Information input method and device, computer device, storage medium and program product

Abstract

The application relates to an information input method and device, computer equipment, a storage medium and a program product. The application relates to the field of big data. The method comprises the following steps: obtaining customer voice information required by a target service, and identifying the customer voice information to obtain a sentence recognition result; obtaining a question and answer matching text according to the sentence recognition result and a question and answer library for a resource loan system which is constructed in advance; determining target question and answer information corresponding to the target service according to the question and answer matching text and an input domain matching library for the resource loan system which is constructed in advance; and sending the target question and answer information to a target terminal; and the target question and answer information is used for displaying the target question and answer information on the target terminal. The method can improve the service efficiency of input information.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of big data, and in particular, to an information input method and device, a computer device, a storage medium, and a program product. BACKGROUND

[0002] In a bank business process, a business personnel needs to collect, verify, and register information of a white-listed customer offline. Currently, the business personnel carries paper materials to the customer's location to collect information and fill in the paper materials, and then inputs the information into a resource loan system one by one, or the business personnel carries a portable device to the customer's location to collect information, and the business personnel manually inputs the collected information online.

[0003] However, due to unclear handwriting on the paper materials, inputting the information into the resource loan system one by one, limited portable devices, and slow typing of the business personnel, the business efficiency of inputting the information is low. SUMMARY

[0004] Therefore, it is necessary to provide an information input method and device, a computer device, a storage medium, and a program product capable of improving the business efficiency of inputting information.

[0005] In a first aspect, the present application provides an information input method. The method comprises:

[0006] obtaining customer voice information required by a target business, and identifying the customer voice information to obtain a sentence recognition result;

[0007] obtaining a question and answer pairing text according to the sentence recognition result and a question and answer library pre-constructed for a resource loan system;

[0008] determining target question and answer information corresponding to the target business according to the question and answer pairing text and an input domain matching library pre-constructed for the resource loan system;

[0009] sending the target question and answer information to a target terminal; the target question and answer information is used to display the target question and answer information on the target terminal.

[0010] In one embodiment, the obtaining of the question and answer pairing text according to the sentence recognition result and the question and answer library pre-constructed for the resource loan system comprises:

[0011] performing word segmentation on each first sentence in the sentence recognition result to obtain a first word segmentation result;

[0012] for each first word segmentation result, determining a similarity between the first word segmentation result and each target object in the question and answer library according to the question and answer library and the first word segmentation result;

[0013] According to the first segmentation result and the similarity between the first segmentation result and each target object in the question and answer library, the question and answer matching text is obtained.

[0014] In one of the embodiments, the target object includes a second sentence and keywords; and the similarity between the first segmentation result and each target object in the question and answer library is determined according to the question and answer library and the first segmentation result, including:

[0015] For each second sentence, the first number of occurrences of each segmentation in the first segmentation result in the second sentence is determined;

[0016] The second number of occurrences of each segmentation in the first segmentation result in the keywords is determined;

[0017] The similarity between the first segmentation result and each target object in the question and answer library is determined according to the first number and the second number.

[0018] In one of the embodiments, the similarity between the first segmentation result and each target object in the question and answer library is determined according to the first number and the second number, including:

[0019] The first product result of the first number and a first preset similarity value is determined;

[0020] The second product result of the second number and a second preset similarity value is determined;

[0021] The similarity between the first segmentation result and each target object in the question and answer library is determined according to the sum of the first product result and the second product result.

[0022] In one of the embodiments, the question and answer matching text is obtained according to the similarity between the first segmentation result and each target object in the question and answer library, including:

[0023] The maximum similarity is determined according to the similarity between the first segmentation result and each target object in the question and answer library;

[0024] The question and answer label of the first segmentation result is determined according to the question and answer type to which the sentence corresponding to the maximum similarity belongs;

[0025] The question and answer matching text is obtained according to the order of the first sentences and the question and answer label of the first segmentation result.

[0026] In one of the embodiments, the number of question and answer matching texts is multiple; and the target question and answer information corresponding to the target business is determined according to the question and answer matching text and the input domain matching library for the resource loan system constructed in advance, including:

[0027] The question and answer matching text with the same input domain as the input domain in the input domain matching library is taken as the target question and answer matching text.

[0028] According to the target question-answer pairing text, target question-answer information corresponding to the target service is determined.

[0029] In one embodiment, the target question-answer information corresponding to the target service is determined according to the target question-answer pairing text, including:

[0030] According to the input domain corresponding to the target question-answer pairing text and a preset input domain set, a target input domain is determined; the target input domain is an input domain provided with a corresponding check dictionary;

[0031] According to the preset check dictionary corresponding to the target input domain and the target question-answer pairing text corresponding to the target input domain, target question-answer information corresponding to the target service is determined.

[0032] In one embodiment, the target question-answer information corresponding to the target service is determined according to the preset check dictionary corresponding to the target input domain and the target question-answer pairing text corresponding to the target input domain, including:

[0033] The target question-answer pairing text corresponding to the target input domain is checked by using the preset check dictionary, and checked target question-answer pairing text is obtained;

[0034] According to the input domain in the input domain matching library and the checked target question-answer pairing text, target question-answer information corresponding to the target service is determined.

[0035] In one embodiment, the target question-answer information corresponding to the target service is determined according to the input domain in the input domain matching library and the checked target question-answer pairing text, including:

[0036] The intersection between the input domain in the input domain matching library and the checked target question-answer pairing text is taken as the target question-answer information corresponding to the target service.

