Operation and maintenance expert recommendation method and device and processing equipment

Abstract

The invention provides an operation and maintenance expert recommendation method, an operation and maintenance expert recommendation device and processing equipment, which are used for specifically considering the expert knowledge distribution adaptation degree, the patent consultation question interestingness, the expert social relationship and the expert state in the matching process under the condition that an automatic matching mechanism is introduced to match operation and maintenance experts suitable for recommendation. In this way, the adaptability of the recommended operation and maintenance experts and the current situation is further improved, it can be guaranteed that the operation and maintenance experts which are adaptive and can quickly provide help can be recommended in the first time, the operation and maintenance work of enterprises can be promoted to be stably and efficiently promoted, and a good foundation is provided for operation of the enterprises.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device and processing equipment for recommending operation and maintenance experts. Background Art

[0002] As enterprises invest in more and more equipment, the corresponding operation and maintenance work becomes more and more complicated. In order to ensure production operations, many enterprises have transferred operation and maintenance services to professional companies to improve the quality of equipment maintenance and ensure the normal operation of the system.

[0003] However, a professional operation and maintenance personnel needs to rely on the accumulation of experience and the precipitation of time to easily cope with related operation and maintenance work. When some operation and maintenance personnel who lack practical experience encounter difficulties, if they only rely on the company's knowledge base to retrieve relevant information, they cannot solve the problem quickly. Therefore, many times the company needs a group of operation and maintenance experts with relevant knowledge and experience to guide these inexperienced employees so that they can solve problems in their work in a timely manner.

[0004] The inventors of the present application have discovered that, excluding the situation where the enterprise has pre-designated specific operation and maintenance experts for help, the traditional way of seeking help from operation and maintenance experts is done manually, that is, the operation and maintenance personnel themselves have to find suitable operation and maintenance experts. This method is obviously not only unscientific but also time-consuming. Therefore, how to quickly find suitable operation and maintenance experts to solve current operation and maintenance problems is a problem that needs to be solved in the enterprise's operation and maintenance work. Summary of the invention

[0005] The present application provides an operation and maintenance expert recommendation method, apparatus and processing equipment, which are used to introduce an automatic matching mechanism to match operation and maintenance experts suitable for recommendation. In the matching process, four aspects are specifically considered, namely, the adaptability of expert knowledge distribution, the interest in patent consultation questions, the social relations of experts and the status of experts. In this way, the adaptability of the recommended operation and maintenance experts to the current situation is further improved, and it can be ensured that operation and maintenance experts who are suitable and can quickly provide effective help are recommended in the first time, so that the enterprise operation and maintenance work can be carried out stably and efficiently, providing a good foundation for the operation of the enterprise.

[0006] In a first aspect, the present application provides an operation and maintenance expert recommendation method, the method comprising:

[0007] Obtaining an operation and maintenance expert consultation request initiated by the user, wherein the operation and maintenance expert consultation request is used to consult an operation and maintenance expert suitable for the task currently being performed by the user;

[0008] Mining and processing the user needs behind the operation and maintenance expert consultation requests to determine the target user needs;

[0009] Based on the needs of target users, the operation and maintenance expert adaptation process is carried out to obtain the quantitative results of the fitness scores of different operation and maintenance experts in the operation and maintenance expert database. Among them, the operation and maintenance expert adaptation process takes into account the fitness of expert knowledge distribution, the interest of patent consultation issues, the social relationship of experts and the status of experts;

[0010] Determine a target operation and maintenance expert based on the quantified results of the fitness scores of different operation and maintenance experts, wherein the number of the target operation and maintenance experts is at least one;

[0011] Push the operation and maintenance expert recommendation information of the target operation and maintenance expert to the user end.

[0012] In a second aspect, the present application provides an operation and maintenance expert recommendation device, the device comprising:

[0013] An acquisition unit, used to acquire an operation and maintenance expert consultation request initiated by a user terminal, wherein the operation and maintenance expert consultation request is used to consult an operation and maintenance expert suitable for the task currently being performed by the user;

[0014] A determination unit is used to mine and process the user needs behind the operation and maintenance expert consultation request to determine the target user needs;

[0015] The adaptation unit is used to carry out operation and maintenance expert adaptation processing based on the needs of target users, and obtain the quantitative results of the fitness scores of different operation and maintenance experts in the operation and maintenance expert database. The operation and maintenance expert adaptation processing considers the fitness of expert knowledge distribution, the interest of patent consultation issues, the social relationship of experts and the status of experts;

[0016] The determination unit is further used to determine a target operation and maintenance expert based on the quantified results of the fitness scores of different operation and maintenance experts, wherein the number of the target operation and maintenance experts is at least one;

[0017] The push unit is used to push the operation and maintenance expert recommendation information of the target operation and maintenance expert to the user end.

[0018] In a third aspect, the present application provides a processing device, including a processor and a memory, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the method provided in the first aspect of the present application or any possible implementation method of the first aspect of the present application is executed.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, which stores multiple instructions, and the instructions are suitable for a processor to load to execute the method provided by the first aspect of the present application or any possible implementation of the first aspect of the present application.

