CN116775813B - Service searching method, device, electronic equipment and readable storage medium - Google Patents
Service searching method, device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN116775813B CN116775813B CN202311065041.4A CN202311065041A CN116775813B CN 116775813 B CN116775813 B CN 116775813B CN 202311065041 A CN202311065041 A CN 202311065041A CN 116775813 B CN116775813 B CN 116775813B
- Authority
- CN
- China
- Prior art keywords
- service
- information
- target
- target user
- alternative
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000000605 extraction Methods 0.000 claims abstract description 24
- 238000003058 natural language processing Methods 0.000 claims description 56
- 230000008451 emotion Effects 0.000 claims description 44
- 230000006399 behavior Effects 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 33
- 230000011218 segmentation Effects 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 17
- 238000012552 review Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000009825 accumulation Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 11
- 238000003032 molecular docking Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application discloses a service searching method, a device, electronic equipment and a readable storage medium, wherein the method comprises the following steps: acquiring preset information and extraction information of each service, wherein the extraction information is obtained by analyzing implicit information of each service; determining alternative services from the preset information and the extracted information according to the service searching requirements of the target user; and displaying the alternative service to the target user.
Description
Technical Field
The application belongs to the field of artificial intelligence, and particularly relates to a service searching method, a service searching device, electronic equipment and a readable storage medium.
Background
Today, where new generation information technology applications are in progress, users can search for business portals to be transacted through online business channels for business transaction. At present, a search for a user service is mainly performed through a service name field, a keyword and a recommended word provided by a service system during release, and the search capability is very limited, for example, a user only knows own requirements and may not know the item name of a certain service in the service system, and when searching according to own requirements, the service system cannot retrieve related service information. Therefore, the current search method has the problems that the search result cannot be accurately obtained and the requirement of the user for searching the service cannot be met because the search field is limited to the name and the keyword of the service and the recommendation word built in the system.
Disclosure of Invention
The embodiment of the application provides a service searching method, a device, electronic equipment and a readable storage medium, which can solve the problems that a searching result cannot be accurately obtained and the requirement of a user for searching a service cannot be met because the searched field is limited to the name and the keyword of the service and the recommendation word built in a system.
In a first aspect, an embodiment of the present application provides a service searching method, where the method includes: acquiring preset information and extraction information of each service, wherein the extraction information is obtained by analyzing implicit information of each service; determining alternative services from the preset information and the extracted information according to the service searching requirements of the target user; and displaying the alternative service to the target user.
In a second aspect, an embodiment of the present application provides a service searching apparatus, including: the acquisition module is used for acquiring preset information and extraction information of each service, wherein the extraction information is obtained by analyzing implicit information of each service; the determining module is used for determining alternative services from the preset information and the extracted information according to the service searching requirement of the target user; and the display module is used for displaying the alternative service to the target user.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, and a program or instruction stored on the memory and executable on the processor, the program or instruction implementing the steps of the method according to the first aspect when executed by the processor.
In a fourth aspect, embodiments of the present application provide a readable storage medium having stored thereon a program or instructions which when executed by a processor perform the steps of the method according to the first aspect.
In a fifth aspect, an embodiment of the present application provides a chip, where the chip includes a processor and a communication interface, where the communication interface is coupled to the processor, and where the processor is configured to execute a program or instructions to implement a method according to the first aspect.
In the embodiment of the application, the preset information and the extraction information of each service are obtained by analyzing the implicit information of each service, the extraction information effectively supplements the preset information of each service, enriches the information available for searching the service, and then determines the alternative service from the preset information and the extraction information according to the service searching requirement of a target user; the alternative service is displayed to the target user, the alternative service meeting the service searching requirement of the target user can be accurately searched in combination with the service searching requirement of the target user, and the alternative service is displayed to the target user for the target user to select.
Drawings
Fig. 1 is a schematic flow chart of a service searching method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a service search system according to an embodiment of the present application;
fig. 3 is a schematic flow chart of another service searching method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a service searching device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type, and are not limited to the number of objects, such as the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.
The service searching method, the device, the electronic equipment and the readable storage medium provided by the embodiment of the application are described in detail below through specific embodiments and application scenes thereof with reference to the accompanying drawings.