[0037] In a second aspect, the application further provides an information input device. The device includes:

[0038] An acquisition module is configured to acquire customer voice information required by a target service, and identify the customer voice information to obtain a sentence recognition result;

[0039] An obtaining module is configured to obtain question-answer pairing text according to the sentence recognition result and a question-answer library for a resource loan system constructed in advance;

[0040] A determination module is configured to determine target question-answer information corresponding to the target service according to the question-answer pairing text and an input domain matching library for the resource loan system constructed in advance;

[0041] The sending module is configured to send the target question and answer information to a target terminal, and the target question and answer information is configured to be displayed on the target terminal.

[0042] In a third aspect, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. The processor implements the steps of any of the above methods when executing the computer program.

[0043] In a fourth aspect, a computer readable storage medium is provided. The computer readable storage medium stores a computer program. The computer program, when executed by a processor, implements the steps of any of the above methods.

[0044] In a fifth aspect, a computer program product is provided. The computer program product includes a computer program. The computer program, when executed by a processor, implements the steps of any of the above methods.

[0045] The above information input method, device, computer device, storage medium and program product, obtain the customer voice information required by the target service, identify the customer voice information to obtain a sentence recognition result, and then obtain a question and answer pairing text according to the sentence recognition result and a question and answer library for the resource loan system constructed in advance. The target question and answer information corresponding to the target service is determined according to the question and answer pairing text and an input domain matching library for the resource loan system constructed in advance. The target question and answer information for the target terminal to display is sent to the target terminal. Since the question and answer pairing text is obtained according to the sentence recognition result and the question and answer library for the resource loan system constructed in advance, and the target question and answer information corresponding to the target service is determined according to the question and answer pairing text and the input domain matching library for the resource loan system constructed in advance, it is verified that the information input into the resource loan system is the target question and answer information corresponding to the target service, and the target question and answer information for the target terminal to display is sent to the target terminal. Therefore, the target question and answer information is automatically input into the resource loan system, and the business efficiency of input information is improved. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 An application environment diagram of the information input method in an embodiment;

[0047] Figure 2 A flowchart of the information input method in an embodiment;

[0048] Figure 3 A flowchart of the question and answer pairing text obtaining method in an embodiment;

[0049] Figure 4 A flowchart of the similarity determining method in an embodiment;

[0050] Figure 5 Flowchart of a similarity determination method in another embodiment;

[0051] Figure 6 Flowchart of a question-answer pairing text obtaining method in an embodiment;

[0052] Figure 7 Flowchart of a target question-answer information determination method in an embodiment;

[0053] Figure 8 Structural block diagram of an information input device in an embodiment;

[0054] Figure 9 Internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0055] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0056] In the conventional technology, a business staff usually carries paper materials to the location of a client, collects information required for a target business, and fills in the paper materials, and then returns to the business handling location to input the information into a resource loan system one by one. Alternatively, the business staff carries a portable device to the location of the client to collect information, and the business staff manually inputs the collected information online.

[0057] However, due to unclear handwriting on the paper materials, re-filling of the paper materials due to errors, inputting the information into the resource loan system one by one, limited portable devices, slow typing of the business staff, network lag, and abnormal resource loan system, etc., the business efficiency of inputting the information is low.

[0058] To solve the above technical problems, the information input method provided by the embodiments of the present application can be applied to an application environment as shown in Figure 1 The terminal 102 communicates with the server 104 through a network. The data storage system can store data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on a cloud or other network server. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0059] In an embodiment, as shown in Figure 2As shown, an information entry method is provided, and the method is applied to Figure 1 The computer device in the method is taken as an example for illustration, and the method comprises the following steps:

[0060] S201, obtaining customer voice information required by a target service, and identifying the customer voice information to obtain a sentence recognition result.

[0061] In this embodiment, the customer voice information required by the target service is obtained by a voice collection device, wherein the voice collection device can be a mobile phone, a recorder or a voice recorder.

[0062] Optionally, before the customer voice information is identified, the customer voice information is subjected to noise removal processing, and then the voice recognition technology is used to identify the customer voice information to obtain the sentence recognition result. The voice recognition technology can be, for example, the ASRT voice recognition technology.

[0063] S202, obtaining question and answer pairing text according to the sentence recognition result and a question and answer library for the resource borrowing system which is constructed in advance.

[0064] The question and answer library comprises question type content, answer type content and keywords, the question type content is for example "where is the main office of your company", the answer type content is for example "the main office of the company is in A, but there is also an office in B", and the keywords are for example "please ask, where and how many", etc. The question and answer library is constructed according to expert experience.

[0065] S203, determining target question and answer information corresponding to the target service according to the question and answer pairing text and an input domain matching library for the resource borrowing system which is constructed in advance.

[0066] In this embodiment, the input domain matching library is constructed according to keywords required by an input interface in the resource borrowing system, and the keywords stored in the input domain matching library are for example company address, ID card, legal representative and registered capital, etc.

[0067] It should be noted that each keyword stored in the input domain matching library corresponds to an input domain of the input interface in the resource borrowing system one by one, for example, a keyword in the input domain matching library is company address, and the corresponding input domain in the input interface in the resource borrowing system is also company address.

[0068] S204, sending the target question and answer information to a target terminal; the target question and answer information is used for displaying the target question and answer information by the target terminal.

[0069] The target question and answer information is sent to the target terminal, so that the resource borrowing system arranged on the target terminal is associated with the target question and answer information, and the target question and answer information is automatically entered into the input interface in the resource borrowing system.

[0070] In the information input method, the client voice information required by the target service is obtained, the sentence recognition result is recognized from the client voice information, the question and answer matching text is obtained according to the sentence recognition result and the question and answer library for the resource loan system constructed in advance, the target question and answer information corresponding to the target service is determined according to the question and answer matching text and the input domain matching library for the resource loan system constructed in advance, and the target question and answer information for the target terminal to display is sent to the target terminal. Since the question and answer matching text is obtained according to the sentence recognition result and the question and answer library for the resource loan system constructed in advance, and the target question and answer information corresponding to the target service is determined according to the question and answer matching text and the input domain matching library for the resource loan system constructed in advance, it is verified that the information input into the resource loan system is the target question and answer information corresponding to the target service, and the target question and answer information for the target terminal to display is sent to the target terminal, so that the target question and answer information is automatically input into the resource loan system, and the business efficiency of input information is improved.