[0020] From the above content, it can be concluded that the present application has the following beneficial effects:

[0021] With regard to the goal of intelligent recommendation of operation and maintenance experts, this application introduces an automatic matching mechanism to match operation and maintenance experts suitable for recommendation. In the matching process, four aspects are also specifically considered, namely, the adaptability of expert knowledge distribution, the interest in patent consultation issues, the social relations of experts and the status of experts. This further improves the adaptability of the recommended operation and maintenance experts to the current situation, and can ensure that operation and maintenance experts who are suitable and can quickly provide effective help are recommended in the first time, so that the enterprise's operation and maintenance work can be carried out stably and efficiently, providing a good foundation for the operation of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A flowchart of the method recommended by the operation and maintenance experts for this application;

[0024] Figure 2 A schematic diagram of a scenario of social relations for this application;

[0025] Figure 3 A schematic diagram of a scenario for the overall solution of this application;

[0026] Figure 4 This is another scenario diagram of the overall solution of this application;

[0027] Figure 5 This is a structural diagram of a device recommended by the operation and maintenance experts for this application;

[0028] Figure 6 A schematic diagram of the structure of the processing equipment of this application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0030] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0031] The division of modules in this application is a logical division. There may be other division methods when it is implemented in actual applications. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between modules can be electrical or other similar forms, which are not limited in this application. In addition, the modules or submodules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in multiple circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the present application.

[0032] Before introducing the operation and maintenance expert recommendation method provided by this application, the background content involved in this application is first introduced.

[0033] The operation and maintenance expert recommendation method, device and computer-readable storage medium provided in the present application can be applied to processing equipment. When an automatic matching mechanism is introduced to match operation and maintenance experts suitable for recommendation, the matching process also specifically considers four aspects: the adaptability of expert knowledge distribution, the interest in patent consultation issues, the social relations of experts and the status of experts. In this way, the adaptability of the recommended operation and maintenance experts to the current situation is further improved, and it can be ensured that operation and maintenance experts who are suitable and can quickly provide effective help are recommended at the first time, so that the enterprise's operation and maintenance work can be carried out stably and efficiently, providing a good foundation for the operation of the enterprise.

[0034] The operation and maintenance expert recommendation method mentioned in this application can be executed by an operation and maintenance expert recommendation device, or a server, physical host or user equipment (UE) and other different types of processing equipment integrated with the operation and maintenance expert recommendation device. The operation and maintenance expert recommendation device can be implemented in hardware or software, and the UE can be a terminal device such as a smart phone, tablet computer, laptop computer, desktop computer or personal digital assistant (PDA), and the operation and maintenance expert recommendation processing device can be set in the form of a device cluster.

[0035] It can be understood that the processing equipment that executes the method recommended by the operation and maintenance experts of this application, or the processing equipment equipped with the application service corresponding to the method recommended by the operation and maintenance experts of this application, is usually a server deployed in the internal network architecture of the enterprise in actual applications. Of course, corresponding to flexible and changeable application requirements, it can also be configured as a physical host or even UE and other types of devices. These are also possible in actual situations. Therefore, this application does not make specific restrictions on the specific device type and device deployment form of the processing equipment, and can meet the operation and maintenance expert recommendation requirements of the user-side operation and maintenance personnel.

[0036] Next, we will introduce the operation and maintenance expert recommendation method provided by this application.

[0037] First, see Figure 1 , Figure 1 A flow chart of the operation and maintenance expert recommendation method of the present application is shown. The operation and maintenance expert recommendation method provided by the present application may specifically include the following steps S101 to S105:

[0038] Step S101, obtaining an operation and maintenance expert consultation request initiated by a user terminal, wherein the operation and maintenance expert consultation request is used to consult an operation and maintenance expert suitable for the task currently being performed by the user;

[0039] It can be understood that for operation and maintenance personnel or even other personnel who have a need for operation and maintenance expert recommendation, they can initiate a corresponding operation and maintenance expert consultation request to the operation and maintenance expert recommendation system involved in this application through the user end (device on the user side, such as a physical host or UE and other devices). The operation and maintenance expert consultation request directly / indirectly indicates the current task performed by the user-side personnel, and is also used to request consultation with an operation and maintenance expert suitable for the current task performed by the user.

[0040] Among them, the operation and maintenance expert recommendation system can be configured in the form of an independent system or embedded in other systems. In addition, it can be configured in the form of an independent device or integrated with other hardware devices. These two aspects are not contradictory.

[0041] In addition, in some cases, in addition to manually initiating an operation and maintenance expert consultation request by relevant personnel on the user side, the user side can also initiate an operation and maintenance expert consultation request through a preset autonomous initiation strategy, so that when the user side determines through relevant condition indicators that there is a need for an operation and maintenance expert recommendation for the current operation and maintenance work, or when the user side receives a relevant operation and maintenance expert consultation request initiation instruction, an operation and maintenance expert consultation request is initiated autonomously, thereby facilitating timely obtaining the help of an adapted target operation and maintenance expert.

[0042] In addition, the acquisition and processing of the operation and maintenance expert consultation request here can be either directly received from the user end, or sent from the user end to other devices and then forwarded by other devices. These are all possible.

