison question for the current item, and determine preset attribute information corresponding to the current item based on a pre-established item entity vocabulary.

[0083] The current item is of interest to the user. Users can enter keywords or specific content through platforms such as answering systems or search engines to learn about the current item. First, the answering system determines whether the question is about item comparison based on the user's question content or keyword information. To determine whether the user's input is an item comparison question, machine learning can be used to train an item comparison intent classifier. This classifier uses a large number of item comparison questions as positive examples and randomly selects other questions as negative examples for classifier training. Ultimately, the classifier identifies the user's input question. Alternatively, the question can be identified through methods such as content segmentation and word matching.

[0084] When it is determined that the question entered by the user is an item comparison question for the current item, the preset attribute information corresponding to the current item can be searched in the item entity vocabulary through the item code of the current item. The preset attribute information can be set by the response platform based on the response usage scenario and / or the category of the current item.

[0085] For example, an intelligent response system is used in the intelligent customer service of an e-commerce platform, automatically answering questions raised by consumers about a particular product. When a consumer wishes to consult customer service regarding a product they purchased, they open the customer service interface and automatically or manually send the link to the product they are inquiring about to the intelligent customer service. Based on the link, the intelligent response system can then determine the product's product code. Using this product code, the system can then search the item entity vocabulary for pre-defined attribute information about the product, such as which store and category the product belongs to, or which store has which features and functions.

[0086] S220: Determine the items to be compared based on the item comparison question, the preset attribute information, and the item entity vocabulary; wherein the item entity vocabulary stores attribute information of each item.

[0087] Specifically, using the intelligent customer service scenario described in step S210 as an example, assume that the preset attribute information for the currently inquired product found in step S210 is the item owner name and category name. Using these two preset information as keywords, the item entity vocabulary can be used to match items with the same item owner name and category name, generating a child item entity vocabulary. This will find items in the same store and category as the currently inquired product; these items are likely candidates for comparison.

[0088] Then, the item comparison question is segmented using mechanical word segmentation to determine whether the comparison question contains entity words included in the sub-item entity word list. If so, the successfully matched entity words are used as target entity words. In other words, the user's question is determined to include which entity words as keywords for searching for the items to be compared. For example, the mechanical word segmentation result for "What is the difference between the price of 1999 and 1899" is "What is the difference between the price of 1999 and 1899". By removing all words longer than one character from the word segmentation result, we obtain the target entity words "1999" and "1899" in the current user's question.

[0089] Finally, we can link the items and find the items corresponding to the target entity words in the sub-item entity word list as the items to be compared.

[0090] S230. When the number of the items to be compared is greater than one, if the context of the item comparison question contains relevant information of any of the items to be compared, the item to be compared corresponding to the relevant information is used as a target comparison item, and the target comparison item is compared with the current item.

[0091] The number of items to be compared that the intelligent answering system can match may be only one, or may be two, three, or even more. Taking into account the size limitation of the terminal screen displaying the comparison results and the readability of the comparison results, the results usually displayed are one-to-one comparison results. In some embodiments, it can also be a personalized comparison result between the current item and the two items to be compared.

[0092] Taking the comparison result as a one-to-one comparison result between the current item and an item to be compared as an example, when the number of matched items to be compared is greater than one, a disambiguation step is required to determine a target comparison item for final comparison from multiple items to be compared.

[0093] First, consider whether the context of the item comparison question mentions one of the multiple items to be compared. If so, the corresponding item to be compared is directly used as the target item for the final comparison. If there are multiple items to be compared, the multiple items to be compared can be displayed, allowing the user to select the target item. If the context of the comparison question does not mention one of the multiple items to be compared, then execute step S240.

[0094] S240. When the context of the item comparison question does not include relevant information of any of the items to be compared, if the item details page of the current item includes any of the items to be compared, the item to be compared included in the item details page is used as a target comparison item, and the target comparison item is compared with the current item.

