Information acquisition method and related device

Abstract

The application discloses an information acquisition method and related equipment, comprising: acquiring a user input question text, and performing word segmentation on the question text to obtain at least one keyword; identifying the type of the question according to the keyword to obtain a question type; if the question type is personnel search, searching in a duty system and a document system according to the keyword, and returning a target object obtained by the search; if the question type is a technical question, searching in a question library and a document system according to the keyword, and returning a target answer obtained by the search; and if the question type is a personnel portrait, searching in a basic information system according to the keyword, and returning a target portrait obtained by the search. The whole consultation process is initiated by the user, and the robot determines the answer content by searching various information systems, so that the required information can be conveniently and efficiently provided for enterprise employees.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and more particularly, to an information acquisition method and related equipment. BACKGROUND

[0002] In an enterprise, it is inevitable to acquire various information to help promote work. For example, relevant contacts are found for a certain process or a certain field; answers are sought to quickly solve technical problems in work; and relevant persons in charge are found for a certain product line.

[0003] At present, the person-finding module mostly searches according to the enterprise internal address book. For technical problems, they are usually solved by relying on their own experience and knowledge or seeking answers through the Internet.

[0004] For an enterprise with a large scale, fine division of labor, and a large number of employees, how to accurately and quickly find relevant personnel in the enterprise becomes a problem to be solved. This problem becomes more prominent when the personnel in the enterprise flow frequently.

[0005] In addition, for various specific technical problems encountered in work, relevant answers may not be quickly searched on the Internet. Therefore, an efficient consultation approach is needed to enable the staff to conveniently and accurately acquire the solution to the technical problem and avoid inefficiently searching for a needle in a haystack on the Internet. SUMMARY

[0006] Therefore, the present application provides an information acquisition method and related equipment to provide efficient consultation services for employees of an enterprise.

[0007] To achieve the above-mentioned purpose, the first aspect of the present application provides an information acquisition method, comprising:

[0008] acquiring a question text input by a user and performing word segmentation on the question text to obtain at least one keyword;

[0009] identifying the type of the question according to the keyword to obtain a problem type;

[0010] if the problem type is personnel finding, searching in a duty system and a document system according to the keyword, and returning a target object obtained by the search;

[0011] if the problem type is a technical problem, searching in a question library and a document system according to the keyword, and returning a target solution obtained by the search;

[0012] if the problem type is a personnel portrait, searching in a basic information system according to the keyword, and returning a target portrait obtained by the search.

[0013] Preferably, the process of searching in the on-duty system and the document system according to the keyword and returning the target object searched comprises:

[0014] determining the business name of the target object according to the keyword;

[0015] searching in the on-duty system according to the business name and judging whether the target object matching the business name is searched;

[0016] if yes, returning the target object searched according to the search result;

[0017] if no, searching in the document system according to the business name with a preset combination rule and returning the target object searched according to the search result.

[0018] Preferably, the process of searching in the document system according to the business name with a preset combination rule and returning the target object searched according to the search result comprises:

[0019] searching for the personnel related to the business name from the documents newly added and / or modified in the document system within a preset time to obtain a search result;

[0020] eliminating the personnel who have left from the search result to obtain at least one candidate personnel;

[0021] obtaining the similarity value of the candidate personnel and the business name and sorting the candidate personnel according to the similarity value;

[0022] taking the candidate personnel with the largest similarity value as the target object searched and returning the target object.

[0023] Preferably, the process of searching in the question bank and the document system according to the keyword and returning the target answer searched comprises:

[0024] traversing each question record recorded in the question bank:

[0025] calculating the distance between the keyword and the question record according to the Jaccard distance algorithm;

[0026] if the distance is less than a first distance threshold, stopping the traversal and taking the question record as the target answer and returning the target answer;

[0027] if the distance is not less than the first distance threshold and less than a second distance threshold, marking the question record as a candidate answer and calculating the total number of candidate answers;

[0028] If the total number of candidate solutions reaches a preset threshold, the traversal stops, and the question record marked as each candidate solution is used as the target solution, and the target solution is returned.

