User demand processing method and device

Abstract

The invention provides a user demand processing method and device, and relates to the technical field of Internet. The user demand processing method comprises the steps of obtaining a target demand of a user, judging whether a field matched with the target demand can be found in data information or not according to the target demand, if yes, finding a target field matched with the target demand and outputting the target field, and if not, processing the target demand according to a preset rule, and obtaining a plurality of related fields corresponding to the target demand, searching the plurality of related fields in the data information, and outputting the plurality of related fields. According to the technical scheme, when it is judged that the field matched with the target demand cannot be found in the data information according to the user demand, the target demand, namely the fixed field corresponding to the fuzzy demand can be determined according to the preset rule, so that the field corresponding to the fuzzy demand is determined, and the user experience is improved. The field corresponding to the fuzzy demand can be found in the data information and output, so that the fuzzy demand in the user demand can be processed.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a method and device for processing user needs. Background Art

[0002] With the continuous development of Internet technology, more and more users are using browsers and applications. In the process of using browsers and applications, a large amount of data information will be derived, such as user information and transaction record information. In order to reuse a large amount of data information, a large amount of data information will be stored in the database. When a user needs to use data information, the required data information must be extracted from the database. Extracting the required data information must be achieved by processing user needs.

[0003] At present, in order to process user needs, it is necessary to search for corresponding fields in the data information according to the user needs, and output the data content corresponding to the found fields. However, user needs can be divided into clear needs and fuzzy needs. Clear needs have fixed fields corresponding to the data information, and the corresponding fields can be found in the data information. However, there are no corresponding fixed fields in the data information for fuzzy needs, that is, the fields corresponding to fuzzy needs are uncertain, so the fields corresponding to the fuzzy needs cannot be found in the data information. In this way, the fuzzy needs cannot be processed, and the failure to process the fuzzy needs will result in the user not being able to use the fields corresponding to the fuzzy needs. Therefore, how to process the fuzzy needs in user needs is an urgent problem to be solved. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method and device for processing user needs, so as to solve the problem of how to process ambiguous needs among user needs.

[0005] In order to solve the above technical problems, the embodiments of the present application provide the following technical solutions:

[0006] The first aspect of the present application provides a method for processing user needs, the method comprising:

[0007] Obtain the user's target needs;

[0008] According to the target requirement, determining whether a field matching the target requirement can be found in the data information;

[0009] If yes, then search for a target field that matches the target requirement and output the target field;

[0010] If not, the target requirement is processed according to a preset rule to obtain a plurality of related fields corresponding to the target requirement;

[0011] The multiple related fields are searched in the data information, and the multiple related fields are output.

[0012] A second aspect of the present application provides a device for processing user needs, the device comprising:

[0013] Acquisition module, used to obtain the user's target needs;

[0014] A judgment module, used to judge whether a field matching the target requirement can be found in the data information according to the target requirement;

[0015] A first search module, configured to search for a target field that matches the target requirement and output the target field;

[0016] A processing module, for processing the target requirement according to a preset rule to obtain a plurality of related fields corresponding to the target requirement if no;

[0017] The second search module is used to search for the multiple related fields in the data information and output the multiple related fields.

[0018] A third aspect of the present application provides a computer-readable storage medium, the storage medium including a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the method for processing user needs of the above-mentioned first aspect or any optional embodiment of the first aspect.

[0019] The fourth aspect of the present application provides an electronic device, which includes: at least one processor; and at least one memory and a bus connected to the processor; wherein the processor and the memory communicate with each other through the bus; the processor is used to call program instructions in the memory to execute the method for processing user needs of the above-mentioned first aspect or any optional embodiment of the first aspect.

[0020] Compared with the prior art, the method and device for processing user needs provided by the present application determine whether a field matching the target need can be found in the data information through the user need, that is, determine whether the user need is a clear need or a fuzzy need. When a field matching the target need cannot be found in the data information, that is, when the user need is a fuzzy need, the fuzzy need is processed according to a preset rule, and multiple related fields corresponding to the fuzzy need can be obtained. In other words, the related fields corresponding to the fuzzy need in the data information can be determined, so that the fields corresponding to the fuzzy need in the data information are determined, and the fields corresponding to the fuzzy need can be found in the data information, and the fuzzy need can also be found. The field output corresponding to the demand can handle the fuzzy demands in the user's demands; compared with the prior art which can only handle the clear demands in the user's demands, and cannot find the corresponding fields in the data information for the fuzzy demands, and cannot feedback any search result information to the user or can only feedback the search error information to the user, the present invention can obtain the relevant fields of the fuzzy demands after processing the fuzzy demands according to preset rules, and can find the fields corresponding to the fuzzy demands in the data information, and promptly feedback the relevant fields corresponding to the fuzzy demands to the users, and the users can promptly obtain the search results of the fuzzy demands by searching the fuzzy demands, so that the users have a better search experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easy to understand. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0022] Figure 1 Schematically shows the process of processing user needs Figure 1 ;

[0023] Figure 2 Schematically shows the process of processing user needs Figure 2 ;

[0024] Figure 3 Schematically shows the process of processing user needs Figure 3 ;

[0025] Figure 4 Schematic diagram showing the structure of the user demand processing device Figure 1 ;

[0026] Figure 5 Schematic diagram showing the structure of the user demand processing device Figure 2 ;

[0027] Figure 6The structure diagram of an electronic device is schematically shown. DETAILED DESCRIPTION

[0028] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0029] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by technicians in the field to which this application belongs.