[0095] If the context of the item comparison question does not contain relevant information about any of the items to be compared, the process then further considers whether the details page of the current item description displays one or more of the items to be compared. If so, and if there are only a single item, the corresponding item to be compared on the details page can be used as the target comparison item. If there are multiple items to be compared, the multiple items can be displayed, allowing the user to select the target comparison item. Furthermore, if the details page of the current item description does not mention any of the multiple items to be compared, then step S250 is executed.

[0096] S250. When the item details page of the current item does not include any of the items to be compared, the items to be compared are sorted according to the resource requirements of the items; the items to be compared in the sorting results are sequentially selected for display according to the preset number of feedback items; and the item to be compared selected by the user is used as the target comparison item for comparison with the current item.

[0097] The resource demand may be sales volume when the current item is a commodity, or parameters such as attention level and recommendation value when the current item is not a commodity. When the context of the prioritized item comparison question and the current item details page do not contain a matching item to be compared, and there are multiple items to be compared, the items to be compared may be sorted according to their resource demand; items to be compared from the sorted results may be selected and displayed in sequence according to the preset number of feedback items; and the item to be compared selected by the user may be used as the target comparison item for comparison with the current item.

[0098] Furthermore, when it is determined that the content input by the user is an item comparison question for the current item, the intelligent answering system can be used to check whether there is a preset corresponding answer. If not, the method steps of this embodiment can be executed.

[0099] The technical solution of this embodiment obtains an item comparison question for the current item and determines the preset attribute information corresponding to the current item in a pre-established item entity vocabulary; then, the items to be compared in the item comparison question are determined based on the item comparison question, the preset attribute information, and the item entity vocabulary; when there are multiple items to be compared, the final target comparison item is selected through a set disambiguation step, and finally the target comparison item is compared with the item information of the current item, and an answer to the item comparison question is generated based on the comparison result. This supports the comparison of any two items in the item library, and is no longer limited to the items in the high-frequency questions asked by users, and also improves the matching degree of the items to be compared.

[0100] The following is an embodiment of an intelligent response device provided by an embodiment of the present invention. This device and the intelligent response methods of the above embodiments are based on the same inventive concept and can be used to implement the intelligent response methods of the above embodiments. For details not fully described in the embodiment of the intelligent response device, please refer to the embodiment of the intelligent response method described above.

[0101] Example 3

[0102] Figure 4 This is a schematic diagram of the structure of an intelligent answering device provided by the third embodiment of the present invention. This embodiment is applicable to the case where the answering system automatically answers questions about item comparison. Figure 4 As shown, the device specifically includes a question acquisition module 310 , a question analysis module 320 and a question answering module 330 .

[0103] Among them, the question acquisition module 310 is used to obtain an item comparison question for the current item, and determine the preset attribute information corresponding to the current item based on a pre-established item entity vocabulary; the question analysis module 320 is used to determine the item to be compared based on the item comparison question, the preset attribute information and the item entity vocabulary; wherein the item entity vocabulary stores the attribute information of each item; the question answering module 330 is used to compare the item to be compared with the item information of the current item, and generate an answer to the item comparison question based on the comparison result.

[0104] The technical solution of this embodiment obtains an item comparison question for the current item and determines the preset attribute information corresponding to the current item in a pre-established item entity vocabulary; then, the item to be compared in the item comparison question is determined based on the item comparison question, the preset attribute information, and the item entity vocabulary; finally, the item to be compared is compared with the item information of the current item, and an answer to the item comparison question is generated based on the comparison result. This supports the comparison of any two items in the item library, and is no longer limited to items in high-frequency questions asked by users, and also improves the matching degree of the items to be compared.

[0105] Optionally, the fields in the item entity word table include item code, item owner name, category name, entity word and entity word type; wherein the entity word type is the general attribute type of the item, and the entity word is the specific attribute content under the corresponding entity word type.