[0029] After traversing all the question records in the question database, determine whether there are any question records marked as candidate solutions;

[0030] If so, then the question record marked as each candidate solution is used as the target solution, and the target solution is returned;

[0031] If not, search the document system based on the keywords and return the target answer obtained from the search.

[0032] Preferably, the process of searching the basic information system based on the keywords and returning the target profile obtained from the search includes:

[0033] The target object's identifier is determined based on the keywords;

[0034] Based on the identifier, a search is performed in the basic information system to obtain the application or product line that the target object is responsible for.

[0035] Obtain at least one other person in charge of the application or product line, calculate the weight of the person in charge, and determine the relevant person in charge based on the weight;

[0036] The target object's responsible application or product line, as well as the relevant responsible personnel, are used as the target profile obtained by the search, and the target profile is returned.

[0037] Preferably, the process of calculating the weight of the responsible personnel and determining the relevant responsible personnel based on the weight includes:

[0038] For the personnel in charge of a product line, calculate the number of applications that the personnel are responsible for in that product line;

[0039] The weight of each responsible person is determined based on the number of applications they are responsible for, with the number of applications being positively correlated with the weight.

[0040] The personnel with the highest weight in the preset number are identified as the relevant responsible personnel.

[0041] Preferably, the process of identifying the question type based on the keywords to obtain the question type includes:

[0042] Determine whether the keyword contains a preset first word or a preset second word;

[0043] If the first preset word is included, the question type is determined to be personnel search; if the second preset word is included, the question type is determined to be personnel profiling.

[0044] If the first preset word and the second preset word are not included, the problem type is determined as a technical problem.

[0045] The second aspect of the present application provides an information acquisition device, comprising:

[0046] A word segmentation unit is configured to acquire a user inputted question text and perform word segmentation on the question text to obtain at least one keyword.

[0047] A problem type determination unit is configured to identify the type of the question according to the keyword to obtain a problem type.

[0048] A personnel search unit is configured to search in a duty system and a document system according to the keyword and return a target object obtained by the search.

[0049] A technical problem unit is configured to search in a question library and a document system according to the keyword and return a target solution obtained by the search.

[0050] A target portrait unit is configured to search in a basic information system according to the keyword and return a target portrait obtained by the search.

[0051] The third aspect of the present application provides an information acquisition device, comprising a memory and a processor.

[0052] The memory is configured to store a program.

[0053] The processor is configured to execute the program to realize each step of the information acquisition method.

[0054] The fourth aspect of the present application provides a storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to realize each step of the information acquisition method.

[0055] Via the technical solution, the application first acquires the question text input by the user, and performs word segmentation on the question text to obtain at least one keyword. Then, the type of the question is identified according to the keyword to obtain a question type. The question type includes personnel search, technical question and personnel portrait. For the question input by the user, if the question type is personnel search, the keyword is searched in the on-duty system and the document system, and the target object searched is returned; if the question type is technical question, the keyword is searched in the question library and the document system, and the target answer searched is returned; if the question type is personnel portrait, the keyword is searched in the basic information system, and the target portrait searched is returned. The entire consultation process is initiated by the user, and the robot determines the answer content by searching various information systems, which can conveniently and efficiently provide the required information for the employees of the enterprise. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only a part of the embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the provided drawings.

[0057] Figure 1 A schematic diagram of the information acquisition method disclosed in the embodiments of the present application;

[0058] Figure 2 A schematic diagram of the information acquisition device disclosed in the embodiments of the present application;

[0059] Figure 3 A schematic diagram of the information acquisition device disclosed in the embodiments of the present application. DETAILED DESCRIPTION

[0060] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0061] The information acquisition method provided by the embodiments of the present application will be introduced below. Please refer to Figure 1 The information acquisition method provided by the embodiments of the present application can include the following steps:

[0062] Step S100, performing word segmentation on the question text to obtain at least one keyword.

[0063] Specifically, the user input question text is acquired, and the question text is segmented to obtain at least one keyword.

[0064] In an optional embodiment, a TF-IDF (term frequency-inverse document frequency) algorithm based on a Jieba Chinese segmentation component can be used to segment the input keyword or sentence.