[0030] For the processing of user needs, the prior art can only process clear needs in user needs, but cannot process fuzzy needs in user needs. Therefore, the present invention takes into account that the prior art cannot process fuzzy needs, resulting in the user being unable to use the fields corresponding to the fuzzy needs, and needs a way to process fuzzy needs, replacing the prior art that cannot process fuzzy needs. To this end, the present invention selects a way to process fuzzy needs in user needs, and can process the target needs according to preset rules to obtain multiple related fields corresponding to the target needs, that is, according to the preset rules, the fixed fields corresponding to the fuzzy needs can be determined, so that the fields corresponding to the fuzzy needs are determined, and the corresponding fields can be found in the data information and output, which also realizes the processing of fuzzy needs in user needs, and can ensure that the user uses the fields corresponding to the fuzzy needs. The main idea of ​​the present invention is to judge the user needs, whether the user needs are clear needs or fuzzy needs, that is, to judge whether the fields matching the target needs can be found in the data information according to the user needs. When the user needs are fuzzy needs, that is, when the fields matching the target needs cannot be found in the data information, the fixed fields corresponding to the fuzzy needs can be determined according to the preset rules, and the corresponding fields can be found in the data information and output.

[0031] The method in the embodiment of the present invention is described in detail below.

[0032] Figure 1 A flowchart schematically shows a method for processing user needs in an embodiment of the present invention, see Figure 1 As shown, the method may include:

[0033] S101. Obtain the user's target needs.

[0034] The user's target needs include clear needs and fuzzy needs, i.e., unclear needs. Clear needs refer to needs that have corresponding fixed fields in the data information, and the fields in the data information corresponding to clear needs are certain. Fuzzy needs refer to needs that do not have corresponding fixed fields in the data information, and the fields in the data information corresponding to fuzzy needs are uncertain.

[0035] For example, the user's target demand is name, and name has a fixed field corresponding to it in the data information. Name can correspond to Zhang San, and name is a clear demand. The user's target demand is user information, and user information has no corresponding fixed field in the data information. User information is a fuzzy demand.

[0036] When the field corresponding to the target requirement is needed, the target requirement of the user can be obtained. The field corresponding to the target requirement can be a field corresponding to the statistical target requirement or a field corresponding to the analytical target requirement. There can be multiple fields corresponding to the target requirement, which are not limited here.

[0037] S102: According to the target requirement, it is determined whether a field matching the target requirement can be found in the data information.

[0038] Specifically, according to the target requirement obtained in step S101, it is determined whether a field matching the target requirement can be found in the data information.

[0039] The data information may be data in the JavaScript Object Notation (JSON) format, data in the txt format, or user behavior log data. There may be many types of data information, which are not limited here.

[0040] Since explicit requirements have corresponding fixed fields in the data information, while fuzzy requirements have no corresponding fixed fields in the data information, in order to determine whether the target requirement is an explicit requirement or a fuzzy requirement, it is necessary to determine whether a field matching the target requirement can be found in the data information based on the target requirement.

[0041] Exemplarily, there are two target requirements, one target requirement is name, and the other target requirement is user information. It is determined whether a field matching the name can be found in the data information, and it is determined whether a field matching the user information can be found in the data information.

[0042] It is determined whether a field matching the target requirement can be found in the data information according to the target requirement. If so, step S103 is executed; if not, step S104 is executed.

[0043] S103: Find a target field that matches the target requirement and output the target field.

[0044] Specifically, when a field matching the target requirement can be found in the data information according to the determination in step S102, the target field matching the target requirement is found and output.

[0045] When a field matching the target requirement can be found in the data information, it means that there is a field corresponding to the target requirement in the data information. That is to say, when the target requirement is a clear requirement, you only need to directly search for the target field matching the clear requirement in the data information, and output the target field after finding the target field. In this way, you can get the target field corresponding to the clear requirement, which is convenient for directly using the target field corresponding to the clear requirement.

[0046] Continuing with the example of step S102, the fields matching the name are searched, and the found fields are Zhang San, Li Si and Zhao Wu, so Zhang San, Li Si and Zhao Wu are output.

[0047] S104: Process the target demand according to preset rules to obtain multiple related fields corresponding to the target demand.

[0048] Specifically, when it is determined in step S102 that no field matching the target requirement can be found in the data information, the target requirement is processed according to a preset rule to obtain a plurality of related fields corresponding to the target requirement.