[0106] Optionally, the question acquisition module is specifically used to:

[0107] According to the item code of the current item, preset attribute information corresponding to the current item is searched in the item entity vocabulary, where the preset attribute information includes the name of the item owner and the category name.

[0108] Optionally, the problem analysis module is specifically used to:

[0109] Extracting, from the item entity word list, sub-item entity words of items having the same preset attribute information as the current item according to the preset attribute information;

[0110] Performing word segmentation on the item comparison question, and extracting target entity words that are identical to the entity words included in the sub-item entity word list from the word segmentation results;

[0111] Search the sub-item entity word table for an item corresponding to the target entity word as an item to be compared.

[0112] Optionally, when the number of the items to be compared is greater than one, the question answering module is specifically configured to:

[0113] When the context of the item comparison question contains relevant information of any of the items to be compared, the item to be compared corresponding to the relevant information is used as the target comparison item;

[0114] The target comparison item is compared with the current item.

[0115] Optionally, when the context of the item comparison question does not include relevant information of any of the items to be compared, the question answering module is further configured to:

[0116] When the item details page of the current item contains any of the items to be compared, the item to be compared contained in the item details page is used as a target comparison item;

[0117] The target comparison item is compared with the current item.

[0118] Optionally, when the item details page of the current item does not include any of the items to be compared, the question answering module is further configured to:

[0119] sorting the items to be compared according to their resource requirements;

[0120] Select the items to be compared in the sorting results in sequence according to the preset number of feedback items for display;

[0121] The item to be compared selected by the user is used as a target comparison item for comparison with the current item.

[0122] Optionally, the comparison result includes a parameter comparison list of the current item and the item to be compared. Optionally, the comparison result includes a parameter comparison list of the current item and the item to be compared.

[0123] The intelligent response device provided in the embodiment of the present invention can execute the intelligent response method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0124] Example 4

[0125] Figure 5 A schematic diagram of the structure of a server provided in embodiment 4 of the present invention. Figure 5 A block diagram of an exemplary server 12 suitable for use in implementing embodiments of the present invention is shown. Figure 5 The server 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0126] like Figure 5 As shown, server 12 is implemented as a general-purpose computing device. Components of server 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and a bus 18 that connects various system components (including system memory 28 and processing units 16).

[0127] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0128] The server 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the server 12, including volatile and non-volatile media, removable and non-removable media.

[0129] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Server 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be configured to read and write non-removable, non-volatile magnetic media ( Figure 5 Not shown, often called a "hard drive"). Although Figure 5 Not shown, a magnetic disk drive for reading and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

[0130] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0131] The server 12 may also communicate with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the server 12, and / or any device that enables the server 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may occur via an input / output (I / O) interface 22. Furthermore, the server 12 may communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the server 12 via a bus 18. It should be understood that, although not shown, other hardware and / or software modules may be used in conjunction with the server 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0132] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the steps of an intelligent response method provided in an embodiment of the present invention, which includes:

[0133] Obtaining an item comparison question for a current item, and determining preset attribute information corresponding to the current item based on a pre-established item entity vocabulary;

[0134] Determining the items to be compared based on the item comparison question, the preset attribute information, and the item entity vocabulary; wherein the item entity vocabulary stores attribute information of each item;

[0135] The item information of the item to be compared is compared with the item information of the current item, and an answer to the item comparison question is generated according to the comparison result.

[0136] Of course, those skilled in the art will understand that the processor can also implement the technical solution of the intelligent response method provided by any embodiment of the present invention.

[0137] Example 5

[0138] This fifth embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps of the intelligent response method provided in any embodiment of the present invention are implemented. The method includes:

[0139] Obtaining an item comparison question for a current item, and determining preset attribute information corresponding to the current item based on a pre-established item entity vocabulary;

[0140] Determining the items to be compared based on the item comparison question, the preset attribute information, and the item entity vocabulary; wherein the item entity vocabulary stores attribute information of each item;

[0141] The item information of the item to be compared is compared with the item information of the current item, and an answer to the item comparison question is generated according to the comparison result.