[0043] Step S102, mining the user needs behind the operation and maintenance expert consultation request to determine the target user needs;

[0044] It can be understood that in order to achieve a more convenient and higher-precision operation and maintenance expert adaptation effect, this application does not directly carry out operation and maintenance expert adaptation processing based on the operation and maintenance expert consultation request obtained previously, but requires further processing of the operation and maintenance expert consultation request to dig out the deep-seated user needs behind the request, so that high-precision operation and maintenance expert matching processing can be efficiently carried out based on more delicate target user needs.

[0045] Specifically, the mining of user needs is to capture the real needs of users, which corresponds to the following situations that may frequently occur in actual situations:

[0046] An employee who is maintaining server equipment enters "power failure" in the expert consultation system, but is recommended an expert who is familiar with switch power failure handling to answer questions. Although it is the same power failure, the power maintenance process of switches and servers is different, so the consultation effect will not be satisfactory. The main reason for this situation is that the problem description entered by the user is too short, and the system cannot clearly identify the user's precise intention, and may even cause ambiguity in the user's needs. If the user is required to describe the consultation problem in detail, it will affect the user's experience.

[0047] In this way, by exploring and understanding user needs, we can avoid the impact of ambiguity or unclear situations caused by brief operation and maintenance expert consultation requests. At the same time, it is also to locate clearer and more accurate user needs for subsequent operation and maintenance expert matching and processing.

[0048] Step S103, based on the needs of the target users, the operation and maintenance expert adaptation process is carried out to obtain the quantitative results of the fitness scores of different operation and maintenance experts in the operation and maintenance expert database, wherein the operation and maintenance expert adaptation process takes into account the fitness of expert knowledge distribution, the interest of patent consultation questions, the social relationship of experts and the status of experts;

[0049] After digging out the target user needs of the user end for recommending adaptive operation and maintenance experts in the current situation, it is easy to understand that the operation and maintenance expert adaptation processing designed in this application can be carried out based on the target user needs.

[0050] Among them, it should be noted that this application specially designs a set of operation and maintenance expert adaptation processing mechanism, which specifically involves the influencing dimensions of expert knowledge distribution adaptation, patent consultation question interest, expert social relations and expert status. In this way, starting from different dimensions, it can better quantify the matching degree between different operation and maintenance experts and the target user needs of the current user end under the current situation, and complete the clear quantification with the final calculated score, namely the adaptation score.

[0051] Step S104, determining a target operation and maintenance expert based on the quantified results of the fitness scores of different operation and maintenance experts, wherein the number of the target operation and maintenance experts is at least one;

[0052] After quantifying the degree of fit between different operation and maintenance experts and the current operation and maintenance work assistance situation through the fit score, it can be understood that screening can be performed to determine the target operation and maintenance expert for final recommendation.

[0053] It can be understood that in the processing link here, when the degree of suitability has been clearly quantified through the score, one or more target operation and maintenance experts can usually be selected from them for specific recommendation based on the score ranking (for example, it can be set in the form of an expert recommendation list / expert ranking list).

[0054] As an example, the number of target operation and maintenance experts may preferably be set to 5.

[0055] Of course, in addition to 5, it can also be other quantities, which can be adjusted according to actual needs.

[0056] Step S105: Pushing the operation and maintenance expert recommendation information of the target operation and maintenance expert to the user terminal.

[0057] After the target operation and maintenance expert for recommendation is determined, it can obviously be pushed to the user end. In the push link, the operation and maintenance expert recommendation information is specifically pushed.

[0058] It is understandable that, for the user-side recommendation processing for users, there may be different recommendation processing methods in actual situations. Correspondingly, the operation and maintenance expert recommendation information of the target operation and maintenance expert pushed to the user side can be adaptively adjusted.

[0059] For example, the operation and maintenance expert recommendation information may indicate that the user terminal may recommend a target operation and maintenance expert in a recommendation program, or directly control the user terminal to initiate a recommendation process of a target operation and maintenance expert.

[0060] from Figure 1 It can be seen from the illustrated embodiments that, with respect to the goal of intelligently recommending operation and maintenance experts, the present application, while introducing an automatic matching mechanism to match operation and maintenance experts suitable for recommendation, also specifically considers four aspects during the matching process, namely, the adaptability of expert knowledge distribution, the interest in patent consultation questions, the social relations of experts, and the status of experts. This further improves the adaptability of the recommended operation and maintenance experts to the current situation, and can ensure that operation and maintenance experts who are suitable and can quickly provide effective help are recommended at the first time, thereby enabling the enterprise's operation and maintenance work to be carried out stably and efficiently, providing a good foundation for the operation of the enterprise.

[0061] Continue to the above Figure 1 Each step of the illustrated embodiment and possible implementation methods thereof in practical applications are described in detail.

[0062] As an exemplary embodiment, step S102 mines the user needs behind the operation and maintenance expert consultation request to determine the target user needs, which may specifically include:

[0063] (1) The task content and consultation description of the operation and maintenance expert consultation request are combined into a demand vector;

[0064] It can be understood that in order to facilitate subsequent operation and maintenance expert adaptation processing, the present application can specifically process the input data in the form of vectors.

[0065] With this in mind, the task content and consulting description of the operation and maintenance expert consulting request obtained earlier can be combined into a demand vector.