[0071] Referring to Figure 3 , Figure 3 FIG. 1 is a flowchart of a method for obtaining question and answer matching text according to an embodiment. The embodiment relates to an optional implementation manner for obtaining question and answer matching text according to a sentence recognition result and a question and answer library for a resource loan system constructed in advance. On the basis of the above embodiment, S202 specifically includes the following steps:

[0072] S301, performing word segmentation processing on each first sentence in the sentence recognition result to obtain a first word segmentation result.

[0073] In the embodiment, the first word segmentation result is obtained by performing word segmentation processing on the first sentence by using an open source word segmentation tool. For example, the first sentence A is segmented into 10 words A1, A2,..., and A10 by using a Chinese language processing package HanLP.

[0074] S302, for each first word segmentation result, determining the similarity between the first word segmentation result and each target object in the question and answer library according to the question and answer library and the first word segmentation result.

[0075] In the embodiment, the similarity can be determined by the number of times that the first word segmentation result appears in each target object in the question and answer library, or can be determined by the similarity value corresponding to the appearance of the first word segmentation result in each target object in the question and answer library.

[0076] S303, for each first word segmentation result, obtaining the question and answer matching text according to the similarity between the first word segmentation result and each target object in the question and answer library.

[0077] The question-answer matched text refers to question type content and answer type content matched with the question type content. For example, "Where is the main office of your company?" is matched with "The main office address of the company is XX."

[0078] The method provided in this embodiment obtains first segmentation results by performing segmentation processing on each first sentence in the sentence recognition result, and determines the similarity of the first segmentation results and each target object in the question-answer library according to the question-answer library and the first segmentation results, and then obtains the question-answer matched text according to the similarity of the first segmentation results and each target object in the question-answer library. That is, this embodiment determines the similarity of the first segmentation results and each target object in the question-answer library according to the question-answer library and the first segmentation results, and then determines the question-answer matched text according to the similarity and the first segmentation results, so as to determine the target question-answer information according to the question-answer matched text, and verify the information entered into the resource loan system as the target question-answer information.

[0079] Reference Figure 4 , Figure 4 FIG. 1 is a flowchart of a similarity determination method in an embodiment. The embodiment relates to an optional implementation manner of how to determine the similarity of the first segmentation results and each target object in the question-answer library according to the question-answer library and the first segmentation results. On the basis of the above embodiment, S302 specifically includes the following steps.

[0080] S401, for each second sentence, determining a first number of occurrences of each segmentation in the first segmentation results in the second sentence.

[0081] For example, the first segmentation results corresponding to the first sentence A include A1, A2,..., and A10, the question-answer library includes B1, B2,..., and Bn second sentences and C1, C2,..., and Cn keywords, A1, A2,..., and A10 are taken out in a loop to determine whether they occur in B1, and then the first number a1 of occurrences of A1, A2,..., and A10 in B1 is determined. In this way, the first numbers b1,..., and n1 of occurrences of A1, A2,..., and A10 in B2,..., and Bn are determined.

[0082] S402, determining a second number of occurrences of each segmentation in the first segmentation results in each keyword.

[0083] In combination with the above example, it is determined whether A1, A2,..., and A10 occur in C1, and then the second number a2 of occurrences of A1, A2,..., and A10 in C1 is determined. In this way, the second numbers b2,..., and n2 of occurrences of A1, A2, and A3 in C2,..., and Cn are determined.

[0084] S403, determine the similarity between the first segmentation result and the target object in the question and answer library according to the first number and the second number.

[0085] In the embodiment, the total number of occurrences of the target object can be determined according to the first number, the weight corresponding to the first number, the second number and the weight corresponding to the second number, and then the similarity between the first segmentation result and the target object is determined. The sum of the first number and the second number can also be used as the total number of occurrences of the target object, and then the similarity between the first segmentation result and the target object is determined according to the relationship between the total number and the preset number.

[0086] The method provided in the embodiment determines the first number of occurrences of each segmentation in the second sentence in the first segmentation result, and determines the second number of occurrences of each segmentation in the first segmentation result in each keyword, and then determines the similarity between the first segmentation result and the target object in the question and answer library according to the first number and the second number. That is, the similarity between the first segmentation result and the target object in the question and answer library is determined according to the first number and the second number in the embodiment, so that the question and answer label corresponding to the first segmentation result can be determined.

[0087] Reference Figure 5 , Figure 5 For another flowchart of the similarity determination method, the embodiment relates to an optional implementation manner of how to determine the similarity between the first segmentation result and the target object in the question and answer library according to the first number and the second number. On the basis of the above embodiment, S403 specifically includes the following steps:

[0088] S501, determine the first product result of the first number and the first preset similarity value.

[0089] In combination with the above example, if only A1, A4, A5 and A8 in A1, A2... A10 appear in the B1 second sentence, the first number is 4, for example, the first preset similarity value is 0.2, and the first product result is 0.8.

[0090] S502, determine the second product result of the second number and the second preset similarity value.

[0091] In combination with the above example, if only A7 in A1, A2... A10 appears in the keyword C1, the second number is 1, for example, the second preset similarity value is 0.6, and the second product result is 0.6.

[0092] S503, determine the similarity between the first segmentation result and the target object in the question and answer library according to the sum of the first product result and the second product result.