[0065] For example, for the input question text "The keyword is a word that can express the center content of the document, commonly used in computer system indexing paper content features, information retrieval, system collection for readers to review. Keyword extraction is a branch of text mining, and is the basic work of text retrieval, document comparison, abstract generation, document classification and clustering, etc. Text mining research", after the TF-IDF of the Jieba Chinese segmentation component is segmented, the keywords "document", "text", "keyword", "mining" and "text retrieval" can be obtained.

[0066] Step S200, according to the keyword, the type of the question is identified, and the question type is obtained.

[0067] Specifically, the question type can include personnel search, technical question and personnel portrait.

[0068] The personnel search can be a search for personnel in a specified department, a specified product or a specified function. Through the personnel search type question, the relevant responsible person can be conveniently found.

[0069] The technical question can be a technical question generated in the research and development process of the technical team of the enterprise. The answer to the technical question can be obtained by the responsible person of each field in the enterprise combined with the work content, and through the technical question, the relevant experience and knowledge can be conveniently and accurately obtained.

[0070] The personnel portrait is information about the responsibilities, fields and skills that the employees in the enterprise are responsible for, the application or product line they are responsible for, and other employee information similar to the work content and nature of the employee. Through the personnel portrait question, the information of the queried personnel can be conveniently and intuitively understood, and other personnel related to the personnel can be known. When the personnel cannot be accessed, other related personnel can be tried to access to temporarily solve the related problem.

[0071] Step S300, if the question type is personnel search, the keyword is searched in the on-duty system and the document system, and the target object obtained by the search is returned.

[0072] Specifically, the on-duty system records staff on duty in the enterprise within a period of time, which can be a past period of time, can be the current day, or can be a future period of time. All staff on duty within a specified time can be queried through the on-duty system.

[0073] The document system is part of the enterprise Wiki (Wikipedia), which can be a system for storing various documents generated within the enterprise, such as work documents, product documents, customer documents, etc.

[0074] Step S400, if the question type is a technical question, search in the question library and the document system according to the keywords, and return the target answer obtained by searching.

[0075] Among them, the question library contains Frequently Asked Questions (FAQ) that are frequently encountered in work. For such questions, they can be sorted by relevant staff within the enterprise, and the solution ideas of the questions can be written by the relevant person in charge in the field, such as the person in charge of each product. Finally, it is summarized into a question library for reference.

[0076] Step S500, if the question type is a personnel portrait, search in the basic information system according to the keywords, and return the target portrait obtained by searching.

[0077] Among them, the basic information system can contain various basic information within the enterprise, such as detailed information of each staff, detailed information of each product, etc. Among them, the detailed information of the staff can include the responsibilities, fields and skills that the staff is good at, and the application or product line that the staff is responsible for, etc. In addition, it can also be linked to other employees whose work content and nature are similar to the employee.

[0078] The application first acquires the question text input by the user, and performs word segmentation on the question text to obtain at least one keyword. Then, the type of the question is identified according to the keyword, and the question type is obtained. Among them, the question type includes personnel search, technical question and personnel portrait. For the question input by the user, if the question type of the question is personnel search, search in the on-duty system and the document system according to the keyword, and return the target object obtained by searching; if the question type of the question is a technical question, search in the question library and the document system according to the keyword, and return the target answer obtained by searching; if the question type of the question is a personnel portrait, search in the basic information system according to the keyword, and return the target portrait obtained by searching. The entire consultation process is initiated by the user, and the robot determines the answer content by searching various information systems, which can conveniently and efficiently provide the required information for the employees of the enterprise.

[0079] In some embodiments of the present application, the process of identifying the type of the question according to the keywords in step S200 can include:

[0080] S1, determining whether the keywords contain a preset first word or a preset second word.

[0081] S2, if the keywords contain the preset first word, determining that the type of the question is personnel search; if the keywords contain the preset second word, determining that the type of the question is personnel profiling.

[0082] S3, if the keywords do not contain the preset first word or the preset second word, determining that the type of the question is a technical question.

[0083] For example, the first word can be set as “find people”, “seek people”, etc., and the second word can be set as “calculate”, “look”, etc.