[0066] It should be noted that the vector processing here not only focuses on the consultation description of the operation and maintenance expert consultation request, but also pays attention to the task content of the user's current task / operation and maintenance task corresponding to the operation and maintenance expert consultation request itself or the user end. This can cover more detailed condition content and obtain more complete and rich vector content, which helps to promote better processing accuracy.

[0067] Among them, since the user's current task can be automatically obtained from the system records such as system operation and maintenance task orders, the filling content of the operation and maintenance expert consultation request can be greatly simplified, and it can also help to deeply understand the user's needs.

[0068] (2) Perform word segmentation processing on the demand vector to obtain the word segmentation processing result;

[0069] After obtaining the initial demand vector, the word segmentation tool can be used to continue the word segmentation process, and the multiple words obtained by splitting form the word segmentation process result.

[0070] (3) Remove stop words and common words from the word segmentation results, and continue to extract noun entities to obtain noun entity extraction results;

[0071] After obtaining the word segmentation results, we can continue to remove stop words and common words (both are two types of words in information retrieval work and belong to existing terminology) to omit meaningless words for understanding user needs and achieve a simplification effect on the content.

[0072] Then, noun entities are further extracted from the processing results after removing stop words and common words to obtain noun entity extraction results.

[0073] (4) Reorganize the noun entity extraction results into a consultation vector Q.

[0074] It can be understood that there are usually multiple noun entities extracted. At this time, these noun entities can be reorganized to form a consultation vector Q. The consultation vector Q obtained through a series of processing in the embodiment here can conveniently carry out subsequent operation and maintenance expert adaptation processing.

[0075] Next, a more specific description of the scheme settings will be given for the impact dimensions of several aspects involved in the operation and maintenance expert adaptation process specially designed for this application.

[0076] It is understandable that the inventors of the present application have found that the existing expert recommendation methods in other scenarios are all content-based expert recommendation methods, which use expert resume information as the basis for mining expert knowledge domain features and characterize expert features through TF-IDF weighted vector space.

[0077] However, on the one hand, the professional knowledge and experience of experts will grow and change over time, while the resume documents in the expert database are not updated every day, which makes it impossible for the system to grasp the changes in the characteristics of the expert's knowledge field in a timely manner; on the other hand, the TF-IDF weighted vector space method ignores the semantics of feature words. When a word with semantics similar to the expert's feature word is used as a query condition, the system cannot accurately locate the expert.

[0078] In this case, as an exemplary embodiment of the present application, corresponding to the expert knowledge distribution adaptability, the method of the present application may further include:

[0079] (1) Segment the expert operation and maintenance record documents of different operation and maintenance experts, remove stop words and common words, and then assign a unique identifier to each word in the document processing results to form a vocabulary;

[0080] It is understandable that operation and maintenance experts usually participate in the operation and maintenance work of the enterprise, and the corresponding operation and maintenance records (expert operation and maintenance record documents) are the materials that expert employees need to submit after each work is completed. This file can be considered as the most suitable supporting document for mining the knowledge distribution of enterprise experts.

[0081] Among them, this document is directly used as a supporting document. This application believes that there may be noise. Because in real scenarios, some operation and maintenance experts may participate in equipment maintenance work, but they may not be able to complete the maintenance work well due to their own lack of ability. Therefore, in specific operations, only positive evaluation content can be extracted.

[0082] After obtaining the expert operation and maintenance record documents of different operation and maintenance experts, they can be simplified by removing the stop words and common words involved. The settings here are similar to those introduced above.

[0083] After simplification, a globally unique identifier (which can be recorded as wordid) can be assigned to each word in the document to form a vocabulary that can be used later.

[0084] (2) After setting the initial parameters of the LDA model and setting the number of topics to 20, based on the document processing results and the vocabulary, the LDA model is called to use the Gibbs sampling algorithm to obtain the topic word list and document topic mapping table;

[0085] Among them, the LDA model, namely the Latent Dirichlet Allocation topic model, is a document body generation model. Considering that this application does not make corresponding improvements to the LDA model itself and focuses on the application of the model, the LDA model itself will not be explained in detail here.

[0086] It can be seen that this application involves the application of the LDA model, which is combined with the Gibbs sampling algorithm (an existing sampling algorithm), so that the subject word list (topic-word list) and the document topic mapping table (document-topic mapping table) are extracted from the document processing results and vocabulary obtained previously.

[0087] (3) Analyze the keyword list and the document topic mapping table to obtain an expert topic mapping table, where the expert topic mapping table identifies the knowledge distribution of different operation and maintenance experts as a topic vector Etopic.

[0088] It can be understood that the keyword list and document topic mapping table extracted by the LDA model above both reflect the relationship between experts and documents. Therefore, the relationship can be analyzed and processed to obtain an expert topic mapping table (expert-topic mapping table). Through the expert topic mapping table, the knowledge distribution of each operation and maintenance expert can be represented by a topic vector Etopic. In this way, the knowledge distribution vector representation method can be used to simply and clearly present the knowledge distribution of the operation and maintenance experts, laying a good application foundation / condition for subsequent matching processing.