[0093] With the above examples, the similarity of the first segmentation result and the B1 second statement in the question and answer library is 0.8+0.6=1.4, and according to the steps of S501 to S503, the similarity of the first segmentation result and the B2...Bn second statement is determined.

[0094] The method provided in the present example is simple and convenient in operation, and has strong operability, by determining a first product result of the first number and the first preset similarity value, determining a second product result of the second number and the second preset similarity value, and then determining the similarity of the first segmentation result and the target object in the question and answer library according to the sum of the first product result and the second product result.

[0095] Reference Figure 6 , Figure 6 The present embodiment relates to a kind of optional implementation of how to obtain question and answer pairing text according to the similarity of first segmentation result and each target object in question and answer library.The flowchart of the method of question and answer pairing text in one embodiment is obtained, and the above-mentioned S303 specifically includes the following steps:

[0096] S601, according to the similarity of first segmentation result and each target object in question and answer library, determine the maximum similarity.

[0097] With the above examples, the similarity of the first segmentation result and the B1 second statement in the question and answer library is 0.8+0.6=1.4, and according to the steps of S501 to S503, the similarity of the first segmentation result and the B2...Bn second statement is determined.

[0098] S602, according to the question and answer type of the statement corresponding to the maximum similarity, determine the question and answer label of first segmentation result.

[0099] With the above examples, if the statement corresponding to B8 second statement belongs to question type content, the question and answer label of first segmentation result is question label, if the statement corresponding to B8 second statement belongs to answer type content, the question and answer label of first segmentation result is answer label.

[0100] S603, according to the order of each first statement and the question and answer label of each first segmentation result, obtain question and answer pairing text.

[0101] For example, the 8 first segmentation results arranged in the order of the first sentences are A, B, C, D, E, F, G and H, and the question and answer labels corresponding to A, B, C, D, E, F, G and H are question, answer, question, question, answer, question, answer and answer respectively, A and B form one question and answer pair text, C, D and E form one question and answer pair text, and F, G and H form one question and answer pair text.

[0102] The method provided in the embodiment determines the maximum similarity according to the similarity between the first segmentation result and each target object in the question and answer library, and further determines the question and answer label of the first segmentation result according to the question and answer type to which the sentence corresponding to the maximum similarity belongs, so as to obtain the question and answer pair text according to the order of each first sentence and the question and answer label of each first segmentation result, thereby enabling the matching of multiple first segmentation results, so that the first segmentation result with a question label corresponds to the first segmentation result with an answer label to obtain the question and answer pair text.

[0103] Optionally, before determining the target question and answer information corresponding to the target business, the method further includes: performing segmentation processing on the question and answer pair text to obtain a segmented question and answer pair text. The segmented question and answer pair text is obtained by performing segmentation processing on the question and answer pair text by using an open source segmentation tool, for example, the segmented question and answer pair text corresponding to the company address includes one question and answer pair text formed by the main office and geographic location A and one question and answer pair text formed by other offices and geographic location B.

[0104] Optionally, before determining the target question and answer information corresponding to the target business, the method further includes: performing error correction processing on the segmented question and answer pair text by using an N-gram model to correct confusing characters by using a text matching library. The text matching library is established according to the stock data assets in the resource loan database and the resource loan field library.

[0105] On the basis of the above-mentioned embodiments, the target question and answer information corresponding to the target business is determined according to the question and answer pair text and the input domain matching library for the resource loan system constructed in advance, which can be achieved in the following manner:

[0106] The question and answer pair text with the same input domain as the input domain in the input domain matching library is taken as the target question and answer pair text; and the target question and answer information corresponding to the target business is determined according to the target question and answer pair text.

[0107] In this embodiment, the segmented words corresponding to the question type statements in the question and answer pair text are compared with each keyword in the input domain matching library one by one, the question and answer pair text corresponding to the segmented words same as the input domain in the input domain matching library is taken as the target question and answer pair text, and then the target question and answer information corresponding to the target business is determined according to the target question and answer pair text. For example, there is a question and answer pair text composed of A and B, a question and answer pair text composed of C, D and E, and a question and answer pair text composed of F, G and H. If the question and answer pair text corresponding to the company address is to be obtained, the segmented words corresponding to the question type statements A, C, D and F are compared with the keywords of the company address in the input domain matching library one by one, the question and answer pair text composed of D and E corresponding to the segmented words same as the input domain in the input domain matching library is taken as the target question and answer pair text, and then the target question and answer information is determined according to the target question and answer pair text composed of D and E.

[0108] Optionally, the input domain corresponding to the target question and answer information is determined according to the input domain corresponding to the target question and answer pair text and a preset input domain set, and then the target question and answer information is determined according to the input domain corresponding to the target question and answer information. The preset input domain set includes an input domain without verification and an input domain requiring verification.

[0109] It should be noted that the input domain without verification and the input domain requiring verification are set based on the target question and answer pair text. If the input domain corresponding to the target question and answer pair text is a text selection box, the input domain corresponding to the target question and answer information is the input domain requiring verification, and if the input domain corresponding to the target question and answer pair text is a text input box, the input domain corresponding to the target question and answer information is the input domain without verification.

[0110] For example, if the answer type content in the target question and answer pair text is an ID card, the input domain corresponding to the target question and answer information is determined to be the ID card input domain from the preset input domain set composed of the company address input domain, the ID card input domain and the legal representative input domain. The ID card input domain is a text input box, so the ID card input domain is an input domain without verification, and then the target question and answer information is determined according to the ID card input domain.

[0111] For another example, if the answer type content in the target question and answer pair text is the C company address ab, the input domain corresponding to the target question and answer information is determined to be the company address input domain from the preset input domain set composed of the company address input domain, the ID card input domain and the legal representative input domain. The company address input domain is a text selection box, so the company address input domain is an input domain requiring verification, and then the target question and answer information is determined according to the company address input domain.