[0084] When the user wants to search for personnel, the user can input “find people shopping cart”, and the keywords “find people” and “shopping cart” are identified in step S100. At this time, according to the keyword “find people”, it can be determined that the type of the question is personnel search.

[0085] When the user wants to query personnel profiling, the user can input “calculate Xu San Duo”, and the keywords “calculate” and “Xu San Duo” are identified in step S100. At this time, according to the keyword “calculate”, it can be determined that the type of the question is personnel profiling.

[0086] When the user wants to ask a technical question, the user can input “vpaas application cannot start”, and the keywords “vpaas”, “application” and “cannot start” are identified in step S100. At this time, the keywords do not contain any first word or second word, so it can be determined that the type of the question is a technical question.

[0087] By setting the first word or the second word, the interpretation of the sentence becomes simple, and the complexity of the question recognition by the robot is reduced.

[0088] In some embodiments of the present application, the process of searching the target object in the on-duty system or the document system according to the keywords in step S300 and returning the target object can include:

[0089] S1, determining the business name of the target object according to the keywords.

[0090] The business name can be the business, the application or the product line of the target object to be searched, etc.

[0091] For example, the keywords of the received question text in step S100 are "find people" and "shopping cart", and the business name here is "shopping cart".

[0092] S2, search in the on-duty system according to the business name, and determine whether the target object matching the business name is searched.

[0093] S3, if the target object matching the business name is searched, return the target object searched according to the search result;

[0094] S4, if the target object matching the business name is not searched, search in the document system according to the business name with a preset combination rule, and return the target object searched according to the search result.

[0095] By searching in the on-duty system first, the on-duty personnel can be obtained, and the on-duty personnel is usually in a working state, so the personnel can be quickly accessed. When the relevant personnel cannot be searched in the on-duty system, the document system is searched to expand the search range.

[0096] The preset combination rule mentioned in S4 above can include the time range of the document, whether in service, etc. Based on this, in some embodiments of the present application, the process of S4 above searching in the document system according to the business name with a preset combination rule and returning the target object searched according to the search result can include:

[0097] S41, search for personnel related to the business name from at least one of the newly added and modified documents in the document system within a preset time, and obtain a search result.

[0098] Among them, by setting the range of the document to be newly added or modified within a preset time, on the one hand, the search range can be reduced and the search time can be reduced; on the other hand, the search result obtained must be active within the preset time, and the personnel related to the business name can be more accurately searched.

[0099] For example, for finding in-service personnel, the preset time can be set to 1 year, and the personnel searched according to this is the personnel active within 1 year, avoiding searching out records of many years ago.

[0100] S42, eliminate personnel who have left the job from the search result, and obtain at least one candidate personnel.

[0101] S43, obtain the similarity value of the candidate personnel and the business name, and sort the candidate personnel according to the similarity value.

[0102] Wherein, according to the business name, a plurality of candidate personnel can be searched out, at this time, a similarity value of each candidate personnel and the business name can be calculated, and through the similarity value, the degree of coincidence of the candidate personnel and the search condition can be determined.

[0103] S44, the candidate personnel with the maximum similarity value in the preset number are taken as the target object obtained by searching, and the target object is returned.

[0104] For example, the preset number can be set to 5, and according to the ranking of the candidate personnel, the 5 candidate personnel with the maximum similarity value are selected as the target object obtained by searching.

[0105] In some embodiments of the present application, the process of searching in the question library and the document system according to the keyword and returning the target answer obtained by searching according to the above-mentioned step S400 can include:

[0106] Traverse each question record recorded in the question library:

[0107] S1, calculate the distance between the keyword and the question record according to the Jaccard distance algorithm.

[0108] S2, if the distance is less than the first distance threshold, stop traversing, and take the question record as the target answer, and return the target answer.

[0109] For example, the first distance threshold is set to 0.3, and when the Jaccard distance between a question record and the keyword is less than 0.3, it is considered that the question record is very close to the question to be asked, and the question record is taken as the target answer.

[0110] S3, if the distance is not less than the first distance threshold and less than the second distance threshold, mark the question record as a candidate answer, and calculate the total number of candidate answers.