[0089] In addition, on another aspect, as an exemplary embodiment of the present application, in terms of the interest level of patent consulting questions, the present application method may further include:

[0090] (1) Obtain feedback from different operation and maintenance experts on historical consulting issues;

[0091] (2) Based on the feedback information, an expert interest matrix is ​​constructed using three types of responses, namely, no response, response with low user rating, and response with high-quality user rating, as distinctions. The expert interest matrix identifies the interest of different operation and maintenance experts in different consulting questions.

[0092] It can be understood that in actual situations, this application believes that when a consulting question is sent to an operation and maintenance expert, the expert will usually have three types of response behaviors: 1. No response; 2. Low-quality response; 3. High-quality response. In this case, these response behaviors are used to express the expert's interest in the consulting question.

[0093] Under the design here, the response behavior of the operation and maintenance experts can be sorted out from the feedback information of the operation and maintenance experts on historical consulting issues (such as consulting information and consulting evaluation information). Low-quality responses and high-quality responses can be distinguished by the corresponding user ratings. When the user rating is greater than 8 points (out of 10 points), it can be considered a high-quality response, otherwise it is a low-quality response, and finally an expert interest matrix (expert-consulting interest matrix) is formed. Subsequently, based on the expert interest matrix, the collaborative filtering method can be used to analyze the expert's interest in the current consulting issue.

[0094] In addition, in another aspect, as an exemplary embodiment of the present application, corresponding to the social relationship of experts, the method of the present application may also include:

[0095] Based on the user department information, department address information and participant information of the operation and maintenance records, the social relationships between different operation and maintenance experts and different users are quantified, and the social relationship quantification results are stored in the expert user relationship table, which identifies the relationship intimacy between different operation and maintenance experts and different users.

[0096] It is understandable that the present application believes that in real life, people may be more willing to help those who are closely related to them; conversely, they are more willing to ask for help from those who are close to them, so mining the social relationship between experts and users will help the system recommend suitable operation and maintenance experts to users.

[0097] Generally speaking, if two people are in the same department, the same office, and have worked together before, the probability that the social relationship between the two is close is very high, that is, the social relationship is strong; conversely, the weaker the connection between departments, the farther the distance between offices, or if they have never worked together, the weaker the social relationship between the two.

[0098] In this regard, the present application can establish the social relationship between users and experts through the three elements of department, office location and cooperation relationship. The social relationship can be calculated by converting the organizational structure tree (divided by department level) into an undirected graph G(V,E), such as Figure 2 A schematic diagram of a scenario showing social relations of the present application is shown.

[0099] In the undirected graph G(V,E), nodes (V) constitute departments, branches, and head offices, and edges (E) between nodes reflect the connections between organizations. The shortest path value between the user's department and the expert's department. The smaller the value, the closer the relationship between departments. For office location elements, the calculation method can refer to the calculation method of department elements.

[0100] In addition, on the other hand, the expert status can be understood as the objective status of one's own work ability, working hours, busy / idle status, etc., which can be used to measure whether one is suitable for providing assistance in current operation and maintenance work.

[0101] Among them, the expert status of the operation and maintenance expert in the current situation can be obtained through the relevant expert table and user status table.

[0102] On the basis of the above, step S103 carries out operation and maintenance expert adaptation processing based on the target user's needs, which may specifically include:

[0103] (1) Convert each word in the consultation vector Q into a corresponding unique identifier through the vocabulary to obtain the conversion result; convert the conversion result into a topic vector Qtopic through the topic word list; calculate the cosine similarity Sim between the topic vector Etopic and the topic vector Qtopic CB(Q, E), obtain the target expert knowledge distribution adaptability of different operation and maintenance experts to the operation and maintenance expert consultation request;

[0104] It can be understood that the cosine similarity is calculated here to quantify the degree of matching between the topic vector Etopic representing the expert knowledge distribution and the topic vector Qtopic representing the knowledge involved in the current consulting question in the knowledge dimension.

[0105] Among them, the topic vector Qtopic representing the knowledge involved in the current consulting question corresponds to the previous processing of the topic vector Etopic representing the distribution of expert knowledge, which involves conversion processing based on the vocabulary and the subject word chain list.

[0106] (2) Calculate the cosine similarity between the topic vector Qtopic and the topic vector of the historical consultation question to obtain the nearest neighbor set; determine the consultation question interest of the neighbor set in the expert interest matrix as the target consultation question interest Sim of different operation and maintenance experts for the operation and maintenance expert consultation request CF (Q,E);

[0107] It can be understood that the collaborative filtering method is involved here. By calculating the cosine similarity, the matching degree between the topic vector Qtopic representing the knowledge involved in the current consulting question and the topic vector of the historical consulting question (the vector processing is the same as the topic vector Qtopic, so it will not be repeated) in the knowledge dimension is quantified. In this way, the most recent / most matching historical consulting question is equated with the current consulting question, and the interest of the operation and maintenance expert in the historical consulting question is determined by the expert interest matrix determined previously, which is used as the interest of the operation and maintenance expert in the current consulting question, and the target consulting question interest Sim CF (Q,E) to reflect.