[0049] When a field matching the target demand cannot be found in the data information, it means that the field corresponding to the target demand does not exist in the data information, that is, the target demand is a fuzzy demand. At this time, the fuzzy demand needs to be processed so that the fuzzy demand corresponds to a fixed field in the data information, that is, a field matching the fuzzy demand can be found in the data information. Specifically, the fuzzy demand is processed according to preset rules, and multiple related fields corresponding to the fuzzy demand are obtained after processing, that is, the fuzzy demand corresponds to a fixed field in the data information.

[0050] Continuing with the example of step S102, the target requirement is user information, but no fields matching the user information can be found in the data information. The user information needs to be processed according to preset rules to obtain fields of name, age, occupation and region. Name, age, occupation and region are relevant fields corresponding to the user information.

[0051] S105. Search for multiple related fields in the data information, and output the multiple related fields.

[0052] Specifically, the multiple related fields obtained in step S104 are searched in the data information, and the multiple related fields are output.

[0053] When it is judged according to the target demand that no field matching the target demand can be found in the data information, that is, when the target demand is a fuzzy demand, the fuzzy demand is processed according to the preset rules to obtain multiple related fields corresponding to the fuzzy demand, and the multiple related fields corresponding to the fuzzy demand are searched in the data information, and the multiple related fields are output after finding the multiple related fields. In this way, the related fields corresponding to the fuzzy demand can be obtained, which is convenient for directly using the related fields corresponding to the fuzzy demand.

[0054] Continuing with the example of step S104, after processing the user information, the fields of name, age, occupation and region are obtained, and the name, age, occupation and region are searched. The corresponding name is Li Si, the corresponding age is 26 years old, the corresponding occupation is teacher, and the corresponding region is Beijing. Then the name is Li Si, the age is 26 years old, the occupation is teacher, and the region is Beijing, and the output is Li Si, the age is 26 years old, the occupation is teacher, and the region is Beijing.

[0055] Based on the above Figure 1 It can be seen from the implementation method that the embodiment of the present invention realizes the purpose of determining the field corresponding to the fuzzy demand by processing the fuzzy demand according to preset rules when the target demand is judged to be a fuzzy demand. When it is judged according to the user demand that the field matching the target demand cannot be found in the data information, that is, when it is judged that the target demand is a fuzzy demand, the fixed field corresponding to the fuzzy demand can be determined by the preset rules. In this way, the field corresponding to the fuzzy demand is determined, and the field corresponding to the fuzzy demand can be found in the data information and output, so that the fuzzy demand in the user demand can be processed, and the user can be guaranteed to use the field corresponding to the fuzzy demand.

[0056] As a refinement and extension of the above embodiment, when the user demand is a fuzzy demand, the fuzzy processing methods are divided into three types according to the number of preset demands similar to the target demand in the historical demand data of all users. The specific operations are: when there is a preset demand similar to the target demand in the historical demand data of all users, multiple preset related fields matched by one preset demand are determined as multiple related fields corresponding to the target demand; when there are multiple preset demands similar to the target demand in the historical demand data of all users, the multiple related fields corresponding to the target demand are determined according to the total number of times each preset demand is proposed; when there are no multiple preset demands similar to the target demand in the historical demand data of all users, the multiple related fields corresponding to the target demand are identified based on the historical demand data of the user. In this way, the fuzzy demands in the user demands can be processed by three different processing methods to determine the multiple related fields corresponding to the fuzzy demands under the three different processing methods, so that the determination of the related fields of the fuzzy demands is more accurate. The above specific operations can be performed by Figure 2 To indicate, Figure 2 The process of the method for processing user needs in the embodiment of the present invention is as follows Figure 2 , see Figure 2 As shown, the method for processing user needs provided by the embodiment of the present invention may include:

[0057] S201. Obtain the user's target needs.

[0058] Step S201 is the same as step S101 and will not be described again here.

[0059] S202: According to the target requirement, it is determined whether a field matching the target requirement can be found in the data information.

[0060] Step S202 is the same as step S102 and will not be described again here.

[0061] It is determined whether a field matching the target requirement can be found in the data information according to the target requirement. If so, step S203 is executed; if not, step S204 is executed.

[0062] S203: Find a target field that matches the target requirement and output the target field.

[0063] Step S203 is the same as step S103, so it will not be described again here.

[0064] When the field matching the target requirement cannot be found in the data information according to step S202, at least one preset requirement similar to the target requirement is found in the historical requirement data of all users. The following steps S204 and S205 are specific operations of finding at least one preset requirement similar to the target requirement in the historical requirement data of all users.

[0065] S204: Determine the degree of overlap between the characters contained in each demand in the historical demand data of all users and the characters contained in the target demand.

[0066] Specifically, when no field matching the target requirement can be found in the data information according to the judgment in step S202, the degree of overlap between the characters contained in each requirement in the historical requirement data of all users and the characters contained in the target requirement is determined.