[0112] The method provided in the embodiment pairs the text of the same question and answer in the input domain in the library with the text of the target question and answer, determines the target question and answer information corresponding to the target business according to the text of the target question and answer, so that the question and answer text required by the input interface in the resource loaning system can be screened out from the plurality of question and answer texts, the accuracy of the input information is improved, and the non-target question and answer information is avoided from being input into the resource loaning system.

[0113] With reference to Figure 7 , Figure 7 FIG. 1 is a flowchart of a method for determining target question and answer information in an embodiment. The embodiment relates to an optional implementation manner for determining the target question and answer information corresponding to the target business according to the target question and answer text. The embodiment is based on the above-mentioned embodiment and specifically includes the following steps.

[0114] In S701, the target input domain is determined according to the input domain corresponding to the target question and answer text and the preset input domain set. The target input domain is an input domain provided with a corresponding check dictionary.

[0115] In the embodiment, the target input domain provided with the corresponding check dictionary is determined according to the input domain corresponding to the target question and answer text and the preset input domain set. For example, if the answer type content in the target question and answer text is the address ab of company C, the target input domain is determined as the company address input domain from the preset input domain composed of the company address input domain, the ID card input domain and the legal representative input domain, and the check dictionary of the company address input domain is each province and city.

[0116] In S702, the target question and answer information corresponding to the target business is determined according to the preset check dictionary corresponding to the target input domain and the target question and answer text corresponding to the target input domain.

[0117] In combination with the above example, if the answer type content in the target question and answer text corresponding to the company address input domain is the address ab of company C, the target question and answer information corresponding to the target business is determined as a province b city according to the preset check dictionary of the company address input domain corresponding to each province and city.

[0118] The method provided in the embodiment determines the target input domain according to the input domain corresponding to the target question and answer text and the preset input domain set, and determines the target question and answer information corresponding to the target business according to the preset check dictionary corresponding to the target input domain and the target question and answer text corresponding to the target input domain, so that whether the format of the target question and answer text needs to be checked can be determined.

[0119] On the basis of the above-mentioned embodiment, S702, the target question and answer information corresponding to the target business is determined according to the preset check dictionary corresponding to the target input domain and the target question and answer text corresponding to the target input domain, which can be implemented in the following manner.

[0120] The target question and answer pairing text corresponding to the target input domain is checked by using a preset check dictionary, to obtain a checked target question and answer pairing text; and the target question and answer information corresponding to the target service is determined according to the input domain in the input domain matching library and the checked target question and answer pairing text.

[0121] In this embodiment, if the format of the target question and answer pairing text is not acceptable to the resource loan system, the target question and answer pairing text corresponding to the target input domain is checked by using a preset check dictionary, to obtain a checked target question and answer pairing text, and the target question and answer information is determined according to the input domain and the checked target question and answer pairing text. For example, the target question and answer text corresponding to the company address input domain is C company address ab, the a province b city preset check dictionary is used to replace C company address ab, to obtain a province b city, and the target question and answer information is determined to be a province b city according to the company address input domain.

[0122] The method provided in this embodiment checks the target question and answer pairing text corresponding to the target input domain by using a preset check dictionary, to obtain a checked target question and answer pairing text, and determines the target question and answer information corresponding to the target service according to the input domain in the input domain matching library and the checked target question and answer pairing text, so that the target question and answer pairing text in a format not acceptable to the resource loan system can be checked, and the target question and answer information can be displayed on the target terminal.

[0123] On the basis of the above-described embodiments, the target question and answer information corresponding to the target service can be determined according to the input domain in the input domain matching library and the checked target question and answer pairing text in the following manner:

[0124] The intersection between the input domain in the input domain matching library and the checked target question and answer pairing text is taken as the target question and answer information corresponding to the target service.

[0125] For example, the input domain in the input domain matching library includes the main office, the company legal person and the customer nature, and the checked target question and answer pairing text includes the main office, a province b city, the company legal person, Zhang San, the personnel scale and 1000 people, and the target question and answer information is the main office, a province b city, the company legal person and Zhang San.

[0126] The method provided in this embodiment takes the intersection between the input domain in the input domain matching library and the checked target question and answer pairing text as the target question and answer information corresponding to the target service. That is, the target question and answer information is determined by taking the intersection in this embodiment, which is simple, convenient and easy to operate.

[0127] It should be understood that although the steps in the flowcharts involved in the embodiments described above are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0128] Based on the same inventive concept, the embodiments of the present application also provide an information input device for implementing the information input method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more information input device embodiments provided below can refer to the limitations of the information input method described above, and will not be repeated here.

[0129] In one embodiment, as shown in Figure 8 Figure 8 is a structural block diagram of an information input device in an embodiment. The device 800 includes an acquisition module 801, an obtaining module 802, a determination module 803, and a sending module 804, wherein:

[0130] The acquisition module 801 is configured to acquire customer voice information required by a target service, and identify the customer voice information to obtain a sentence recognition result.

[0131] The obtaining module 802 is configured to obtain a question and answer paired text according to the sentence recognition result and a pre-constructed question and answer bank for a resource loan system.

[0132] The determination module 803 is configured to determine target question and answer information corresponding to the target service according to the question and answer paired text and a pre-constructed input domain matching bank for the resource loan system.

[0133] The sending module 804 is configured to send the target question and answer information to a target terminal. The target question and answer information is used for the target terminal to display the target question and answer information.