[0108] (3) Determine the expert-user relationship table and determine the relationship intimacy R(U,E) between different operation and maintenance experts for the operation and maintenance expert consultation request;

[0109] It can be understood that here, the expert user relationship table previously determined to characterize the relationship intimacy between different operation and maintenance experts and different users is used to determine the relationship intimacy between the operation and maintenance expert and the current operation and maintenance expert consultation request or the current user, and is reflected in the relationship intimacy R(U,E).

[0110] (4) Obtain the working status S(E) of different operation and maintenance experts;

[0111] It can be understood that the working status of the operation and maintenance expert side is obtained here and is reflected by the working status S(E).

[0112] After obtaining the specific data in the four aspects, the calculation scheme for calculating the comprehensive fitness score specially designed in this application can be used to advance the calculation of the specific fitness score.

[0113] (5) In Sim CB (Q,E),Sim CF Based on (Q, E), R(U, E) and S(E), the following formula is used to quantify the fitness scores of different operation and maintenance experts:

[0114]

[0115] Among them, j = 1, 2…k, k is the number of different operation and maintenance experts, α, β, γ are the weights of different factors, when in the idle working state, S(E j )=0.

[0116] It can be seen that this application introduces the expert status as a restriction condition into the calculation process of the adaptation score, and when it is not in an idle state or in a busy state, the score is set to 0, that is, the corresponding expert is removed from the recommended expert list, eliminating the possibility of the corresponding expert adapting to the current user needs.

[0117] As an example, α may be 0.6, β may be 0.3, and γ may be 0.1.

[0118] Thus, the embodiment here is a specific implementation scheme for quantifying the fitness score of the operation and maintenance expert, combined with a specific quantification formula, so that the present application scheme can be applied more conveniently and effectively in practical applications to achieve the goal of efficiently and accurately recommending the adaptive target operation and maintenance expert scheme.

[0119] In addition, the above solutions can also be combined with Figure 3 and Figure 4 The following is a schematic diagram of the overall solution of the present application for a more vivid understanding.

[0120] The above is an introduction to the operation and maintenance expert recommendation method provided by this application. In order to better implement the operation and maintenance expert recommendation method provided by this application, this application also provides an operation and maintenance expert recommendation device from the perspective of functional modules.

[0121] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of the operation and maintenance expert recommendation device of the present application. In the present application, the operation and maintenance expert recommendation device 500 may specifically include the following structure:

[0122] The acquisition unit 501 is used to acquire an operation and maintenance expert consultation request initiated by a user terminal, wherein the operation and maintenance expert consultation request is used to consult an operation and maintenance expert suitable for the task currently being performed by the user;

[0123] A determination unit 502 is used to mine the user needs behind the operation and maintenance expert consultation request to determine the target user needs;

[0124] The adaptation unit 503 is used to carry out operation and maintenance expert adaptation processing based on the target user's needs, and obtain the quantitative results of the fitness scores of different operation and maintenance experts in the operation and maintenance expert database, wherein the operation and maintenance expert adaptation processing considers the fitness of expert knowledge distribution, the interest of patent consultation questions, the social relationship of experts and the status of experts;

[0125] The determination unit 502 is further configured to determine a target operation and maintenance expert based on the quantified results of the fitness scores of different operation and maintenance experts, wherein the number of the target operation and maintenance experts is at least one;

[0126] The push unit 504 is used to push the operation and maintenance expert recommendation information of the target operation and maintenance expert to the user terminal.

[0127] In yet another exemplary embodiment, the determining unit 502 is specifically configured to:

[0128] The task content and consultation description of the operation and maintenance expert consultation request are combined into a demand vector;

[0129] Perform word segmentation processing on the demand vector to obtain the word segmentation processing result;

[0130] Remove stop words and common words from the word segmentation results, and continue to extract noun entities to obtain noun entity extraction results;

[0131] The noun entity extraction results are reorganized into a consultation vector Q.

[0132] In another exemplary embodiment, in terms of expert knowledge distribution adaptability, the device further includes a presetting unit 505, which is used to:

[0133] Segment the expert operation and maintenance record documents of different operation and maintenance experts, remove stop words and common words, and then assign a unique identifier to each word in the document processing results to form a vocabulary;

[0134] After setting the initial parameters of the LDA model and setting the number of topics to 20, based on the document processing results and the vocabulary, the LDA model is called to use the Gibbs sampling algorithm to obtain the topic word list and document topic mapping table;

[0135] The subject word list and the document subject mapping table are analyzed to obtain an expert subject mapping table, wherein the expert subject mapping table identifies the knowledge distribution of different operation and maintenance experts as a subject vector Etopic.

[0136] In another exemplary embodiment, in response to the interest level of the patent consulting question, the preset unit 505 is further used to:

[0137] Obtain feedback from different operation and maintenance experts on historical consulting issues;

[0138] Based on the feedback information, an expert interest matrix is ​​constructed using three types of replies, namely no reply, low user evaluation reply and high-quality user evaluation reply, as distinctions. The expert interest matrix identifies the interest of different operation and maintenance experts in consulting questions.

[0139] In another exemplary embodiment, corresponding to the expert social relationship aspect, the presetting unit 505 is further used to:

[0140] Based on the user department information, department address information and participant information of the operation and maintenance records, the social relationships between different operation and maintenance experts and different users are quantified, and the social relationship quantification results are stored in the expert user relationship table, which identifies the relationship intimacy between different operation and maintenance experts and different users.