Fig. 1 shows a flowchart of a service searching method according to an embodiment of the present application, where the method may be performed by an electronic device, and the electronic device may include: a terminal device, wherein the terminal device may be, for example, a vehicle terminal or a mobile phone terminal. Referring to fig. 1, the method may include the steps of:
step 102: acquiring preset information and extraction information of each service, wherein the extraction information is obtained by analyzing implicit information of each service;
the preset information of each service comprises a service name, a keyword and a recommended word, and the preset information is preset by the system. The implicit information of each service comprises evaluation information of each service and reply information of the consultation problem, and the information related to the service is extracted through analysis of the evaluation information of each service and the reply information of the consultation problem, and can also be used as information for determining search service.
Step 104: determining alternative services from the preset information and the extracted information according to the service searching requirements of the target user;
optionally, the service search requirement of the target user may not be completely matched with the service information, and the service search requirement needs to be analyzed to obtain a core meaning expressed by the service search requirement, so that the candidate service is determined from the preset information and the extracted information according to the core meaning, and the searching accuracy is improved.
Step 106: and displaying the alternative service to the target user.
According to the embodiment of the application, the preset information of each service and the extraction information obtained after analyzing the implicit information of each service are obtained, the extraction information effectively supplements the information which can be used for searching the service on the basis of the preset information of each service, enriches the information which can be used for searching the service, then determines the alternative service matched with the service searching requirement of the target user from the preset information and the extraction information according to the service searching requirement of the target user, displays the alternative service to the target user, can accurately search the alternative service meeting the service searching requirement of the target user in combination with the service searching requirement of the target user, and displays the alternative service to the target user for selection by the target user, thereby solving the problem of lack of the information which can be used for searching the service, and meeting the service searching requirement of the target user, and enabling more accurate searching results to be obtained.
In one implementation, the acquiring the extraction information of each service in step 102 may include:
step 1021: word segmentation is carried out on the implicit information through word segmentation functions of natural language processing (Natural Language Processing, NLP) to obtain at least one first information;
in order to improve the efficiency of service searching and facilitate user operation, the search information input by the user is usually expressed in short forms such as characters, words, phrases, etc., while the implicit information, such as evaluation information of each service and reply information of consultation questions, is usually expressed in complex forms such as sentences, long sentences, etc., so when the implicit information is analyzed, the implicit information is segmented for subsequent extraction and use of useful information.
Step 1022: extracting emotion words related to the service from the first information through a text function of natural language processing NLP;
the implicit information, such as the evaluation information of each service and the reply information of the consultation problem, has obvious emotion colors, such as comment on online handling birth certificate, is simple and convenient for my life, needs to run a plurality of departments before and submit a plurality of materials, and is satisfied with the government's convenience for civilian life only by doing one-time handling. The word segmentation obtains online handling, birth proving, convenience, satisfaction and the like, the emotion words in the word segmentation are extracted, the emotion words are convenient and satisfied, the obtained emotion words can be known to express positive evaluation, and the service can be recommended to a user when the user has the requirement of searching the service.
Alternatively, the emotion words in the first information can be judged by comparing the first information with the emotion word dictionary, and emotion words related to the service can be extracted.
Step 1023: extracting entity words related to the service in the first information through a named entity recognition function of natural language processing NLP;
wherein the extracted information includes the emotion word and the entity word. In the implicit information, for example, the evaluation information of each service and the reply information of the consultation problem may include the service used or queried by the user, and according to the above example, entity words related to the service, such as "online handling" and "birth certificate" may be extracted from the first information obtained after word segmentation, where the entity words may not be the same as the names in the preset information, but have the same meaning, and in the case that the user searches using the entity words but not using the preset information, the system may still display the corresponding service that matches the service searching requirement of the user and that exists in the system, without occurrence of no query result.
That is, the preset information of each service generally does not include the emotion words and the entity words, but the user may use the emotion words or the entity words to search for the service, and the extracted information including the emotion words and the entity words is supplemented to the information which can be used for searching for the service, so that the service searching requirement of the user can be more comprehensively met, and the alternative service which meets the service searching requirement of the user can be accurately determined.