[0067] All users include the user who proposes the target demand and other users who have proposed any demand before. Each demand in the historical demand data can be any demand proposed by other users and any demand proposed by the user who proposes the target demand. Any demand includes demands that are the same as the target demand and demands that are different from the target demand.

[0068] All characters contained in each demand in the historical demand data of all users are compared with all characters contained in the target demand to determine the degree of overlap between all characters contained in each demand and all characters contained in the target demand.

[0069] Each demand in the historical demand data of all users will correspond to a degree of overlap.

[0070] S205: Determine the historical demands whose overlap degree is within a preset range as preset demands similar to the target demand.

[0071] The overlap degree within a preset range is screened out, and the demand corresponding to the screened overlap degree is determined as a preset demand similar to the target demand.

[0072] The preset range may be 80%-100%, or 60%-100%. There may be multiple preset ranges, which are not limited here.

[0073] Exemplarily, there are three demands in the historical demand data of all users, namely user occupational information, user basic information and user order data, the target demand is user basic information, the degree of overlap between the characters contained in the user occupational information and the characters contained in the user basic information is 66.7%, the degree of overlap between the characters contained in the user basic information and the characters contained in the user basic information is 100%, the degree of overlap between the characters contained in the user order data and the characters contained in the user basic information is 33.3%, and the preset range is 60%-100%. Then the preset demands similar to the target demand are user occupational information and user basic information.

[0074] By comparing the degree of overlap between the characters contained in each demand in the historical demand data of all users and the characters contained in the target demand, one or more demands with a certain degree of overlap can be screened out and determined as preset demands similar to the target demand, so that the determined similar preset demands are more accurate.

[0075] S206: If there is a preset requirement similar to the target requirement, multiple preset related fields matched by the preset requirement are determined as multiple related fields corresponding to the target requirement.

[0076] The historical demand data includes not only user demands but also fields corresponding to the user demands. User demands and fields are stored correspondingly.

[0077] If it is determined in step S205 that there is a preset requirement similar to the target requirement, multiple preset related fields that have been matched with the preset requirement are obtained, and the multiple preset related fields are determined as multiple related fields corresponding to the target requirement.

[0078] If there are multiple preset requirements similar to the target requirement as determined in step S205, multiple related fields corresponding to the target requirement are determined according to the total number of times each requirement is proposed. The following steps S207 and S208 are specific operations of determining multiple related fields corresponding to the target requirement according to the total number of times each requirement is proposed if there are multiple preset requirements similar to the target requirement.

[0079] S207: If there are multiple preset requirements similar to the target requirement, determine the preset requirement with the largest total number of times proposed among the multiple preset requirements.

[0080] If there are multiple preset requirements similar to the target requirement as determined in step S205, it is necessary to screen the multiple preset requirements to select the preset requirement with the largest total number of times proposed.

[0081] Each preset demand is proposed a different total number of times, and it is necessary to determine a preset demand with a maximum total number of times proposed from among multiple preset demands with different total numbers of times proposed.

[0082] For example, there are three preset requirements, namely preset requirement A, preset requirement B and preset requirement C. The total number of times preset requirement A is proposed is 12 times, the total number of times preset requirement B is proposed is 38 times, and the total number of times preset requirement C is proposed is 66 times. It is determined that the preset requirement with the largest total number of proposals is preset requirement C.

[0083] S208: Determine the multiple preset related fields matched by the preset demand with the largest total number as the multiple related fields corresponding to the target demand.

[0084] Specifically, multiple preset related fields that have been matched by the preset requirement with the largest total number of matches determined in step S207 are obtained, and the multiple preset related fields are determined as multiple related fields corresponding to the target requirement.

[0085] Following the example of step S207, the fields matched before the preset requirement C that was proposed the largest number of times are name, region and occupation, and name, region and occupation are determined as multiple related fields corresponding to the target requirement.

[0086] The preset demand with the largest total number of times proposed in the historical demand data can be determined as multiple related fields corresponding to the target demand, so that the fields of the fuzzy demand determined when there are multiple preset demands similar to the target demand in the historical demand data of all users are more accurate.

[0087] If there is no at least one preset requirement similar to the target requirement as determined in step S205, multiple relevant fields corresponding to the target requirement are identified based on the intelligent chat tool. If there is no at least one preset requirement similar to the target requirement, multiple relevant fields corresponding to the target requirement are identified based on the intelligent chat tool, including: inputting the target requirement and the question template into the intelligent chat tool so that the intelligent chat tool feeds back the output result, the question template is used to inquire about the output field corresponding to the target requirement; and the following step S211 determines all the output fields contained in the output result as multiple relevant fields corresponding to the target requirement.

[0088] The following steps S209 and S210 are specific operations of inputting the target demand and the question template into the intelligent chat tool so that the intelligent chat tool feeds back the output result if there is no at least one preset demand similar to the target demand.