[0141] In yet another exemplary embodiment, the adaptation unit 504 is specifically configured to:

[0142] (1) Convert each word in the consultation vector Q into a corresponding unique identifier through the vocabulary to obtain the conversion result; convert the conversion result into a topic vector Qtopic through the topic word list; calculate the cosine similarity Sim between the topic vector Etopic and the topic vector Qtopic CB (Q, E), obtain the target expert knowledge distribution adaptability of different operation and maintenance experts to the operation and maintenance expert consultation request;

[0143] (2) Calculate the cosine similarity between the topic vector Qtopic and the topic vector of the historical consultation question to obtain the nearest neighbor set; determine the consultation question interest of the neighbor set in the expert interest matrix as the target consultation question interest Sim of different operation and maintenance experts for the operation and maintenance expert consultation request CF (Q,E);

[0144] (3) Determine the expert-user relationship table and determine the relationship intimacy R(U,E) between different operation and maintenance experts for the operation and maintenance expert consultation request;

[0145] (4) Obtain the working status S(E) of different operation and maintenance experts;

[0146] (5) In Sim CB (Q,E),Sim CF Based on (Q, E), R(U, E) and S(E), the following formula is used to quantify the fitness scores of different operation and maintenance experts:

[0147]

[0148] Among them, j = 1, 2…k, k is the number of different operation and maintenance experts, α, β, γ are the weights of different factors, when in the idle working state, S(E j )=0.

[0149] In yet another exemplary embodiment, the number of target operation and maintenance experts is specifically five.

[0150] This application also provides a processing device from the perspective of hardware structure, see Figure 6 , Figure 6 601, a memory 602, and an input / output device 603. The processor 601 is used to execute the computer program stored in the memory 602 to implement the following Figure 1 The steps of the operation and maintenance expert recommendation method in the corresponding embodiment; or, the processor 601 is used to execute the computer program stored in the memory 602 to implement the following Figure 5 Corresponding to the functions of each unit in the embodiment, the memory 602 is used to store the processor 601 executing the above Figure 1 The computer program required by the operation and maintenance expert recommendation method in the corresponding embodiment.

[0151] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 602, and executed by the processor 601 to complete the present application. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.

[0152] The processing device may include, but is not limited to, a processor 601, a memory 602, and an input / output device 603. Those skilled in the art will appreciate that the illustration is merely an example of a processing device and does not constitute a limitation on the processing device, and may include more or fewer components than shown in the illustration, or a combination of certain components, or different components. For example, the processing device may also include a network access device, a bus, etc., and the processor 601, the memory 602, the input / output device 603, etc. are connected via a bus.

[0153] The processor 601 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the processing device, and uses various interfaces and lines to connect various parts of the entire device.

[0154] The memory 602 can be used to store computer programs and / or modules. The processor 601 implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 602 and calling the data stored in the memory 602. The memory 602 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the processing device, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0155] When the processor 601 is used to execute the computer program stored in the memory 602, the following functions can be implemented:

[0156] Obtaining an operation and maintenance expert consultation request initiated by the user, wherein the operation and maintenance expert consultation request is used to consult an operation and maintenance expert suitable for the task currently being performed by the user;

[0157] Mining and processing the user needs behind the operation and maintenance expert consultation requests to determine the target user needs;

[0158] Based on the needs of target users, the operation and maintenance expert adaptation process is carried out to obtain the quantitative results of the fitness scores of different operation and maintenance experts in the operation and maintenance expert database. Among them, the operation and maintenance expert adaptation process takes into account the fitness of expert knowledge distribution, the interest of patent consultation issues, the social relationship of experts and the status of experts;

[0159] Determine a target operation and maintenance expert based on the quantified results of the fitness scores of different operation and maintenance experts, wherein the number of the target operation and maintenance experts is at least one;

[0160] Push the operation and maintenance expert recommendation information of the target operation and maintenance expert to the user end.

[0161] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the operation and maintenance expert recommended device, processing equipment and its corresponding units described above can refer to the following Figure 1 The description of the operation and maintenance expert recommendation method in the corresponding embodiment will not be repeated here.

[0162] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0163] To this end, the present application provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the present application as follows: Figure 1 The steps of the method recommended by the operation and maintenance expert in the corresponding embodiment, the specific operation can refer to the following Figure 1 The description of the operation and maintenance expert recommendation method in the corresponding embodiment will not be repeated here.

[0164] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0165] Due to the instructions stored in the computer-readable storage medium, the present application can be executed. Figure 1 The steps of the operation and maintenance expert recommendation method in the corresponding embodiment, therefore, the present application can be implemented as follows Figure 1 The beneficial effects that can be achieved by the operation and maintenance expert recommendation method in the corresponding embodiment are detailed in the previous description and will not be repeated here.