[0134] ​The information input device provided by the embodiment obtains customer voice information required by a target service, identifies the customer voice information to obtain a sentence recognition result, and then obtains question and answer matched text according to the sentence recognition result and a question and answer library for the resource loan system constructed in advance, so as to determine target question and answer information corresponding to the target service according to the question and answer matched text and an input domain matching library for the resource loan system constructed in advance, and send the target question and answer information for display to the target terminal. Since the question and answer matched text is obtained according to the sentence recognition result and the question and answer library for the resource loan system constructed in advance, and the target question and answer information corresponding to the target service is determined according to the question and answer matched text and the input domain matching library for the resource loan system constructed in advance, it is verified that the information input into the resource loan system is the target question and answer information corresponding to the target service, and the target question and answer information is sent to the target terminal for display, so that the target question and answer information is automatically input into the resource loan system, and the business efficiency of input information is improved.

[0135] In some embodiments, the obtaining module 802 includes:

[0136] The first obtaining unit is configured to perform word segmentation processing on each first sentence in the sentence recognition result to obtain a first word segmentation result.

[0137] The first determining unit is configured to, for each first word segmentation result, determine a similarity between the first word segmentation result and each target object in the question and answer library according to the question and answer library and the first word segmentation result.

[0138] The second obtaining unit is configured to, for each first word segmentation result, obtain question and answer matched text according to the similarity between the first word segmentation result and each target object in the question and answer library.

[0139] In some embodiments, the first determining unit includes:

[0140] The first determining sub-unit is configured to, for each second sentence, determine a first number of times that each word segmentation in the first word segmentation result appears in the second sentence.

[0141] The second determining sub-unit is configured to determine a second number of times that each word segmentation in the first word segmentation result appears in each keyword.

[0142] The third determining sub-unit is configured to determine the similarity between the first word segmentation result and the target object in the question and answer library according to the first number and the second number.

[0143] In some embodiments, the third determining sub-unit is specifically configured to determine a first product result of the first number and a first preset similarity value, determine a second product result of the second number and a second preset similarity value, and determine the similarity between the first word segmentation result and the target object in the question and answer library according to a sum of the first product result and the second product result.

[0144] In some embodiments, the second obtaining unit is specifically configured to determine a maximum similarity according to the similarity between the first segmentation result and each target object in the question and answer library; determine a question and answer label of the first segmentation result according to a question and answer type to which a sentence corresponding to the maximum similarity belongs; and obtain the question and answer pairing text according to the sequence of the first sentences and the question and answer label of the first segmentation result.

[0145] In some embodiments, the determining module 803 includes:

[0146] The pairing unit is configured to take the question and answer pairing text that is the same as the input domain in the input domain matching library as the target question and answer pairing text.

[0147] The second determining unit is configured to determine the target question and answer information corresponding to the target service according to the target question and answer pairing text.

[0148] In some embodiments, the second determining unit includes:

[0149] The fourth determining sub-unit is configured to determine the target input domain according to the input domain corresponding to the target question and answer pairing text and the preset input domain set; and the target input domain is an input domain provided with a corresponding verification dictionary.

[0150] The fifth determining sub-unit is configured to determine the target question and answer information corresponding to the target service according to the preset verification dictionary corresponding to the target input domain and the target question and answer pairing text corresponding to the target input domain.

[0151] In some embodiments, the fifth determining sub-unit is specifically configured to verify the target question and answer pairing text corresponding to the target input domain by using the preset verification dictionary to obtain a verified target question and answer pairing text; and determine the target question and answer information corresponding to the target service according to the input domain in the input domain matching library and the verified target question and answer pairing text.

[0152] In some embodiments, the fifth determining sub-unit is further specifically configured to take the intersection between the input domain in the input domain matching library and the verified target question and answer pairing text as the target question and answer information corresponding to the target service.

[0153] The above modules in the information input device can be all or partially realized by software, hardware, and a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in the computer device in a software form, so as to be called and executed by a processor to perform the operations corresponding to the above modules.

[0154] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 9As shown in the figure. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store target objects and input domain data. The network interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement an information input method.

[0155] Those skilled in the art can understand that, Figure 9 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0156] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps:

[0157] Obtain customer voice information required by the target service, and identify the customer voice information to obtain a sentence recognition result;

[0158] According to the sentence recognition result and the pre-constructed question and answer library for the resource loan system, obtain a question and answer matching text;

[0159] According to the question and answer matching text and the pre-constructed input domain matching library for the resource loan system, determine target question and answer information corresponding to the target service;

[0160] Send the target question and answer information to the target terminal; the target question and answer information is used to display the target question and answer information by the target terminal.

[0161] In one embodiment, the processor executing the computer program further implements the following steps:

[0162] Carry out word segmentation processing on each first sentence in the sentence recognition result to obtain a first word segmentation result;

[0163] For each first word segmentation result, according to the question and answer library and the first word segmentation result, determine the similarity between the first word segmentation result and each target object in the question and answer library;

[0164] For each first word segmentation result, according to the similarity between the first word segmentation result and each target object in the question and answer library, obtain a question and answer matching text.

[0165] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0166] For each second sentence, determine a first number of occurrences of each word in the first word segmentation result in the second sentence;

[0167] Determine a second number of occurrences of each word in the first word segmentation result in each keyword;

[0168] Determine the similarity between the first word segmentation result and the target object in the Q&A library according to the first number and the second number.

[0169] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0170] Determine a first product result of the first number and a first preset similarity value;

[0171] Determine a second product result of the second number and a second preset similarity value;

[0172] Determine the similarity between the first word segmentation result and the target object in the Q&A library according to the sum of the first product result and the second product result.

[0173] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0174] Determine the maximum similarity according to the similarity between the first word segmentation result and each target object in the Q&A library;

[0175] Determine the Q&A label of the first word segmentation result according to the Q&A type to which the sentence corresponding to the maximum similarity belongs;

[0176] Obtain the Q&A paired text according to the order of the first sentences and the Q&A labels of the first word segmentation results.