[0089] S209: If there is no at least one preset requirement similar to the target requirement, generate a question statement according to the target requirement and the question template.

[0090] If it is determined in step S205 that there is no at least one preset requirement similar to the target requirement, that is, there is no requirement similar to the target requirement in the historical requirement data of all users, a question statement is generated according to the target requirement and the question template.

[0091] The question template is used to inquire about the output field corresponding to the target requirement. The question template can include a predicate and an object, and is a question sentence lacking a subject. For example, the question template is "what content is included".

[0092] The target requirement can be used as the subject of the question sentence, and the question template can be used as the predicate and object of the question sentence. The subject, predicate and object are combined to generate a sentence, that is, the target requirement and the question template are combined to generate a question sentence. The question sentence can also be generated by a sentence generation tool. Specifically, the target requirement and the question template are input into the sentence generation tool, and the sentence generation tool can output a question sentence. For example, the sentence generation tool can be an AI sentence generator.

[0093] For example, the target demand is user order information, the question template may be which fields are included, and a generated question statement is "What fields are included in user order information?".

[0094] S210: Input the question statement into the intelligent chat tool so that the intelligent chat tool feeds back an output result.

[0095] There are many ways to input question statements into the intelligent chat tool. It can be input into the intelligent chat tool in the form of voice or text. The way to input question statements into the intelligent chat tool is not limited here.

[0096] The question statement is input into the intelligent chat tool, and the intelligent chat tool can perform semantic analysis on the question statement and output the question result corresponding to the question statement.

[0097] Continuing with the example of step S209, the question statement is "What fields does the user order information include?" The corresponding output results of "What fields does the user order information include" are the user's basic information, the user's ordered products, the user's transaction amount and the user's order quantity.

[0098] S211. Determine all output fields included in the output result as multiple related fields corresponding to the target requirements.

[0099] Specifically, all output fields included in the output result fed back in step S210 are determined as a plurality of relevant fields corresponding to the target requirement.

[0100] Continuing with the example of step S210, the output result is user basic information, user ordered products, user transaction amount and user order quantity. All output fields included in the output result are user basic information, user ordered products, user transaction amount and user order quantity. User basic information, user ordered products, user transaction amount and user order quantity are determined as multiple related fields corresponding to user order information.

[0101] Input the target demand and a question statement generated by the question template into the intelligent chat tool, so that the output result containing the output field fed back by the intelligent chat tool can be obtained, so that when there are no multiple preset demands similar to the target demand in the historical demand data of all users, multiple relevant fields corresponding to the target demand can also be fed back, that is, fuzzy demands can be processed. In addition, the machine itself does not need to process the fuzzy demands in the target demand to obtain the corresponding fields. It only needs to use the intelligent chat tool to process the fuzzy demands in the target demand to obtain the corresponding fields, so that the machine itself processes less data, does not have the problem of slow processing, and can improve the processing efficiency of fuzzy demands in the target demand.

[0102] S212: Search for multiple related fields in the data information, and output the multiple related fields.

[0103] Step S212 is the same as step S105 and will not be described again here.

[0104] As another embodiment of the present invention, the above embodiment including steps S201 to S212 may be replaced with the step “if there is no at least one preset requirement similar to the target requirement, input the target requirement and the question template into the intelligent chat tool so that the intelligent chat tool can feedback the specific operation of the output result”, that is, step S209 and step S210 may be replaced. The overall solution after replacement can be Figure 3 To indicate, Figure 3 The process of the method for processing user needs in the embodiment of the present invention is as follows Figure 3 , see Figure 3 As shown, the method for processing user needs provided by the embodiment of the present invention may include:

[0105] S301, obtaining the user's target needs.

[0106] Step S301 is the same as step S101 and will not be described again here.

[0107] S302: According to the target requirement, it is determined whether a field matching the target requirement can be found in the data information.

[0108] Step S302 is the same as step S102, so it will not be described again here.

[0109] It is determined whether a field matching the target requirement can be found in the data information according to the target requirement. If so, step S303 is executed; if not, step S304 is executed.

[0110] S303: Find the target field that matches the target requirement and output the target field.

[0111] Step S303 is the same as step S103, so it will not be described again here.

[0112] When the field matching the target requirement cannot be found in the data information according to step S302, at least one preset requirement similar to the target requirement is found in the historical requirement data of all users. The following steps S304 and S305 are specific operations of finding at least one preset requirement similar to the target requirement in the historical requirement data of all users.

[0113] S304: Determine the degree of overlap between the characters contained in each demand in the historical demand data of all users and the characters contained in the target demand.

[0114] Step S304 is the same as step S204, so it will not be described again here.

[0115] S305: Determine the historical demands whose overlap degree is within a preset range as preset demands similar to the target demand.

[0116] Step S305 is the same as step S205, so it will not be described again here.

[0117] S306: If there is a preset requirement similar to the target requirement, multiple preset related fields matched by the preset requirement are determined as multiple related fields corresponding to the target requirement.