In one implementation, the step 104 may include the following steps:
step 1041: analyzing the service searching requirement of the target user through a natural language processing NLP function to obtain target emotion words and target entity words related to target service in the service searching requirement;
optionally, the step 1041 may specifically include:
step 1, word segmentation is carried out on the business search requirement of the target user through the word segmentation function of the natural language processing NLP, and at least one piece of second information is obtained;
step 2, extracting target emotion words related to the target service from the second information through the text function of the natural language processing NLP;
and step 3, extracting target entity words related to the target service from the second information through a named entity recognition function and a synonym divergence function of the natural language processing NLP.
Step 1042: determining a first alternative service from the preset information according to the target emotion words and the target entity words;
step 1043: determining a second alternative service from the extracted information according to the target emotion words and the target entity words; the first alternative service is supplemented through the second alternative service, so that more alternative services are provided for the target user.
Step 1044: and sequencing the first alternative service and the second alternative service according to the historical behavior track of the target user to obtain ordered alternative services.
In the embodiment of the application, after the preset information and the extracted information of each service are obtained, the problem that the preset information and the extracted information of each service are not fully matched with the service searching requirement of a target user may be inconvenient to search from the preset information and the extracted information of each service directly according to the service searching requirement, and the target emotion words and the target entity words related to the target service in the service searching requirement are obtained by analyzing the service searching requirement input by the target user, so that searching is carried out from the preset information and the extracted information of each service according to the target emotion words and the target entity words, wherein the first alternative service is determined from the preset information, and the second alternative service is determined from the extracted information; in order to preferentially display the alternative service which is more matched with the service searching requirement of the target user to the target user, the first alternative service and the second alternative service are ordered according to the historical behavior track of the target user, so that the obtained ordered alternative service is displayed to the target user.
For example, the user searches for "social security payment", the candidate results have an accumulation payment and medical security payment, and the user history behavior track has an accumulation payment, and the weight of the accumulation payment in the candidate results is adjusted so as to be ranked in front in the searched candidate result list.
In one implementation, the historical behavior trace of the target user in step 1044 is obtained by extracting a business review record, a business transaction record, and a business knowledge collection record of the target user.
The method comprises the steps of extracting records of behaviors of a target user such as business consulting, business handling and business knowledge collection, tagging each behavior of the target user to form a tag library of the target user so as to be convenient for calling, and specifically constructing the tag library for the target user through the following steps.
Step 110: the business consulting record, the business handling record and the business knowledge collection record of the target user are segmented through a natural language processing NLP function and a deep learning algorithm to obtain at least one third message;
step 112: extracting labels related to the services in the third information;
step 114: and taking the label as the historical behavior track of the target user.
In the embodiment of the application, the labels related to each service in the service consulting record, the service transacting record and the service knowledge collection record of the target user are extracted, the labels can clearly express the historical behavior track of the target user, and when the alternative services are ordered, the weight of the target user on each alternative service can be determined by consulting the labels in the label library of the target user, so that the alternative services which are more in line with the service searching requirement of the target user are ordered before so as to be convenient for the user to select.
In one implementation, the implicit information includes evaluation information of the respective services and reply information of the consultation questions; after the acquiring the preset information and extracting the information of each service in step 102, the method may further include: establishing an index for the preset information and the extracted information of each service; the index of the preset information comprises the service name, the title, the content feed and the content; the index of the extracted information comprises the service identification, the evaluation information and the reply information of the consultation problem.
In the embodiment of the application, the index is established for the preset information and the extracted information of each service, so that after the user inputs the service searching requirement, the alternative service can be quickly searched and displayed to the user, the searching efficiency is improved, and the user experience is also improved.
Fig. 2 is a schematic structural diagram of a service search system according to an embodiment of the present application. As shown in fig. 2, the system comprises an implicit information docking module 21, an implicit information collecting module 22, a common information collecting module 23, an implicit information analyzing module 24, an information indexing module 25, a user behavior track data docking module 26, a user behavior collecting and labeling module 27, a retrieving module 28, an entity word emotion word library 29, an index library 210 and a user tag library 211.
The implicit information docking module 21 may dock with the answer information interface of the good and bad evaluation and consultation questions mounted on the shared exchange platform through a RESTFul interface, and obtain the answer information of the good and bad evaluation and consultation questions through a timing task scheduling mode, and use the answer information as a front module of the implicit information collecting module 22 to realize docking of the implicit information.