[0177] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0178] Select the Q&A paired text that matches the input domain in the input domain matching library as the target Q&A paired text;

[0179] Determine the target Q&A information corresponding to the target business according to the target Q&A paired text.

[0180] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0181] Determine the target input domain according to the input domain corresponding to the target Q&A paired text and the preset input domain set; the target input domain is an input domain provided with a corresponding verification dictionary;

[0182] According to the preset check dictionary corresponding to the target input domain and the target question and answer pairing text corresponding to the target input domain, target question and answer information corresponding to the target service is determined.

[0183] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0184] The target question and answer pairing text corresponding to the target input domain is checked using the preset check dictionary, to obtain checked target question and answer pairing text.

[0185] According to the input domain in the input domain matching library and the checked target question and answer pairing text, target question and answer information corresponding to the target service is determined.

[0186] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0187] The intersection between the input domain in the input domain matching library and the checked target question and answer pairing text is taken as the target question and answer information corresponding to the target service.

[0188] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program, when executed by a processor, implements the following steps:

[0189] Obtaining customer voice information required by a target service, and recognizing the customer voice information to obtain a sentence recognition result;

[0190] According to the sentence recognition result and a question and answer library for a resource loan system constructed in advance, a question and answer pairing text is obtained.

[0191] According to the question and answer pairing text and an input domain matching library for the resource loan system constructed in advance, target question and answer information corresponding to the target service is determined.

[0192] The target question and answer information is sent to a target terminal; the target question and answer information is used to display the target question and answer information by the target terminal.

[0193] In one embodiment, the computer program, when executed by the processor, also implements the following steps:

[0194] Each first sentence in the sentence recognition result is subjected to word segmentation processing to obtain a first word segmentation result.

[0195] For each first word segmentation result, the similarity of the first word segmentation result to each target object in the question and answer library is determined according to the question and answer library and the first word segmentation result.

[0196] For each first word segmentation result, the question and answer pairing text is obtained according to the similarity of the first word segmentation result to each target object in the question and answer library.

[0197] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0198] For each second sentence, determine a first number of times each word in the first word segmentation result appears in the second sentence;

[0199] Determine a second number of times each word in the first word segmentation result appears in each keyword;

[0200] Determine the similarity between the first word segmentation result and the target object in the question and answer library according to the first number and the second number.

[0201] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0202] Determine a first product result of the first number and a first preset similarity value;

[0203] Determine a second product result of the second number and a second preset similarity value;

[0204] Determine the similarity between the first word segmentation result and the target object in the question and answer library according to the sum of the first product result and the second product result.

[0205] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0206] Determine the maximum similarity according to the similarity between the first word segmentation result and each target object in the question and answer library;

[0207] Determine the question and answer label of the first word segmentation result according to the question and answer type to which the sentence corresponding to the maximum similarity belongs;

[0208] Obtain the question and answer pairing text according to the order of the first sentences and the question and answer labels of the first word segmentation results.

[0209] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0210] Select the question and answer pairing text that matches the input domain in the input domain matching library as the target question and answer pairing text;

[0211] Determine the target question and answer information corresponding to the target business according to the target question and answer pairing text.

[0212] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0213] Determine the target input domain according to the input domain corresponding to the target question and answer pairing text and the preset input domain set; the target input domain is an input domain provided with a corresponding verification dictionary;

[0214] According to the preset check dictionary corresponding to the target input domain and the target question and answer pairing text corresponding to the target input domain, target question and answer information corresponding to the target service is determined.

[0215] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0216] The target question and answer pairing text corresponding to the target input domain is checked using the preset check dictionary to obtain checked target question and answer pairing text.

[0217] According to the input domain in the input domain matching library and the checked target question and answer pairing text, target question and answer information corresponding to the target service is determined.

[0218] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0219] The intersection between the input domain in the input domain matching library and the checked target question and answer pairing text is taken as the target question and answer information corresponding to the target service.

[0220] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by the processor, implements the following steps:

[0221] Obtaining customer voice information required by the target service, and recognizing the customer voice information to obtain a sentence recognition result;

[0222] According to the sentence recognition result and the pre-constructed question and answer library for the resource loan system, a question and answer pairing text is obtained.

[0223] According to the question and answer pairing text and the pre-constructed input domain matching library for the resource loan system, target question and answer information corresponding to the target service is determined.

[0224] Sending the target question and answer information to the target terminal; the target question and answer information is used for the target terminal to display the target question and answer information.

[0225] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0226] Carrying out word segmentation processing on each first sentence in the sentence recognition result to obtain a first word segmentation result;

[0227] For each first word segmentation result, according to the question and answer library and the first word segmentation result, a similarity between the first word segmentation result and each target object in the question and answer library is determined.

[0228] For each first word segmentation result, according to the similarity between the first word segmentation result and each target object in the question and answer library, a question and answer pairing text is obtained.

[0229] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0230] For each second sentence, determine a first number of times each word in the first word segmentation result appears in the second sentence;

[0231] Determine a second number of times each word in the first word segmentation result appears in each keyword;

[0232] Determine the similarity between the first word segmentation result and the target object in the question and answer library according to the first number and the second number.

[0233] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0234] Determine a first product result of the first number and a first preset similarity value;

[0235] Determine a second product result of the second number and a second preset similarity value;

[0236] Determine the similarity between the first word segmentation result and the target object in the question and answer library according to the sum of the first product result and the second product result.

[0237] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0238] Determine the maximum similarity according to the similarity between the first word segmentation result and each target object in the question and answer library;

[0239] Determine the question and answer label of the first word segmentation result according to the question and answer type to which the sentence corresponding to the maximum similarity belongs;

[0240] Obtain the question and answer paired text according to the order of the first sentences and the question and answer labels of the first word segmentation results.