[0118] Step S306 is the same as step S206 and will not be described again.

[0119] If there are multiple preset requirements similar to the target requirement as determined in step S305, multiple related fields corresponding to the target requirement are determined according to the total number of times each requirement is proposed. The following steps S307 and S308 are specific operations of determining multiple related fields corresponding to the target requirement according to the total number of times each requirement is proposed if there are multiple preset requirements similar to the target requirement.

[0120] S307: If there are multiple preset requirements similar to the target requirement, determine the preset requirement with the largest total number of times proposed among the multiple preset requirements.

[0121] Step S307 is the same as step S207, so it will not be repeated here.

[0122] S308: Determine the multiple preset related fields matched by the preset requirement with the largest total number as the multiple related fields corresponding to the target requirement.

[0123] Step S308 is the same as step S208, so it will not be repeated here.

[0124] If there is no at least one preset requirement similar to the target requirement as determined in step S305, multiple relevant fields corresponding to the target requirement are identified based on the intelligent chat tool. If there is no at least one preset requirement similar to the target requirement, multiple relevant fields corresponding to the target requirement are identified based on the intelligent chat tool, including: inputting the target requirement and the question template into the intelligent chat tool so that the intelligent chat tool feeds back the output result, the question template is used to inquire about the output field corresponding to the target requirement; and the following step S313 determines all the output fields contained in the output result as multiple relevant fields corresponding to the target requirement.

[0125] The following steps S309 and S310 are specific operations of inputting the target demand and the question template into the intelligent chat tool so that the intelligent chat tool feeds back the output result if there is no at least one preset demand similar to the target demand.

[0126] S309: If there is no at least one preset requirement similar to the target requirement, the target requirement is split into multiple first target requirements according to the type of phrases in the target requirement.

[0127] If step S305 determines that there is no at least one preset demand similar to the target demand, that is, there is no demand similar to the target demand in the historical demand data of all users, the target demand is split into multiple first target demands according to the type of phrases in the target demand.

[0128] There are multiple phrases in the target demand, and a phrase refers to a compound word. The target demand is divided into multiple first target demands according to different compound words. Each first target demand contains only one phrase, that is, a compound word.

[0129] For example, the target demand is who is Zhang San, which can be split into two demands, including demand 1 and demand 2. Requirement 1 is about Zhang San and demand 2 is about who is Zhang San. The target demand is user information, which can be split into two demands, including demand 3 and demand 4. Requirement 3 is about the user and demand 4 is about the information.

[0130] S310. Generate multiple question statements using multiple first target requirements and question templates respectively, and input the multiple question statements into the intelligent chat tool so that the intelligent chat tool feeds back multiple preset output results corresponding to the multiple question statements.

[0131] The question template is used to inquire about the output field corresponding to the target requirement. The question template can include a predicate and an object, and is a question sentence lacking a subject. For example, the question template is "what content is included".

[0132] Multiple first target requirements can be used as the subject of the question statement, and the question template can be used as the predicate and object of the question statement. Each subject can be combined with the predicate and object to generate multiple sentences, that is, multiple first target requirements can be combined with the question template to generate multiple question statements. Question statements can also be generated through a sentence generation tool. Specifically, each first target requirement and question template are input into the sentence generation tool, and the sentence generation tool can output a question statement corresponding to each first target requirement. For example, the sentence generation tool can be an AI sentence generator.

[0133] The number of question statements is the same as the number of the first target requirement. There are multiple ways to input question statements into the intelligent chat tool. They can be input into the intelligent chat tool in the form of voice or text. There is no limitation on the way of inputting question statements into the intelligent chat tool.

[0134] Input multiple question statements into the intelligent chat tool. The intelligent chat tool can perform semantic analysis on each question statement, and can output question results corresponding to the multiple question statements. Each question statement corresponds to a question result, and the number of question results is the same as the number of question statements.

[0135] Continuing with the example of step S309, the question template is what contents are included, and two question statements are generated, namely what contents does 'user' include, and what contents does 'information' include. The preset output result corresponding to "what contents does 'user' include" is result 1, and result 1 includes the login account, name and nickname. The preset output result corresponding to "what contents does 'information' include" is result 2, and result 2 includes name, age, occupation and region.

[0136] S311. Obtain all preset output fields included in multiple preset output results, and remove duplicates from all preset output fields.

[0137] Each preset output result includes output fields. Duplicate output fields may appear in different preset output results. In order to avoid duplicate output fields in the output results and to avoid subsequent repeated searches for duplicate output fields, it is necessary to obtain all preset output fields included in all preset output results, deduplicate all preset output fields, and obtain preset output fields without duplication.

[0138] Continuing with the example of step S310, all the preset output fields obtained are login account, name, nickname, name, age, occupation and region. After deduplication of these preset output fields, the preset output fields obtained are login account, name, nickname, age, occupation and region.