The implicit information collection module 22 can collect related information aiming at the answer information of the good and bad evaluation system and the consultation problem in the business service platform through the implicit information docking module 21, and analyze the related comment information by filtering unnecessary fields and junk data. For example, the parsed content includes: office evaluation and hotline consultation.
The common information collection module 23 can be in a form of docking through a RESTFul interface, and is in a form of docking with a resource library of each service by adopting an http protocol, and the information of each service in the resource library, including service matters, policy titles, policy contents, service lists, service applications and the like, is collected at fixed time through a timing task.
The implicit information analysis module 24 analyzes the information collected by the implicit information collection module 22 through artificial intelligence technology, extracts entity words, emotion words and the like related to each service, and forms an entity word emotion word library 29. The method specifically can segment implicit information through an NPL word segmentation technology, and then compares a word segmentation result with an emotion word dictionary through an NLP text comparison technology to extract emotion words related to a service. And extracting entity words related to the service through an NLP named entity recognition technology.
The information indexing module 25 builds an index for the above general information and the entity words and emotion words extracted according to the implicit information, and constructs an index library 210, so as to facilitate searching. Specifically, the method comprises the following steps of 1, ordinary information index: the content of the index mainly comprises a transaction name, a title, a content feed and content. 2. Entity word index: the content of the index is mainly the entity words and emotion words extracted by the partial implicit information analysis module 24. 3. Implicit information index: the index content is mainly captured hidden information, and the hidden information index content mainly comprises item/policy identification, office evaluation information, hotline consultation reply information and the like. The main present of this index is to provide information by implicit information index when both the normal information index and the entity word index fail to hit.
Alternatively, the index may be established by using an inverted index technique of a search engine, that is, an entry-Document (Term-Doc) index, where Term-Doc is a mapping from Term to Document, and when the relevant functions are processed, such as sorting and highlighting, the corresponding Term value, location information of Term, etc. need to be found through the Document identification, and when a user inputs a Term, a Document containing the Term may be returned.
The user behavior trace data docking module 26 is used for docking with the user behavior trace data interface through the RESTFul interface, and obtaining user behavior trace data through a timing task scheduling mode.
The user behavior collection and labeling module 27 collects the behavior tracks of the user through the user behavior track data docking module 26, and labels the user according to the behavior of the user such as policy consulting, transaction handling, government knowledge collection and the like in the service network, so as to form a user label library 211.
The method comprises the steps of marking a user, carrying out intention understanding and classification and marking on contents through text analysis and a bi-directional encoder representation (Bidirectional Encoder Representation from Transformers, bert) pre-training model of a transformer, carrying out multidimensional analysis and deep intention mining on service contents, and providing favorable conditions for realizing automatic classification under preset rules and recommending search.
Firstly, classifying the text of the business content, and the text can be processed through a multi-layer neural network and a support vector machine. The business content is then represented in a high-dimensional embedded vector by a deep neural network language model. And secondly, performing data cleaning on the processed embedded vector, for example, filtering repeated data to form a behavior model. The behavior tags of each user are then composed of the behavior data in the behavior model described above, stored in the form of a tag tree, e.g., user a, tag class 1: occupation, tag class 2: hobbies; occupational this branch includes the tag: teacher and athlete; preference for this branch includes: lecturing and running; the tag trees of a plurality of users constitute a tag library. In addition, the formation of the tag tree can be realized through an artificial intelligence algorithm, an algorithm marking interface is called through behavior data, the behavior data text is transmitted to an algorithm service, the algorithm service performs word segmentation according to the behavior data text in the current behavior model, matches keywords and tags in the current model according to word segmentation results, extracts tag data conforming to the current matching results, calculates matching scores, filters low-score data not conforming to requirements, and forms a group of tag information which is ordered in reverse order by the matching scores and returns to a tag library. After the tag library receives the current tag array, tag data is matched with the current portrait dimension, and tags conforming to the current dimension are assigned to the corresponding dimension.
For example: the algorithm return label is: and (5) collecting the accumulation fund. After the tag library obtains the tag of the accumulation fund payment, the accumulation fund payment tag is matched through dimension configuration, and if the dimension matching of the current tag is found to be the history transaction, the accumulation fund transaction tag is supplemented in the history transaction information of the current personal tag.