[0142] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0143] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0144] Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0145] The computer program code for performing the operations of the present invention can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0146] Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using a general-purpose computing device. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they can be implemented using program code executable by a computer device, which can then be stored in a storage device and executed by the computing device. Alternatively, they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

[0147] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. An intelligent answering method, characterized in that: include: Obtaining an item comparison question for a current item, and determining preset attribute information corresponding to the current item based on a pre-established item entity vocabulary; Determining the items to be compared based on the item comparison question, the preset attribute information, and the item entity vocabulary; wherein the item entity vocabulary stores attribute information of each item; Comparing the item information of the item to be compared with the item information of the current item, and generating an answer to the item comparison question based on the comparison result; When the number of the items to be compared is greater than one, comparing the item information of the item to be compared with the item information of the current item includes: When the context of the item comparison question contains relevant information about one of the items to be compared, the item to be compared corresponding to the relevant information of the item is used as the target comparison item; when the context of the item comparison question contains relevant information about multiple items to be compared, the relevant information of the multiple items is displayed, and the item to be compared selected by the user is used as the target comparison item; The target comparison item is compared with the current item.

2. The method according to claim 1, characterized in that The fields in the item entity word table include item code, item owner name, category name, entity word and entity word type; wherein the entity word type is the general attribute type of the item, and the entity word is the specific attribute content under the corresponding entity word type.

3. The method according to claim 2, characterized in that Determining preset attribute information corresponding to the current item based on a pre-established item entity vocabulary includes: According to the item code of the current item, preset attribute information corresponding to the current item is searched in the item entity vocabulary, where the preset attribute information includes the name of the item owner and the category name.

4. The method according to claim 2 or 3, characterized in that The determining of the items to be compared based on the item comparison question, the preset attribute information, and the item entity vocabulary includes: Extracting, from the item entity word list, sub-item entity words of items having the same preset attribute information as the current item according to the preset attribute information; Performing word segmentation on the item comparison question, and extracting target entity words that are identical to the entity words included in the sub-item entity word list from the word segmentation results; Search the sub-item entity word table for an item corresponding to the target entity word as an item to be compared.

5. The method according to claim 1, wherein When the context of the item comparison question does not include relevant information of any of the items to be compared, the method further includes: When the item details page of the current item contains any of the items to be compared, the item to be compared contained in the item details page is used as a target comparison item; The target comparison item is compared with the current item.

6. The method according to claim 5, characterized in that When the item details page of the current item does not include any of the items to be compared, the method further includes: sorting the items to be compared according to their resource requirements; Select the items to be compared in the sorting results in sequence according to the preset number of feedback items for display; The item to be compared selected by the user is used as a target comparison item for comparison with the current item.

7. The method according to claim 1, characterized in that The comparison result includes a parameter comparison list of the current item and the item to be compared.

8. An intelligent answering device, characterized in that: include: A question acquisition module is used to acquire an item comparison question for a current item and determine preset attribute information corresponding to the current item based on a pre-established item entity vocabulary; a question analysis module, configured to determine the items to be compared based on the item comparison question, the preset attribute information, and the item entity vocabulary; wherein the item entity vocabulary stores the attribute information of each item; a question answering module, configured to compare the item information of the item to be compared with the item information of the current item, and generate an answer to the item comparison question based on the comparison result; When the number of the items to be compared is greater than one, the question answering module is specifically configured to: When the context of the item comparison question contains relevant information about one of the items to be compared, the item to be compared corresponding to the relevant information of the item is used as the target comparison item; when the context of the item comparison question contains relevant information about multiple items to be compared, the relevant information of the multiple items is displayed, and the item to be compared selected by the user is used as the target comparison item; The target comparison item is compared with the current item.

9. A server, characterized in that: The server includes: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the intelligent response method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the intelligent response method as described in any one of claims 1 to 7 is implemented.

Images