[0139] S312: Determine the result including the preset output field after deduplication as the output result.

[0140] Determining the result including the preset output field after deduplication as the output result can avoid duplicate output fields in the output result and ensure the uniqueness of the preset output field in the output result.

[0141] Continuing with the example of step S311, the deduplicated result 1 includes the login account, name and nickname, and the deduplicated result 2 includes age, occupation and region. The deduplicated result 1 including the login account, name and nickname, and the deduplicated result 2 including age, occupation and region are determined as the output results.

[0142] S313: Determine all output fields included in the output result as multiple related fields corresponding to the target requirements.

[0143] Step S313 is the same as step S211, so it will not be repeated here.

[0144] The target demand can be split into multiple first target demands according to different phrases, and a question statement can be generated according to each first target demand and the question template. Multiple question statements can be generated and input into the intelligent chat tool. Multiple preset output results corresponding to the multiple question statements can be fed back. The multiple preset output results fed back are richer than the output results before splitting. The fields in these output results are deduplicated, and the result composed of the deduplicated output fields is used as the final output result. In this way, when there are no multiple preset demands similar to the target demand in the historical demand data of all users, the output results containing the fields can also be fed back, and the output results determined by the richer multiple preset output results are richer.

[0145] S314. Search for multiple related fields in the data information, and output the multiple related fields.

[0146] Step S314 is the same as step S105 and will not be described again here.

[0147] Based on the same inventive concept, as an implementation of the above-mentioned method for processing user demands, an embodiment of the present invention further provides a device for processing user demands. Figure 4 The structure of the device in the embodiment of the present invention is Figure 1 , see Figure 4 As shown, the device may include:

[0148] The acquisition module 401 is used to acquire the target demand of the user;

[0149] The judging module 402 is used to judge whether a field matching the target requirement can be found in the data information according to the target requirement obtained by the obtaining module 401;

[0150] A first search module 403 is used to search for a target field matching the target requirement and output the target field if the judgment module 402 judges that a field matching the target requirement can be found in the data information;

[0151] The processing module 404 is used to process the target requirement according to a preset rule to obtain a plurality of related fields corresponding to the target requirement if the judging module 402 judges that no field matching the target requirement can be found in the data information;

[0152] The second search module 405 is used to search the data information for the multiple related fields obtained by the processing module 404 and output the multiple related fields.

[0153] exist Figure 4 Based on the present invention, another embodiment of the device is provided, see Figure 5 As shown, Figure 5 The structure of the device in the embodiment of the present invention is Figure 2 , the device may include:

[0154] The processing module 404 includes:

[0155] A searching unit 4041 is used to search for at least one preset demand similar to the target demand in the historical demand data of all users;

[0156] A first determining unit 4042 is configured to determine, if a preset requirement similar to the target requirement is found by the searching unit 4041, a plurality of preset related fields matched by the preset requirement as the plurality of related fields corresponding to the target requirement;

[0157] A second determining unit 4043 is configured to determine a plurality of related fields corresponding to the target requirement according to the total number of times each requirement is proposed if there are multiple preset requirements similar to the target requirement found by the searching unit 4041;

[0158] The identification unit 4044 is used to identify multiple related fields corresponding to the target demand based on the intelligent chat tool if there is no at least one preset demand similar to the target demand found by the search unit 4041.

[0159] Furthermore, the search unit 4041 includes:

[0160] The first determining subunit 40411 is used to determine the degree of overlap between the characters contained in each requirement in the historical requirement data of all users and the characters contained in the target requirement if there is no at least one preset requirement similar to the target requirement found by the searching unit 4041;

[0161] The second determining subunit 40412 is used to determine the historical demands whose overlap degree is within a preset range determined by the first determining subunit 40411 as preset demands similar to the target demand.

[0162] Further, the second determining unit 4043 includes:

[0163] The third determining subunit 40431 is used to determine the preset requirement that has been proposed the largest total number of times among the multiple preset requirements;

[0164] The fourth determining subunit 40432 is used to determine the multiple preset related fields matched by the preset demand with the largest total number of times determined by the third determining subunit 40431 as the multiple related fields corresponding to the target demand.

[0165] Further, the identification unit 4044 includes:

[0166] An input subunit 40441 is used to input the target requirement and the question template into the intelligent chat tool so that the intelligent chat tool can feed back an output result, wherein the question template is used to inquire about the output field corresponding to the target requirement;

[0167] The fifth determining subunit 40442 is used to determine all output fields included in the output result fed back by the input subunit 40441 as multiple related fields corresponding to the target demand.

[0168] Furthermore, the input subunit 40441 is specifically used to generate a question statement according to the target demand and the question template; and input the question statement into the intelligent chat tool so that the intelligent chat tool feeds back an output result.