The retrieval module 28 returns the alternative service desired by the user according to the service search requirement entered by the user. Specifically, through the retrieval RESTFul interface of the retrieval module 28, the keywords input by the upper layer application (such as a business service network and a business service mobile terminal) search window user are obtained. 2. And performing word segmentation, analysis and synonym divergence on the user input through NLP text word segmentation, NLP named entity recognition and NLP synonym technology. Extracting the entity words and emotion words in the Chinese language. 3. And searching the service information in each index through the word segmentation result, the entity word and the emotion word in the last step and through an elastic search engine to obtain an alternative result. 4. And screening result data which accords with the user behavior track label from the alternative results by combining with the user behavior track label library, and adjusting the sequencing. For example: and (3) the user searches for social insurance payment, and has the accumulation fund payment and medical insurance payment in the alternative results, and the accumulation fund label is arranged in the user behavior track label library, so that the accumulation fund payment weight in the alternative results is adjusted to be ranked in front in the alternative result list.
Fig. 3 is a flow chart of another service searching method provided by the embodiment of the application, as shown in fig. 3, the method includes the following steps:
step 301: receiving search conditions input by a target user in a service network; for example, "where social security payment queries can be made";
step 302: word segmentation is carried out on the search conditions, and target entity words are extracted; the words are segmented to obtain 'where social security payment inquiry can be carried out', core words 'social security', divergent synonyms 'social insurance' and the like are analyzed, and entity words 'social security payment inquiry' are extracted.
Step 303: retrieving from the common information index according to the target entity word to obtain a first alternative result; such as "social insurance payment" business.
Step 304: retrieving from the entity word index according to the target entity word to obtain a second alternative result; such as "social premium payment (town enterprise employee)" business.
Step 305: retrieving from the implicit information index according to the target entity word to obtain a third alternative result; for example, the transaction items which can be handled on line, such as the accumulation fund payment, the medical insurance payment and the like, are searched from the implicit information.
Step 306: sorting the first alternative result, the second alternative result and the third alternative result by combining with the behavior track labels in the user label library, and returning the sorted results to the target user; wherein the ranking of the alternative results that meet the target user behavior label is advanced. For example, the real intention of the target user is to inquire about the accumulation fund payment, the user inputs the search condition 'where the user can make social security payment inquiry', the candidate data obtained in the previous three steps has social insurance payment, medical security payment, accumulation fund payment and other matters, the history matters in the user behavior track label are combined to handle the accumulation fund payment label, and the sorting weight of the accumulation fund payment matters in the candidate result is adjusted to be sorted into the first one.
The embodiment of the application solves the problems that the user searches service data inaccurately and cannot identify the searching intention, does not search only for a few fields such as service names, keywords and the like, extracts core keywords such as entity words, emotion words and the like in implicit information of evaluation feedback data of the user, indexes the words, provides a searching function, marks the user according to the behavior track of the individual and enterprise users in a service network, combines the user labels, filters the searched alternative results, optimizes the ordering of the alternative results, improves the service searching efficiency and accuracy, is more convenient for the user to search service and conduct service handling, and improves the user experience.
It should be noted that, in the service searching method provided by the embodiment of the present application, the execution body may be a service searching device, or a control module in the service searching device for executing the service searching method. In the embodiment of the application, a service searching device is taken as an example to execute a service searching method.
Fig. 4 is a schematic structural diagram of a service searching device according to an embodiment of the present application. As shown in fig. 4, the apparatus 400 includes: an acquisition module 41, a determination module 42 and a presentation module 43.
The acquiring module 41 is configured to acquire preset information and extracted information of each service, where the extracted information is obtained by analyzing implicit information of each service; a determining module 42, configured to determine an alternative service from the preset information and the extracted information according to a service search requirement of a target user; and the display module 43 is configured to display the alternative service to the target user.
In one implementation manner, the obtaining module 41 may be configured to perform word segmentation on the implicit information through a word segmentation function of the natural language processing NLP to obtain at least one first information; extracting emotion words related to the service from the first information through a text function of natural language processing NLP; extracting entity words related to the service in the first information through a named entity recognition function of natural language processing NLP; wherein the extracted information includes the emotion word and the entity word.