[0166] The operation and maintenance expert recommendation method, device, processing equipment and computer-readable storage medium provided by the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for recommending operation and maintenance experts, characterized in that: The method comprises: Obtaining an operation and maintenance expert consultation request initiated by a user, wherein the operation and maintenance expert consultation request is used to consult an operation and maintenance expert suitable for the task currently being performed by the user; Mining and processing the user needs behind the operation and maintenance expert consultation request to determine the target user needs; Based on the target user needs, the operation and maintenance expert adaptation process is carried out to obtain the quantitative results of the fitness scores of different operation and maintenance experts in the operation and maintenance expert database, wherein the operation and maintenance expert adaptation process takes into account the fitness of expert knowledge distribution, the interest of patent consultation issues, the social relationship of experts and the status of experts; Determine a target operation and maintenance expert based on the quantified results of the fitness scores of the different operation and maintenance experts, wherein the number of the target operation and maintenance experts is at least one; Pushing the operation and maintenance expert recommendation information of the target operation and maintenance expert to the user terminal.

2. The method according to claim 1, characterized in that The mining of user needs behind the operation and maintenance expert consultation request to determine target user needs includes: Combining the task content and the consulting description of the operation and maintenance expert consulting request into a demand vector; Performing word segmentation processing on the demand vector to obtain a word segmentation processing result; Remove stop words and common words from the word segmentation processing result, and continue to extract noun entities to obtain a noun entity extraction result; The noun entity extraction results are reorganized into a consultation vector Q.

3. The method according to claim 2, characterized in that Corresponding to the expert knowledge distribution adaptability, the method further includes: Segment the expert operation and maintenance record documents of different operation and maintenance experts, remove stop words and common words, and then assign a unique identifier to each word in the document processing results to form a vocabulary; After setting the initial parameters of the LDA model and setting the number of topics to 20, based on the document processing results and the vocabulary, the LDA model is called to use the Gibbs sampling algorithm to obtain a topic word list and a document topic mapping table; The subject word list and the document topic mapping table are analyzed to obtain an expert topic mapping table, wherein the expert topic mapping table identifies the knowledge distribution of the different operation and maintenance experts as a topic vector Etopic.

4. The method according to claim 3, characterized in that: In terms of the interest level of the patent consultation question, the method further includes: Obtaining feedback information from different operation and maintenance experts on historical consulting issues; On the basis of the feedback information, an expert interest matrix is ​​constructed using the three reply modes of no reply, low user evaluation reply and high-quality user evaluation reply as distinguishing methods, wherein the expert interest matrix identifies the consulting question interests of different operation and maintenance experts for different consulting questions.

5. The method according to claim 4, characterized in that Corresponding to the expert social relationship aspect, the method further includes: Based on user department information, department address information and participant information of operation and maintenance records, the social relationships between the different operation and maintenance experts and different users are quantified, and the social relationship quantification results are stored in an expert user relationship table, which identifies the relationship intimacy between the different operation and maintenance experts and the different users.

6. The method according to claim 5, characterized in that The operation and maintenance expert adaptation process is carried out based on the target user needs, including: (1) Convert each word in the consultation vector Q into the corresponding unique identifier through the word list to obtain a conversion result; convert the conversion result into a topic vector Qtopic through the topic word list; calculate the cosine similarity Sim between the topic vector Etopic and the topic vector Qtopic CB (Q, E), obtaining the target expert knowledge distribution adaptability of the different operation and maintenance experts to the operation and maintenance expert consultation request; (2) Calculating the cosine similarity between the topic vector Qtopic and the topic vector of the historical consulting question to obtain a nearest neighbor set; determining the consulting question interest of the neighbor set in the expert interest matrix as the target consulting question interest Sim of the different operation and maintenance experts for the operation and maintenance expert consulting request CF (Q,E); (3) determining the expert-user relationship table, and determining the relationship intimacy R(U, E) between the different operation and maintenance experts and the operation and maintenance expert consultation request; (4) Obtaining the working status S(E) of the different operation and maintenance experts; (5) In Sim CB (Q,E),Sim CF Based on (Q, E), R(U, E) and S(E), the following formula is used to quantify the fitness scores of different operation and maintenance experts: Wherein, j = 1, 2…k, k is the number of different operation and maintenance experts, α, β, γ are the weights of different factors, and when in the idle working state, S(E j )=0.

7. The method according to claim 1, characterized in that The specific number of the target operation and maintenance experts is 5.

8. An operation and maintenance expert recommendation device, characterized in that: The device comprises: An acquisition unit, used to acquire an operation and maintenance expert consultation request initiated by a user terminal, wherein the operation and maintenance expert consultation request is used to consult an operation and maintenance expert suitable for the task currently being performed by the user; A determination unit, configured to mine and process the user needs behind the operation and maintenance expert consultation request to determine the target user needs; An adaptation unit, used to carry out operation and maintenance expert adaptation processing based on the target user's needs, and obtain the quantitative results of the fitness scores of different operation and maintenance experts in the operation and maintenance expert database, wherein the operation and maintenance expert adaptation processing considers the fitness of expert knowledge distribution, the interest of patent consultation questions, the social relationship of experts and the status of experts; The determination unit is further configured to determine a target operation and maintenance expert based on the quantified results of the fitness scores of the different operation and maintenance experts, wherein the number of the target operation and maintenance experts is at least one; The push unit is used to push the operation and maintenance expert recommendation information of the target operation and maintenance expert to the user terminal.

9. A processing device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and the processor executes the method according to any one of claims 1 to 7 when calling the computer program in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the method according to any one of claims 1 to 7.

Images