[0111] For example, the first distance threshold is set to 0.3, and the second distance threshold is set to 0.65, and when the Jaccard distance between a question record and the keyword is between 0.3 and 0.65, it is considered that the question is likely to be related to the question to be asked, and the question record is marked as a candidate answer.

[0112] S4, if the total number of candidate answers reaches a preset threshold, stop traversing, and take the question records marked as the candidate answers as the target answer, and return the target answer.

[0113] For example, the threshold is set to 10, and when the total number of candidate answers reaches 10, the traversal is stopped, and other question records in the question library are not judged.

[0114] S5, after traversing all the question records recorded in the question library, it is determined whether there is a question record marked as a candidate answer.

[0115] For some questions, the entire question library can be traversed and no corresponding answer can be found. Therefore, it is also necessary to make a judgment.

[0116] S6, if there is a question record marked as a candidate answer, the question record marked as each candidate answer is taken as a target answer, and the target answer is returned.

[0117] S7, if there is no question record marked as a candidate answer, a search is performed in the document system according to the keyword, and a target answer obtained by the search is returned.

[0118] Since the question library records the FAQ of the enterprise, it contains the frequently-occurring questions and answers in work. By first searching the technical question in the question library, the answer to the technical question can be quickly located. When no corresponding answer can be found in the question library, a search is performed in the document system, and the document system is used as a useful supplement.

[0119] In some embodiments of the present application, the process of searching in the basic information system according to the keyword and returning the target portrait obtained by the search in the above step S500 can include:

[0120] S1, determining the identification of the target object according to the keyword.

[0121] S2, searching in the basic information system according to the identification of the target object to obtain the application or product line responsible by the target object.

[0122] S3, obtaining at least one other responsible person of the responsible application or product line, calculating the weight of the responsible person, and determining the related responsible person according to the weight.

[0123] S4, taking the application or product line responsible by the target object and the related responsible person as the target portrait obtained by the search, and returning the target portrait.

[0124] By this method, other persons can clearly understand the product and professional content of the queried person, and can understand the information of the person similar to the queried person.

[0125] In some embodiments of the present application, the process of calculating the weight of the responsible person and determining the related responsible person according to the weight in the above S3 can include:

[0126] S31, for the responsible person responsible for the product line, the number of applications responsible by the responsible person in the product line is calculated.

[0127] S32, determining a weight of the responsible person according to a number of applications that the responsible person is responsible for, wherein the number is positively correlated with the weight.

[0128] S33, determining a preset number of responsible persons with the largest weight as the relevant responsible persons.

[0129] A product line can include multiple applications, and therefore, for a responsible person responsible for a product line, the number of applications that the responsible person is responsible for in the product line can also be calculated, which can reflect the importance of the responsible person in the product line to some extent.

[0130] The information acquisition device provided in the embodiments of the present application is described below. The information acquisition device described below can be referred to in correspondence with the information acquisition method described above.

[0131] Please refer to Figure 2 The information acquisition device provided in the embodiments of the present application can include:

[0132] The word segmentation unit 21 is configured to acquire a user input question text and perform word segmentation on the question text to obtain at least one keyword.

[0133] The question type determination unit 22 is configured to identify the type of the question according to the keyword to obtain a question type.

[0134] The person searching unit 23 is configured to search in a duty system and a document system according to the keyword and return a target object obtained by the search.

[0135] The technical problem unit 24 is configured to search in a question library and a document system according to the keyword and return a target solution obtained by the search.

[0136] The target portrait unit 25 is configured to search in a basic information system according to the keyword and return a target portrait obtained by the search.

[0137] In some embodiments of the present application, the process of identifying the type of the question according to the keyword to obtain a question type by the question type determination unit 22 described above can include:

[0138] determining whether the keyword contains a preset first word or a preset second word.

[0139] If the keyword contains the preset first word, it is determined that the question type is a person search; if the keyword contains the preset second word, it is determined that the question type is a person portrait.

[0140] If the keyword does not contain the preset first word and the preset second word, it is determined that the question type is a technical problem.

[0141] In some embodiments of the present application, the process of searching for the target object according to the keywords in the on-duty system and the document system and returning the target object can include:

[0142] determining the business name of the target object according to the keywords;

[0143] searching in the on-duty system according to the business name and determining whether the target object matching the business name is found;

[0144] if yes, returning the target object found according to the search result;

[0145] if no, searching in the document system according to the business name with a preset combination rule and returning the target object found according to the search result.

[0146] In some embodiments of the present application, the process of searching in the document system according to the business name with a preset combination rule and returning the target object according to the search result can include:

[0147] searching for the personnel related to the business name from the documents newly added and / or modified in the document system within a preset time to obtain a search result;

[0148] eliminating the personnel who have left from the search result to obtain at least one candidate personnel;

[0149] obtaining the similarity value of the candidate personnel and the business name and sorting the candidate personnel according to the similarity value;

[0150] taking the candidate personnel with the largest similarity value as the target object found and returning the target object.

[0151] In some embodiments of the present application, the process of searching for the target object according to the keywords in the on-duty system and the document system and returning the target object can include:

[0152] traversing each problem record recorded in the problem library:

[0153] calculating the distance between the keywords and the problem record according to the Jaccard distance algorithm;

[0154] if the distance is less than a first distance threshold, stopping the traversal and taking the problem record as the target answer and returning the target answer;

[0155] if the distance is not less than the first distance threshold and less than a second distance threshold, marking the problem record as a candidate answer and calculating the total number of candidate answers;

[0156] If the total number of candidate answers reaches a preset threshold, the traversal is stopped, and a question record marked as a candidate answer is taken as a target answer, and the target answer is returned;

[0157] After each question record recorded in the question library is traversed, it is determined whether there is a question record marked as a candidate answer;

[0158] If yes, a question record marked as a candidate answer is taken as a target answer, and the target answer is returned;

[0159] If no, a search is performed in a document system according to the keyword, and a target answer obtained by the search is returned.

[0160] In some embodiments of the present application, the process in which the target portrait unit 25 performs a search in a basic information system according to the keyword and returns a target portrait obtained by the search can include:

[0161] Determining an identifier of a target object according to the keyword;

[0162] Performing a search in a basic information system according to the identifier to obtain an application or product line responsible by the target object;

[0163] Obtaining at least one other responsible person of the responsible application or product line, calculating a weight of the responsible person, and determining a related responsible person according to the weight;

[0164] Taking the application or product line responsible by the target object and the related responsible person as a target portrait obtained by the search, and returning the target portrait.

[0165] In some embodiments of the present application, the process in which the target portrait unit 25 calculates a weight of the responsible person and determines a related responsible person according to the weight can include:

[0166] For a responsible person responsible for a product line, the number of applications responsible by the responsible person in the product line is calculated;

[0167] According to the number of applications responsible by each responsible person, a weight of the responsible person is determined, and the number and the weight are positively correlated;

[0168] A preset number of responsible persons with the largest weight are determined as related responsible persons.

[0169] The information acquisition device provided by the embodiments of the present application can be applied to information acquisition equipment such as computers, mobile phones and the like. Optionally, Figure 3 A hardware structure block diagram of the information acquisition equipment is shown, and reference is made to Figure 3The hardware structure for information acquisition can include at least one processor 31, at least one communication interface 32, at least one memory 33, and at least one communication bus 34.

[0170] In the embodiments of the present application, the number of the processor 31, the communication interface 32, the memory 33, and the communication bus 34 is at least one, and the processor 31, the communication interface 32, and the memory 33 complete communication with each other through the communication bus 34.

[0171] The processor 31 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application, etc.

[0172] The memory 32 can include a high-speed RAM memory, and can also include a non-volatile memory, such as at least one disk memory.

[0173] The memory 33 stores a program, and the processor 31 can invoke the program stored in the memory 33, and the program is used for:

[0174] acquiring a question text input by a user, and performing word segmentation on the question text to obtain at least one keyword;

[0175] identifying a type of the question according to the keyword to obtain a question type;

[0176] if the question type is personnel search, searching in a duty system and a document system according to the keyword, and returning a target object obtained by the searching;

[0177] if the question type is a technical question, searching in a question library and a document system according to the keyword, and returning a target answer obtained by the searching;

[0178] if the question type is a personnel portrait, searching in a basic information system according to the keyword, and returning a target portrait obtained by the searching.

[0179] Optionally, the detailed functions and extended functions of the program can refer to the description above.

[0180] The embodiments of the present application also provide a storage medium which can store a program suitable for a processor to execute, and the program is used for:

[0181] acquiring a question text input by a user, and performing word segmentation on the question text to obtain at least one keyword;

[0182] According to the keywords, the type of the question is identified, and a question type is obtained;

[0183] If the question type is personnel search, the keywords are searched in a duty system and a document system, and a target object searched is returned;

[0184] If the question type is a technical question, the keywords are searched in a question library and a document system, and a target answer searched is returned;

[0185] If the question type is a personnel portrait, the keywords are searched in a basic information system, and a target portrait searched is returned.

[0186] Optionally, the refinement function and the extension function of the program can refer to the description above.

[0187] In summary:

[0188] The application first acquires a question text input by a user, and performs word segmentation on the question text to obtain at least one keyword. Then, according to the keywords, the type of the question is identified, and a question type is obtained. The question type includes personnel search, a technical question, and a personnel portrait. For the question input by the user, if the question type is personnel search, the keywords are searched in a duty system and a document system, and a target object searched is returned; if the question type is a technical question, the keywords are searched in a question library and a document system, and a target answer searched is returned; if the question type is a personnel portrait, the keywords are searched in a basic information system, and a target portrait searched is returned. The entire consultation process is initiated by the user, and the robot determines the answer content by searching various information systems, which can conveniently and efficiently provide the required information for enterprise employees.

[0189] Finally, it should be noted that in this document, the terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0190] The various embodiments described in this specification are intended to be combinable unless otherwise indicated herein. The various embodiments described in this specification are described in the progressions noted, with each embodiment emphasizing different aspects over others. The various embodiments can be combined according to need and similar parts from each embodiment refer to each other as appropriate.

[0191] The foregoing description of the disclosed embodiments enables a person skilled in the art to make or use the application. Modifications of these embodiments will occur to those skilled in the art, and all such modifications are believed to be within the scope of the application. As will be apparent, certain embodiments of the application can be practiced without all the features presented. Therefore, the foregoing description should not be taken as limiting the scope of the application which is defined by the appended claims.

Claims

1. An information acquisition method characterized by comprising: The method comprises the following steps: acquiring user input question text, and performing word segmentation on the question text to obtain at least one keyword; identifying the type of the question according to the keyword to obtain a question type; if the question type is personnel search, searching in a duty system and a document system according to the keyword, and returning a target object obtained by the search; wherein the personnel search is to search for personnel in a specified department, a specified product or a specified function; if the question type is a technical question, searching in a question library and a document system according to the keyword, and returning a target answer obtained by the search; wherein the technical question is a technical question generated in the research and development process of an enterprise technical team; if the question type is a personnel portrait, searching in a basic information system according to the keyword, and returning a target portrait obtained by the search; wherein the personnel portrait includes the responsibility, the field and the skill that an employee in an enterprise is good at, and the application or the product line that the employee is responsible for; wherein the process of searching in the basic information system according to the keyword and returning the target portrait obtained by the search comprises: determining the identification of the target object according to the keyword; searching in the basic information system according to the identification to obtain the application or the product line that the target object is responsible for; obtaining at least one other responsible personnel of the responsible application or the product line, calculating the weight of the responsible personnel, and determining the related responsible personnel according to the weight; taking the application or the product line that the target object is responsible for and the related responsible personnel as the target portrait obtained by the search, and returning the target portrait.

2. The method of claim 1, wherein, The process of searching in the duty system and the document system according to the keyword and returning the target object obtained by the search comprises: determining the business name of the target object according to the keyword; searching in the duty system according to the business name to determine whether the target object matching the business name is searched; if yes, returning the target object obtained by the search according to the search result; if no, searching in the document system according to the business name with a preset combination rule, and returning the target object obtained by the search according to the search result.

3. The method of claim 2, wherein, The process of searching in the document system according to the business name with a preset combination rule and returning the target object obtained by the search according to the search result comprises: searching for personnel related to the business name from the documents newly added and / or modified in the preset time in the document system to obtain a search result; eliminating the personnel who have resigned from the search result to obtain at least one candidate personnel; obtaining the similarity value of the candidate personnel and the business name, and sorting the candidate personnel according to the similarity value; taking the preset number of candidate personnel with the largest similarity as the target object obtained by the search, and returning the target object.

4. The method of claim 1, wherein, The process of searching in the question library and the document system according to the keyword and returning the target answer obtained by the search comprises: traversing each problem record recorded in the question library: calculating the distance between the keyword and the problem record according to the Jaccard distance algorithm; If the distance is less than a first distance threshold, the iteration is stopped, and the question record is taken as a target answer, and the target answer is returned; If the distance is not less than the first distance threshold and less than a second distance threshold, the question record is marked as a candidate answer, and a total number of candidate answers is calculated; If the total number of candidate answers reaches a preset threshold, the iteration is stopped, and the question record marked as each candidate answer is taken as a target answer, and the target answer is returned; After each question record recorded in the question library is iterated, it is determined whether there is a question record marked as a candidate answer; If yes, the question record marked as each candidate answer is taken as a target answer, and the target answer is returned; If no, a search is performed in a document system according to the keyword, and a target answer obtained by the search is returned.

5. The method of claim 1, wherein, The weight of the responsible person is calculated, and a process of determining the relevant responsible person according to the weight includes: For the responsible person responsible for a product line, the number of applications that the responsible person is responsible for in the product line is calculated; According to the number of applications that each responsible person is responsible for, the weight of the responsible person is determined, and the number and the weight are positively correlated; A preset number of responsible persons with the largest weight are determined as the relevant responsible persons.

6. The method of claim 1, wherein, A process of identifying the type of the question according to the keyword includes: It is determined whether the keyword contains a preset first word or a second word; If the preset first word is contained, it is determined that the type of the question is personnel search; if the preset second word is contained, it is determined that the type of the question is personnel portrait; If the preset first word and the second word are not contained, it is determined that the type of the question is a technical question.

7. An information acquisition apparatus characterized by comprising: It includes: A word segmentation unit is configured to obtain a question text input by a user, and perform word segmentation on the question text to obtain at least one keyword; A question type determination unit is configured to identify the type of the question according to the keyword, and obtain a question type; A personnel search unit is configured to, if the type of the question is personnel search, perform a search in a duty system and a document system according to the keyword, and return a target object obtained by the search; wherein the personnel search is a search for personnel in a specified department, a specified product or a specified function; A technical question unit is configured to, if the type of the question is a technical question, perform a search in a question library and a document system according to the keyword, and return a target answer obtained by the search; wherein the technical question is a technical question generated in a research and development process of a technical team in an enterprise; A target portrait unit is configured to, if the type of the question is personnel portrait, perform a search in a basic information system according to the keyword, and return a target portrait obtained by the search; wherein the personnel portrait includes a responsibility, a field and a skill that an employee in the enterprise is good at, and an application or a product line that the employee is responsible for; The target portrait unit is configured to perform a search in the basic information system according to the keyword, and return a target portrait obtained by the search, and the process includes: The identification of a target object is determined according to the keyword; A search is performed in the basic information system according to the identification, and an application or a product line that the target object is responsible for is obtained. obtaining at least one other responsible person of the application or product line responsible by the target object, calculating the weight of the responsible person, and determining the relevant responsible person according to the weight; taking the application or product line responsible by the target object and the relevant responsible person as the target portrait obtained by searching, and returning the target portrait.

8. An information acquisition apparatus characterized by comprising: comprise: a memory and a processor; the memory is used for storing a program; the processor is used for executing the program, and realizing each step of the information acquisition method according to any one of claims 1-6.

9. A storage medium having stored thereon a computer program, characterized in that the computer program is executed by the processor, and realizes each step of the information acquisition method according to any one of claims 1-6.

Images