In one implementation manner, the determining module 42 may be configured to analyze, through a natural language processing NLP function, a service search requirement of the target user to obtain a target emotion word and a target entity word related to a target service in the service search requirement; determining a first alternative service from the preset information according to the target emotion words and the target entity words; determining a second alternative service from the extracted information according to the target emotion words and the target entity words; and sequencing the first alternative service and the second alternative service according to the historical behavior track of the target user to obtain ordered alternative services.
In one implementation manner, the determining module 42 analyzes the service search requirement of the target user through the natural language processing NLP function to obtain the target emotion word and the target entity word related to the target service in the service search requirement, which may include:
the word segmentation function of the natural language processing NLP is used for segmenting the business search requirement of the target user to obtain at least one piece of second information; extracting target emotion words related to the target service from the second information through the text function of the natural language processing NLP; and extracting target entity words related to the target service from the second information through a named entity recognition function and a synonym divergence function of the natural language processing NLP.
In one implementation, the historical behavior trace of the target user in the determining module 42 is obtained by extracting a business review record, a business transaction record, and a business knowledge collection record of the target user.
In one implementation, the extracting the business review record, the business transaction record, and the business knowledge collection record of the target user in the determining module 42 may include: the business consulting record, the business handling record and the business knowledge collection record of the target user are segmented through a natural language processing NLP function and a deep learning algorithm to obtain at least one third message; extracting labels related to the services in the third information; and taking the label as the historical behavior track of the target user.
In one implementation manner, the service searching apparatus 400 may further include a marking module, configured to set up an index for the preset information and the extracted information of each service; the index of the preset information comprises the service name, the title, the content feed and the content; the index of the extracted information comprises the service identification, the evaluation information and the reply information of the consultation problem.
The service searching device in the embodiment of the application can be a device, and can also be a component, an integrated circuit or a chip in the terminal. The apparatus may be a mobile electronic device, for example, a mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (um-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), and the non-mobile electronic device may be a personal computer (personal computer, PC), a Television (TV), a teller machine or a self-service machine, and the embodiment of the present application is not limited specifically.
The service searching device in the embodiment of the application can be a device with an operating system. The operating system may be an Android operating system, an ios operating system, or other possible operating systems, and the embodiment of the present application is not limited specifically.
The service searching device provided by the embodiment of the present application can implement each process implemented in the method embodiment of fig. 1 or fig. 3, and in order to avoid repetition, a description is omitted here.
Based on the same technical concept, the embodiment of the application also provides an electronic device, which is used for executing the service searching method, and fig. 5 is a schematic structural diagram of an electronic device for implementing the embodiments of the application. The electronic device may have a relatively large difference due to different configurations or performances, and may include a processor (processor) 501, a communication interface (Communications Interface) 502, a memory (memory) 503, and a communication bus 504, where the processor 501, the communication interface 502, and the memory 503 complete communication with each other through the communication bus 504. The processor 501 may call a computer program stored on the memory 503 and executable on the processor 501 to perform the steps of:
acquiring preset information and extraction information of each service, wherein the extraction information is obtained by analyzing implicit information of each service; determining alternative services from the preset information and the extracted information according to the service searching requirements of the target user; and displaying the alternative service to the target user.
The specific implementation steps can refer to the steps of the signal abnormality detection method embodiment, and the same technical effects can be achieved, so that repetition is avoided, and details are not repeated here.
It should be noted that, the electronic device in the embodiment of the present application includes: a terminal or other device besides a terminal.
The above electronic device structure does not constitute a limitation of the electronic device, and the electronic device may include more or less components than illustrated, or may combine some components, or may be different in arrangement of components, for example, an input unit, may include a graphics processor (Graphics Processing Unit, GPU) and a microphone, and a display unit may configure a display panel in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit includes at least one of a touch panel and other input devices. Touch panels are also known as touch screens. Other input devices may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and so forth, which are not described in detail herein.
The memory may be used to store software programs as well as various data. The memory may mainly include a first memory area storing programs or instructions and a second memory area storing data, wherein the first memory area may store an operating system, application programs or instructions (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like. Further, the memory may include volatile memory or nonvolatile memory, or the memory may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM), static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (ddr SDRAM), enhanced SDRAM (Enhanced SDRAM), synchronous DRAM (SLDRAM), and Direct RAM (DRRAM).