[0169] Furthermore, the input subunit 40441 is specifically used to split the target demand into multiple first target demands according to the type of phrases in the target demand; generate multiple question statements using the multiple first target demands and the question template respectively, and input the multiple question statements into the intelligent chat tool so that the intelligent chat tool feeds back multiple preset output results corresponding to the multiple question statements; obtains all preset output fields contained in the multiple preset output results, and deduplicates all the preset output fields; and determines the result containing the deduplicated preset output fields as the output result.

[0170] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device. Figure 6 is a structural diagram of an electronic device in an embodiment of the present invention, see Figure 6 As shown, the electronic device 60 may include: at least one processor 601; and at least one memory 602 and a bus 603 connected to the processor 601; wherein the processor 601 and the memory 602 communicate with each other via the bus 603; the processor 601 is used to call the program instructions in the memory 602 to execute the method for processing user needs in one or more of the above-mentioned embodiments.

[0171] It should be noted here that the description of the above embodiment of the processing device for user needs is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the embodiment of the processing device for user needs of the embodiment of the present invention, please refer to the description of the method embodiment of the present invention for understanding.

[0172] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the method in one or more of the above embodiments.

[0173] It should be noted here that the description of the above computer-readable storage medium embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the embodiment of the computer-readable storage medium of the embodiment of the present invention, please refer to the description of the method embodiment of the present invention for understanding.

[0174] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for processing user needs, characterized in that: The method comprises: Obtain the user's target needs; According to the target requirement, determining whether a field matching the target requirement can be found in the data information; If yes, then search for a target field that matches the target requirement and output the target field; If not, the target requirement is processed according to a preset rule to obtain a plurality of related fields corresponding to the target requirement; The multiple related fields are searched in the data information, and the multiple related fields are output.

2. The method according to claim 1, characterized in that The target requirement is processed according to a preset rule to obtain a plurality of related fields corresponding to the target requirement, including: Find at least one preset demand similar to the target demand in the historical demand data of all users; If there is a preset requirement similar to the target requirement, multiple preset related fields matched by the preset requirement are determined as multiple related fields corresponding to the target requirement; If there are multiple preset requirements similar to the target requirement, determine multiple related fields corresponding to the target requirement according to the total number of times each requirement is proposed; If there is no at least one preset requirement similar to the target requirement, multiple related fields corresponding to the target requirement are identified based on the intelligent chat tool.

3. The method according to claim 2, characterized in that The step of searching for at least one preset requirement similar to the target requirement in the historical requirement data of all users includes: Determine the degree of overlap between the characters contained in each demand in the historical demand data of all users and the characters contained in the target demand; The historical demands whose overlap degree is within a preset range are determined as preset demands similar to the target demand.

4. The method according to claim 2, characterized in that: If there are multiple preset requirements similar to the target requirement, multiple related fields corresponding to the target requirement are determined according to the total number of times each requirement is proposed, including: Determining, among the plurality of preset requirements, a preset requirement that has been proposed the greatest number of times; The multiple preset related fields matched by the preset requirements with the largest total number of matches are determined as the multiple related fields corresponding to the target requirements.

5. The method according to claim 2, characterized in that: If there is no at least one preset requirement similar to the target requirement, identifying multiple related fields corresponding to the target requirement based on the intelligent chat tool includes: Inputting the target requirement and the question template into the intelligent chat tool so that the intelligent chat tool feeds back the output result, wherein the question template is used to inquire about the output field corresponding to the target requirement; All output fields included in the output result are determined as multiple related fields corresponding to the target demand.

6. The method according to claim 5, characterized in that The step of inputting the target requirement and the question template into the intelligent chat tool so that the intelligent chat tool feeds back an output result includes: Generate a question statement according to the target requirement and the question template; The question statement is input into the intelligent chat tool so that the intelligent chat tool feeds back an output result.

7. The method according to claim 5, characterized in that The step of inputting the target requirement and the question template into the intelligent chat tool so that the intelligent chat tool feeds back an output result includes: According to the type of the phrase in the target demand, the target demand is divided into a plurality of first target demands; Generate a plurality of question statements by respectively combining the plurality of first target requirements with the question template, and input the plurality of question statements into the intelligent chat tool, so that the intelligent chat tool feeds back a plurality of preset output results corresponding to the plurality of question statements; Acquire all preset output fields included in the plurality of preset output results, and remove duplicates from all the preset output fields; The result including the preset output fields after deduplication is determined as the output result.

8. A user demand processing device, characterized in that: The device comprises: Acquisition module, used to obtain the user's target needs; A judgment module, used to judge whether a field matching the target requirement can be found in the data information according to the target requirement; A first search module, configured to search for a target field that matches the target requirement and output the target field; A processing module, for processing the target requirement according to a preset rule to obtain a plurality of related fields corresponding to the target requirement if no; The second search module is used to search for the multiple related fields in the data information and output the multiple related fields.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and at least one memory and bus connected to the processor; The processor and the memory communicate with each other via the bus; the processor is used to call program instructions in the memory to execute the method for processing user needs as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the method for processing user needs according to any one of claims 1 to 7.

Images