[0241] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0242] Match the question and answer paired text with the input domain in the library to the input domain in the library;

[0243] Determine the target question and answer information corresponding to the target business according to the target question and answer paired text.

[0244] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0245] Determine the target input domain according to the input domain corresponding to the target question and answer paired text and the preset input domain set; the target input domain is an input domain provided with a corresponding verification dictionary;

[0246] According to the preset check dictionary corresponding to the target input domain and the target question and answer pairing text corresponding to the target input domain, target question and answer information corresponding to the target service is determined.

[0247] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0248] The target question and answer pairing text corresponding to the target input domain is checked by using the preset check dictionary, and checked target question and answer pairing text is obtained.

[0249] According to the input domain in the input domain matching library and the checked target question and answer pairing text, target question and answer information corresponding to the target service is determined.

[0250] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0251] The intersection between the input domain in the input domain matching library and the checked target question and answer pairing text is taken as the target question and answer information corresponding to the target service.

[0252] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0253] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0254] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0255] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An information entry method, characterized in that, The method includes: Obtain customer voice information required for the target business, and recognize the customer voice information to obtain the sentence recognition result; The first word segmentation result is obtained by segmenting each first sentence in the sentence recognition result. For each of the first word segmentation results, the similarity between the first word segmentation result and each target object in the question-and-answer database is determined based on the pre-constructed question-and-answer database for the resource borrowing system and the first word segmentation results. The target objects include the second statement and each keyword. For each of the first word segmentation results, the maximum similarity is determined based on the similarity between the first word segmentation result and each target object in the question-and-answer database, and the question-and-answer tag of the first word segmentation result is determined based on the question-and-answer type to which the statement corresponding to the maximum similarity belongs; Based on the order of the first statements and the question-and-answer tags of the first word segmentation results, the question-and-answer paired text is obtained; Based on the question-and-answer matching text and the pre-built input domain matching library for the resource borrowing system, the target question-and-answer information corresponding to the target business is determined; The target question and answer information is sent to the target terminal; the target question and answer information is used for the target terminal to display the target question and answer information.

2. The method according to claim 1, characterized in that, Determining the similarity between the first word segmentation result and each target object in the question-answering database includes: For each of the second statements, determine the first occurrence number of each word in the first word segmentation result in the second statement; Determine the second frequency of each word segmentation in the first word segmentation result in each keyword; The similarity between the first word segmentation result and the target object in the question-and-answer database is determined based on the first number of times and the second number of times.

3. The method according to claim 2, characterized in that, Determining the similarity between the first word segmentation result and the target object in the question-answering database based on the first count and the second count includes: Determine the first product result of the first number of times and the first preset similarity value; Determine the second product result of the second number and the second preset similarity value; Based on the sum of the first product result and the second product result, the similarity between the first word segmentation result and the target object in the question-and-answer database is determined.

4. The method according to claim 1, characterized in that, The number of question-and-answer matching texts is multiple; the step of determining the target question-and-answer information corresponding to the target service based on the question-and-answer matching texts and a pre-built input domain matching library for the resource borrowing system includes: Use the question-and-answer matching text that has the same input field as the input field in the input field matching library as the target question-and-answer matching text; The target question and answer information corresponding to the target service is determined based on the target question and answer matching text.

5. The method according to claim 4, characterized in that, The step of determining the target question-and-answer information corresponding to the target service based on the target question-and-answer matching text includes: The target input field is determined based on the input field corresponding to the target question-and-answer matching text and a preset set of input fields; the target input field is an input field with a corresponding validation dictionary. Based on the preset verification dictionary corresponding to the target input field and the target question-and-answer pairing text corresponding to the target input field, the target question-and-answer information corresponding to the target service is determined.

6. The method according to claim 5, characterized in that, The step of determining the target question-and-answer information corresponding to the target service based on the preset verification dictionary corresponding to the target input domain and the target question-and-answer pairing text corresponding to the target input domain includes: The target question-and-answer matching text corresponding to the target input domain is validated using the preset validation dictionary to obtain the validated target question-and-answer matching text. Based on the input domain in the input domain matching library and the verified target question-and-answer matching text, the target question-and-answer information corresponding to the target service is determined.

7. The method according to claim 6, characterized in that, The step of determining the target question-and-answer information corresponding to the target service based on the input domain in the input domain matching library and the verified target question-and-answer matching text includes: The intersection between the input domain in the input domain matching library and the verified target question-and-answer matching text is taken as the target question-and-answer information corresponding to the target service.

8. An information input device, characterized in that, The device includes: The acquisition module is used to acquire customer voice information required by the target business and to identify the customer voice information to obtain the sentence recognition result; The acquisition module includes a first acquisition unit, a first determination unit, and a second acquisition unit. The first obtaining unit is used to perform word segmentation processing on each first statement in the statement recognition result to obtain a first word segmentation result. The first determining unit is used to determine the similarity between each of the first word segmentation results and each target object in the question-and-answer database based on a pre-built question-and-answer database for the resource borrowing system and the first word segmentation results. The target objects include the second statement and each keyword. The second obtaining unit is used to determine the maximum similarity between each of the first word segmentation results and each target object in the question-and-answer database, and to determine the question-and-answer tag of the first word segmentation result according to the question-and-answer type of the statement corresponding to the maximum similarity; and to obtain the question-and-answer matching text according to the order of each of the first statements and the question-and-answer tag of each of the first word segmentation results. The determination module is used to determine the target question and answer information corresponding to the target business based on the question and answer matching text and a pre-built input domain matching library for the resource borrowing system. The sending module is used to send the target question and answer information to the target terminal; the target question and answer information is used for the target terminal to display the target question and answer information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images