The processor may include one or more processing units; optionally, the processor integrates an application processor that primarily processes operations involving an operating system, user interface, application programs, and the like, and a modem processor that primarily processes wireless communication signals, such as a baseband processor. It will be appreciated that the modem processor described above may not be integrated into the processor.
The embodiment of the application also provides a readable storage medium, on which a program or an instruction is stored, which when executed by a processor, implements each process of the above-mentioned service searching method embodiment, and can achieve the same technical effects, and in order to avoid repetition, the description is omitted here.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium such as a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.
The embodiment of the application further provides a chip, which comprises a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used for running programs or instructions to realize the processes of the above service searching method embodiment, and can achieve the same technical effects, so that repetition is avoided, and the description is omitted here.
It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are to be protected by the present application.
Claims (9)
1. A business searching method, comprising:
acquiring preset information and extraction information of each service, wherein the extraction information is obtained by analyzing implicit information of each service;
determining alternative services from the preset information and the extracted information according to the service searching requirements of the target user;
displaying the alternative service to the target user;
the obtaining the extraction information of each service includes:
word segmentation is carried out on the implicit information through a word segmentation function of natural language processing NLP, so that at least one piece of first information is obtained;
extracting emotion words related to the service from the first information through a text function of natural language processing NLP;
extracting entity words related to the service in the first information through a named entity recognition function of natural language processing NLP;
wherein the extracted information includes the emotion word and the entity word.
2. The method of claim 1, wherein determining the alternative service from the preset information and the extracted information according to the service search requirement of the target user comprises:
analyzing the service searching requirement of the target user through a natural language processing NLP function to obtain target emotion words and target entity words related to target service in the service searching requirement;
determining a first alternative service from the preset information according to the target emotion words and the target entity words;
determining a second alternative service from the extracted information according to the target emotion words and the target entity words;
and sequencing the first alternative service and the second alternative service according to the historical behavior track of the target user to obtain ordered alternative services.
3. The method according to claim 2, wherein the analyzing, by the natural language processing NLP function, the service search requirement of the target user to obtain the target emotion word and the target entity word related to the target service in the service search requirement includes:
the word segmentation function of the natural language processing NLP is used for segmenting the business search requirement of the target user to obtain at least one piece of second information;
extracting target emotion words related to the target service from the second information through the text function of the natural language processing NLP;
and extracting target entity words related to the target service from the second information through a named entity recognition function and a synonym divergence function of the natural language processing NLP.
4. The method of claim 2, wherein the historical behavior trace of the target user is extracted from business consulting records, business handling records, and business knowledge collection records of the target user.
5. The method of claim 4, wherein the extracting by extracting the business review record, business transaction record, and business knowledge collection record of the target user comprises:
the business consulting record, the business handling record and the business knowledge collection record of the target user are segmented through a natural language processing NLP function and a deep learning algorithm to obtain at least one third message;
extracting labels related to the services in the third information;
and taking the label as the historical behavior track of the target user.
6. The method of claim 1, wherein the implicit information includes evaluation information for the respective services and reply information to the consultation questions; after the preset information and the extracted information of each service are obtained, the method further comprises the following steps:
establishing an index for the preset information and the extracted information of each service;
the index of the preset information comprises a service name, a title, a content feed and content; the index of the extracted information comprises service identification, evaluation information and reply information of the consultation questions.
7. A traffic search device, comprising:
the acquisition module is used for acquiring preset information and extraction information of each service, wherein the extraction information is obtained by analyzing implicit information of each service;
the determining module is used for determining alternative services from the preset information and the extracted information according to the service searching requirement of the target user;
the display module is used for displaying the alternative service to the target user;
the obtaining the extraction information of each service includes:
word segmentation is carried out on the implicit information through a word segmentation function of natural language processing NLP, so that at least one piece of first information is obtained;
extracting emotion words related to the service from the first information through a text function of natural language processing NLP;
extracting entity words related to the service in the first information through a named entity recognition function of natural language processing NLP;
wherein the extracted information includes the emotion word and the entity word.
8. An electronic device comprising a processor, a memory and a program or instruction stored on the memory and executable on the processor, which when executed by the processor implements the steps of the business search method of any one of claims 1 to 6.
9. A readable storage medium, characterized in that the readable storage medium has stored thereon a program or instructions which, when executed by a processor, implement the steps of the service search method according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311065041.4A CN116775813B (en) | 2023-08-23 | 2023-08-23 | Service searching method, device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311065041.4A CN116775813B (en) | 2023-08-23 | 2023-08-23 | Service searching method, device, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116775813A CN116775813A (en) | 2023-09-19 |
| CN116775813B true CN116775813B (en) | 2023-11-24 |
Family
ID=87989880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311065041.4A Active CN116775813B (en) | 2023-08-23 | 2023-08-23 | Service searching method, device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116775813B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191133A (en) * | 2019-12-31 | 2020-05-22 | 口口相传(北京)网络技术有限公司 | Service search processing method, device and equipment |
| CN111859154A (en) * | 2020-07-06 | 2020-10-30 | 中国银行股份有限公司 | Application recommendation method and device |
| CN112733024A (en) * | 2021-01-05 | 2021-04-30 | 北京三快在线科技有限公司 | Information recommendation method and device |
| CN112765974A (en) * | 2021-01-19 | 2021-05-07 | 海尔数字科技(北京)有限公司 | Service assisting method, electronic device and readable storage medium |
| CN114330329A (en) * | 2021-12-23 | 2022-04-12 | 广东太平洋互联网信息服务有限公司 | Service content searching method and device, electronic equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7475059B2 (en) * | 2003-02-13 | 2009-01-06 | Sap Ag | Adapting business objects for searches and searching adapted business objects |
| US10417649B2 (en) * | 2012-09-28 | 2019-09-17 | Oracle International Corporation | Business process global searching |
-
2023
- 2023-08-23 CN CN202311065041.4A patent/CN116775813B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191133A (en) * | 2019-12-31 | 2020-05-22 | 口口相传(北京)网络技术有限公司 | Service search processing method, device and equipment |
| CN111859154A (en) * | 2020-07-06 | 2020-10-30 | 中国银行股份有限公司 | Application recommendation method and device |
| CN112733024A (en) * | 2021-01-05 | 2021-04-30 | 北京三快在线科技有限公司 | Information recommendation method and device |
| CN112765974A (en) * | 2021-01-19 | 2021-05-07 | 海尔数字科技(北京)有限公司 | Service assisting method, electronic device and readable storage medium |
| CN114330329A (en) * | 2021-12-23 | 2022-04-12 | 广东太平洋互联网信息服务有限公司 | Service content searching method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116775813A (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112632385B (en) | Course recommendation method, course recommendation device, computer equipment and medium | |
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| CN105824959B (en) | Public opinion monitoring method and system | |
| US8549016B2 (en) | System and method for providing robust topic identification in social indexes | |
| CN103514299B (en) | Information search method and device | |
| CN111144723A (en) | Method and system for recommending people's job matching and storage medium | |
| CN111324771B (en) | Video tag determination method and device, electronic equipment and storage medium | |
| US11023503B2 (en) | Suggesting text in an electronic document | |
| US20210103622A1 (en) | Information search method, device, apparatus and computer-readable medium | |
| US20190377824A1 (en) | Schemaless systems and methods for automatically building and utilizing a chatbot knowledge base or the like | |
| CN110941702A (en) | Retrieval method and device for laws and regulations and laws and readable storage medium | |
| CN111881283A (en) | Business keyword library creating method, intelligent chat guiding method and device | |
| CN112182145A (en) | Text similarity determination method, device, equipment and storage medium | |
| Puccetti et al. | Technology identification from patent texts: A novel named entity recognition method | |
| CN111782793A (en) | Intelligent customer service processing method, system and equipment | |
| CN111310065A (en) | Social contact recommendation method and device, server and storage medium | |
| CN110647504B (en) | Method and device for searching judicial documents | |
| CN112307314A (en) | Method and device for generating fine selection abstract of search engine | |
| KR20200064490A (en) | Server and method for automatically generating profile | |
| Wei et al. | Online education recommendation model based on user behavior data analysis | |
| Walha et al. | A Lexicon approach to multidimensional analysis of tweets opinion | |
| CN116775813B (en) | Service searching method, device, electronic equipment and readable storage medium | |
| CN113792230B (en) | Service linking method, device, electronic equipment and storage medium | |
| CN113988057A (en) | Title generation method, device, equipment and medium based on concept extraction | |
| CN113870998A (en) | Interrogation method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |