Candidate word display method and device, computer equipment and storage medium

Abstract

The invention relates to a candidate word display method and device, computer equipment and a storage medium, and can be applied to the fields of artificial intelligence and financial science and technology. The method comprises the steps of obtaining input information input by a target user, determining a first name library from a plurality of human resource name libraries according to identification information corresponding to the target user, and obtaining a second name library according to a social group corresponding to the target user; obtaining a target candidate word corresponding to the input information in a target name word library; the target noun library comprises at least one of a first noun library and a second noun library; according to the use frequency of the target candidate word, updating the weight of the target candidate word; and determining a display sequence of the target candidate words according to the updated weights of the target candidate words, and arranging and displaying the target candidate words according to the display sequence. By adopting the method, the name input efficiency and accuracy can be improved.

Description

Technical Field

[0001] This application relates to the field of computer technologies, and in particular, to a method, apparatus, computer device, storage medium, and computer program product for displaying candidate words, which can be applied to the fields of artificial intelligence and fintech. Background Art

[0002] Entering a person's name in an input method is a frequently used function by users. The existing input methods generally match and retrieve the sorting of candidate person names in a default person name library, first giving the initial sorting of candidate person names, and then dynamically adjusting the frequency according to the different input frequencies of users. Finally, the effect of preferentially displaying the most frequently used candidate person names of this user is achieved. However, in some special usage scenarios, such as in an enterprise office scenario, users enter person names more for office communication. At this time, it is more likely to enter the names of people in the same department, the same region, and the same business field as themselves. Using the default person name library and dynamic frequency modulation of traditional input methods will result in low input efficiency and low sorting accuracy.

[0003] For users who use the input method of this device for the first time, since the default person name library is exactly the same, it takes a period of time to sort the frequently used candidate words in the front row of the input method according to the dynamic frequency modulation, and the operation efficiency is relatively low. When multiple candidate person names match the input information, the sorting method of multiple candidate words only considers user behavior information such as historical usage frequency, and does not consider more sorting methods such as department, geographical location, and business field. In specific usage scenarios, it may cause the person names that users really need to use to be sorted to a later position, and the sorting accuracy is low. For some social relationships that cannot be directly represented by explicit tag data, such as cross-departmental communication, cross-business field communication, flexible team and other communication needs, the human resources data does not contain directly relevant data for reference, and it is impossible to identify the implicit social groups of these users, and it is also difficult to support the query and sorting of candidate person names in the above scenarios.

[0004] The current input method cannot accurately display and sort candidate person names, resulting in low efficiency and accuracy of users entering person names. Summary of the Invention

[0005] Based on this, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product for displaying candidate words that can improve the efficiency and accuracy of users entering person names in response to the above technical problems.

[0006] In a first aspect, this application provides a method for displaying candidate words, including:

[0007] Obtain the input information entered by the target user. According to the identification information corresponding to the target user, determine the first personal name library from multiple human resource personal name libraries, and obtain the second personal name library according to the social group corresponding to the target user; each human resource personal name library corresponds to at least one identification information.

[0008] In the target personal name library, obtain the target candidate words corresponding to the input information; the target personal name library includes at least one of the first personal name library and the second personal name library.

[0009] Update the weight of the target candidate words according to the usage frequency of the target candidate words.

[0010] Determine the display order of the target candidate words according to the updated weights of the target candidate words, and arrange and display the target candidate words according to the display order.

[0011] In one embodiment, the method further includes:

[0012] When the input information entered by the target user is obtained, obtain the user information of the target user; the user information includes the human resource data and historical social data of the target user.

[0013] Determine the identification information and social group corresponding to the target user according to the user information.

[0014] In one embodiment, determining the identification information and social group corresponding to the target user according to the user information includes:

[0015] Determine the identification information corresponding to the target user according to the human resource data corresponding to the target user; the identification information includes one or more of geographical location, affiliated enterprise, department, and business field.

[0016] Determine the associated users with social relationships with the target user according to the historical social data corresponding to the target user, and determine the social group corresponding to the target user according to the target user and the associated users.

[0017] In one embodiment, determining the associated users with social relationships with the target user according to the historical social data corresponding to the target user includes:

[0018] Generate a node network diagram according to the historical social data; the node network diagram includes nodes and the connections between every two nodes, the nodes are used to represent users, and the connections are used to represent the social relationships between users.

[0019] Calculate the similarity between every two nodes, and use the users corresponding to the two nodes with a similarity greater than the social relationship threshold as the two users with social relationships.

[0020] Obtain associated users based on the target nodes used to represent target users in the node network diagram.

[0021] In one embodiment, obtain the input information entered by the target user, including:

[0022] Obtain the input pinyin of the target user, and detect the input pinyin according to the default personal name library built in the input method;

[0023] In the case where there is text data in the default personal name library that matches the input pinyin, use the input pinyin as the input information.

[0024] In one embodiment, in the target personal name library, obtain the target candidate words corresponding to the input information, including:

[0025] In the target personal name library, obtain the query candidate words corresponding to the input information;

[0026] According to the default personal name library built in the input method, obtain the basic candidate words corresponding to the input information;

[0027] Use the basic candidate words and the query candidate words as the target candidate words.

[0028] In one embodiment, update the weights of the target candidate words according to the usage frequencies of the target candidate words, including:

[0029] Update the weights of the basic candidate words and the query candidate words according to the usage frequencies of the basic candidate words and the query candidate words, and the same candidate words between the basic candidate words and the query candidate words;

[0030] According to the usage frequency of the query candidate words and the degree of correlation between the query candidate words and the identification information, secondarily update the weights of the query candidate words.

[0031] In a second aspect, the present application also provides a candidate word display device, including:

[0032] An acquisition module, configured to acquire the input information entered by the target user, determine the first personal name library from multiple human resource personal name libraries according to the identification information corresponding to the target user, and acquire the second personal name library according to the social group corresponding to the target user; each human resource personal name library corresponds to at least one identification information;

[0033] A query module, configured to obtain target candidate words corresponding to the input information in the target personal name library; the target personal name library includes at least one of the first personal name library and the second personal name library;

[0034] A processing module, configured to update the weights of the target candidate words according to the usage frequencies of the target candidate words;

[0035] A sorting module, configured to determine the display order of target candidate words according to the weights of the updated target candidate words, and arrange and display the target candidate words according to the display order.

[0036] In a third aspect, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0037] Obtain input information input by a target user, determine a first personal name library from multiple human resource personal name libraries according to the identification information corresponding to the target user, and obtain a second personal name library according to the social group corresponding to the target user; each human resource personal name library corresponds to at least one piece of identification information;

[0038] In the target personal name library, obtain target candidate words corresponding to the input information; the target personal name library includes at least one of the first personal name library and the second personal name library;

[0039] Update the weights of the target candidate words according to the usage frequencies of the target candidate words;

[0040] Determine the display order of the target candidate words according to the weights of the updated target candidate words, and arrange and display the target candidate words according to the display order.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0042] Obtain input information input by a target user, determine a first personal name library from multiple human resource personal name libraries according to the identification information corresponding to the target user, and obtain a second personal name library according to the social group corresponding to the target user; each human resource personal name library corresponds to at least one piece of identification information;

[0043] In the target personal name library, obtain target candidate words corresponding to the input information; the target personal name library includes at least one of the first personal name library and the second personal name library;

[0044] Update the weights of the target candidate words according to the usage frequencies of the target candidate words;

[0045] Determine the display order of the target candidate words according to the weights of the updated target candidate words, and arrange and display the target candidate words according to the display order.

[0046] In a fifth aspect, the present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0047] Obtain the input information entered by the target user, determine the first personal name library from multiple human resource personal name libraries according to the identification information corresponding to the target user, and obtain the second personal name library according to the social group corresponding to the target user; each human resource personal name library corresponds to at least one identification information;

[0048] In the target personal name library, obtain the target candidate words corresponding to the input information; the target personal name library includes at least one of the first personal name library and the second personal name library;

[0049] Update the weight of the target candidate words according to the usage frequency of the target candidate words;

[0050] Determine the display order of the target candidate words according to the updated weight of the target candidate words, and arrange and display the target candidate words according to the display order.

[0051] The above candidate word display method, device, computer device, storage medium and computer program product obtain the input information entered by the target user, determine the first personal name library from multiple human resource personal name libraries according to the identification information corresponding to the target user, and obtain the second personal name library according to the social group corresponding to the target user; in the target personal name library, obtain the target candidate words corresponding to the input information; the target personal name library includes at least one of the first personal name library and the second personal name library; update the weight of the target candidate words according to the usage frequency of the target candidate words; determine the display order of the target candidate words according to the updated weight of the target candidate words, and arrange and display the target candidate words according to the display order. Incorporate the enterprise's human resource data and various social data into the retrieval and sorting process of input legal person name candidate words. When the user uses this input method to enter input information, information such as the user's location, department, and business field will be obtained together. The name candidate words with a high business association with this user will be recommended first, and according to the established sorting strategy, determine the sorting order of multiple name candidate words. Users who use the input method for the first time can obtain relatively commonly used name candidate words, improving the efficiency and accuracy of entering names. Description of the Drawings

[0052] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0053] Figure 1 It is an application environment diagram of the candidate word display method in an embodiment;

[0054] Figure 2Schematic flow diagram of a candidate word display method in an embodiment;

[0055] Figure 3 Schematic diagram of a node network diagram structure in an embodiment;

[0056] Figure 4 Block diagram of a candidate word display device in an embodiment;

[0057] Figure 5 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0058] In order to make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] The candidate word display method provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed in the cloud or other network servers. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0060] In an exemplary embodiment, as Figure 2 shown, a candidate word display method is provided. Taking the method applied to the Figure 1 terminal 102 as an example, the method includes the following steps 202 to 208. Among them:

[0061] Step 202, obtain the input information input by the target user, determine the first personal name library from multiple human resource personal name libraries according to the identification information corresponding to the target user, and obtain the second personal name library according to the social group corresponding to the target user; each human resource personal name library corresponds to at least one identification information.

[0062] Among them, the identification information can be, but is not limited to, enterprise feature identifications such as the affiliated enterprise, branch company, department, group, position, ability level, geographical location, and business field, etc.; the human resource personal name library refers to the personal name library formulated by the enterprise based on dimensions such as branch company, department, group, position, and ability level; the social group refers to the personal name library of people who have a social relationship with the target user, and the human resource personal name library and the social group can be pre-constructed based on the enterprise's human resource and social network data.

[0063] Optionally, obtain the input information entered by the target user, and obtain the user information of the target user. The user information includes the identification information and social information corresponding to the target user. Then, based on the identification information, select the first personal name library that matches the identification information from multiple human resource personal name libraries, determine the social group of the target user based on the social information, and create a second personal name library according to the names in the social group.

[0064] Step 204, in the target personal name library, obtain the target candidate words corresponding to the input information; the target personal name library includes at least one of the first personal name library and the second personal name library.

[0065] Optionally, in the target personal name library, obtain at least one query candidate word corresponding to the input information, and according to the default personal name library built in the input method, obtain at least one basic candidate word corresponding to the input information, and use the basic candidate word and the query candidate word as the target candidate words.

[0066] Step 206, update the weights of the target candidate words according to the usage frequencies of the target candidate words.

[0067] Optionally, update the weights of each basic candidate word and query candidate word according to the usage frequencies of each basic candidate word and query candidate word, and the same candidate words in the basic candidate words and query candidate words, and then secondarily update the weights of each query candidate word according to the usage frequencies of each query candidate word and the degree of relevance between each query candidate word and the identification information.

[0068] Step 208, determine the display order of the target candidate words according to the weights of the updated target candidate words, and arrange and display the target candidate words according to the display order.

[0069] Optionally, determine the display order of each target candidate word according to the weights of each updated target candidate word, and arrange and display each target candidate word according to the display order.

[0070] In the above candidate word display method, the enterprise's human resource data and various social data are incorporated into the retrieval and sorting process of candidate legal person names. When the user uses this input method to input information, information such as the user's region, department, and business field will be obtained together. The candidate person names with a high business association with this user will be recommended first, and according to the established sorting strategy, the sorting order of multiple candidate person names will be determined. Users who use the input method for the first time can obtain relatively common candidate person names, improving the efficiency and accuracy of inputting person names.

[0071] In one embodiment, the method further includes: when obtaining the input information input by the target user, obtaining the user information of the target user; the user information includes the human resource data and historical social data of the target user; determining the identification information corresponding to the target user according to the human resource data corresponding to the target user; the identification information includes one or more of geographical location, affiliated enterprise, department, and business field; generating a node network diagram according to the historical social data; the node network diagram includes nodes and the connections between every two nodes, and the nodes are used to represent users, and the connections are used to represent the social relationships between users; calculating the similarity between every two nodes, and taking the users corresponding to the two nodes with a similarity greater than the social relationship threshold as two users with a social relationship; obtaining associated users according to the target node used to represent the target user in the node network diagram, and determining the social group corresponding to the target user according to the target user and the associated users.

[0072] Optionally, first generate a node network diagram and generate an undirected graph using various information included in the enterprise social data. The node network diagram consists of nodes and connections. In this node network diagram, a node refers to an individual user in the enterprise; if there is a connection between two individuals, there will be a connection between them. The rules for generating the node network diagram can include: if two users communicate with each other through the enterprise's chat system (such as OA), it is regarded as a connection between them; if two users establish a connection through the enterprise's email system or meeting system (such as both have participated in the same video conference), it is regarded as a connection between them, and so on. For two nodes with a connection, create a connection between them. Let U represent the set of all nodes and L represent the set of all connections, then the structure of the node network diagram can be expressed as C = { U,L}, as Figure 3 shown.

[0073] Then calculate the similarity between nodes, and calculate the "structural similarity" between two nodes on the generated node network diagram. Identify the structure of a certain node. Assume that node u ∈ U, then the structure C(u) of u is defined as: u itself and all nodes that have a connection with u. That is:

[0074] C(u) = { v ∈ U | (u, v) ∈ L} ∪ { u}

[0075] In the formula, v represents all nodes connected to u. Then the structural similarity between nodes u and v can be defined as: the overlapping part between the structure of u and the structure of v. That is:

[0076] Б(u, v) = C(u) ∩ C(v)

[0077] It can be seen that the more similar the structures of user u and user v are, the greater the calculated structural similarity Б between them will be, which means they have similar communication needs. Therefore, users with a relatively large structural similarity Б can be grouped into the same social group.

[0078] Finally, determine the strong social relationship threshold. After calculating the similarity Б between nodes, a threshold ε needs to be set for the structural similarity between nodes to determine how large the value of the structural similarity Б should be to be grouped into the same social group. The value of the threshold ε can be determined according to the needs of the enterprise after analyzing a large amount of test data.

[0079] After determining the threshold ε, define "the social group G of node u" as the set of users connected to node u and whose structural similarity with node u is greater than the threshold ε. That is:

[0080] G(u) = { v ∈ U | (u, v) ∈ L ∩ Б(u, v) > ε}

[0081] In the formula, v represents all nodes connected to u. Users determined to belong to the same social group can be considered to have a strong correlation in social relationships.

[0082] In this embodiment, according to the human resource data corresponding to the target user, determine the identification information corresponding to the target user. According to the historical social data corresponding to the target user, determine the associated users having social relationships with the target user. Based on the target user and the associated users, a second person name library related to the social group of the target user can be obtained.

[0083] In one embodiment, obtain the input information input by the target user, including: obtain the input pinyin of the target user, and detect the input pinyin according to the default person name library built in the input method; in the case where there is text data in the default person name library that matches the input pinyin, use the input pinyin as the input information.

[0084] Optionally, monitor the input behavior of the user input device. If it is recognized that the pinyin input by the user meets the input conditions for a personal name, for example, the candidate word matching the pinyin exists in the default personal name library of the input method, then use the pinyin input by the user as the input information of the valid input.

[0085] In this embodiment, obtain the input pinyin of the target user and detect the input pinyin according to the default personal name library built in the input method, so as to determine whether the input of the target user is a valid input.

[0086] In one embodiment, obtaining the target candidate word corresponding to the input information in the target personal name library includes: obtaining the query candidate word corresponding to the input information in the target personal name library; obtaining the basic candidate word corresponding to the input information according to the default personal name library built in the input method; using the basic candidate word and the query candidate word as the target candidate word.

[0087] Optionally, obtain the personal identification information of the current user in the human resources database, which may include identification information such as the location, subsidiary company, department, and business area. Based on the obtained user personal information, select a part of the name libraries from all the name libraries of the enterprise for loading. The loaded name library can be a set of users who belong to the same social group as the current user after analysis. It can also be a set based on basic human resources data, such as loading the human resources list of the same department and the same region as the current user. For example, if the subsidiary company identification of the current user is "Business R & D Center", then load the name library marked with "Business R & D Center" from all the name libraries of the enterprise as an alternative for the next search. The above example is only for better explaining the technical solution of the present invention and is not a limitation of the present invention. Therefore, any identification and mapping method that may be applied to this scenario should be included within the scope of the present invention. Use the obtained name library as the query range and the information input by the user as the query content to query the candidate words of the personal name. The query result may not contain, contain 1, or contain multiple query results. For example, if the pinyin input by the user in module S2 is "wangxiaohan", and in the name library loaded in S32, if no personal name that exactly matches "wangxiaohan" can be found, then the default personal name library of the input method can be used to return the candidate words; if one or more personal names that exactly match "wangxiaohan" can be found, such as "Wang Xiaohan", "Wang Xiaohan", "Wang Xiaohan", etc., then sort the order of display of the one or more personal name candidate words.

[0088] In this embodiment, based on the data input by the user, query in the corresponding name library according to a specific query strategy, and one or more personal name candidate words can be generated according to the query result.

[0089] In one embodiment, the weight of the target candidate word is updated according to the usage frequency of the target candidate word, including: updating the weights of the basic candidate word and the query candidate word according to the usage frequency of the basic candidate word and the query candidate word, and the same candidate words between the basic candidate word and the query candidate word; and updating the weight of the query candidate word for the second time according to the usage frequency of the query candidate word and the correlation between the query candidate word and the identification information.

[0090] Optionally, one or more query candidate words obtained by the query are compared with one or more basic candidate words generated in the default person noun library built into the input method, and based on a preset weight calculation method, an initial weight relationship between the query candidate words and the basic candidate words is obtained. For example, for the pinyin "wangxiaohan" input by the user, its basic candidate words are "王晓寒" and "王小韩". After querying according to the subsidiary and department labels, multiple query candidate words "王晓翰", "汪晓寒" and "王小涵" are obtained. It is necessary to first determine the initial weights of these two batches of candidate words to determine whether to display the basic candidate words first or the query candidate words first. The weight calculation methods that can be considered include: if the user has used a basic candidate word with a frequency much greater than the frequency of each query candidate word in the past, the weight of this basic candidate word can be increased; if a candidate word appears in both the basic candidate word and the query candidate word, the weight of this candidate word can be increased.

[0091] Furthermore, the weights between multiple query candidate words are adjusted twice, and when there are more than one query candidate words, the weights are used to determine the sorting order of the multiple query candidate words. For example: among multiple query candidate words, the weights of candidate words that the user has used with a higher frequency in the past can be increased; among multiple query candidate words, the weights of words with multiple identifiers related to the user's personal information can be increased. For example, the candidate word "Wang Xiaohan" is consistent with the user in the identifiers "Business R&D Center", "Beijing", and "Front-end Development", and the weight of this candidate word is higher. However, the candidate word "Wang Xiaohan" is consistent with the user only in the identifier "Beijing", and the weight of this candidate word is lower. The above examples are only for better illustrating the technical solution of the present invention, not for limiting the present invention, so any weight determination scheme that may be applied to this scenario should be included in the scope of the present invention.

[0092] In this embodiment, for a plurality of candidate names, weights can be calculated for the candidate names based on a certain sorting strategy, and the display order of the candidate names in the front-end input method can be determined according to the weights.

[0093] In an exemplary embodiment, a candidate word display method includes:

[0094] Obtain the input pinyin of the target user, and detect the input pinyin according to the default personal name library built in the input method; in the case that there is text data in the default personal name library that matches the input pinyin, use the input pinyin as the input information.

[0095] In the case of obtaining the input information input by the target user, obtain the user information of the target user; the user information includes the human resources data and historical social data of the target user.

[0096] According to the human resources data corresponding to the target user, determine the identification information corresponding to the target user; the identification information includes one or more of geographical location, affiliated enterprise, department, and business field; generate a node network diagram according to the historical social data; the node network diagram includes nodes and connections between every two nodes, the nodes are used to represent users, and the connections are used to represent the social relationships between users; calculate the similarity between every two nodes, and use the users corresponding to the two nodes with a similarity greater than the social relationship threshold as the two users with a social relationship; according to the target node used to represent the target user in the node network diagram, obtain associated users, and determine the social group corresponding to the target user according to the target user and the associated users.

[0097] According to the identification information corresponding to the target user, determine the first personal name library from multiple human resources personal name libraries, and obtain the second personal name library according to the social group corresponding to the target user; each human resources personal name library corresponds to at least one piece of identification information;

[0098] In the target personal name library, obtain the query candidate words corresponding to the input information; according to the default personal name library built in the input method, obtain the basic candidate words corresponding to the input information; use the basic candidate words and the query candidate words as the target candidate words. The target personal name library includes at least one of the first personal name library and the second personal name library.

[0099] Update the weights of the basic candidate words and the query candidate words according to the usage frequencies of the basic candidate words and the query candidate words, and the same candidate words between the basic candidate words and the query candidate words; secondarily update the weights of the query candidate words according to the usage frequency of the query candidate words and the degree of correlation between the query candidate words and the identification information.

[0100] Determine the display order of the target candidate words according to the weights of the updated target candidate words, and arrange and display the target candidate words according to the display order.

[0101] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless specifically stated herein, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0102] Based on the same inventive concept, an embodiment of the present application further provides a candidate word display device for implementing the candidate word display method described above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the candidate word display device provided below can refer to the limitations on the candidate word display method in the above text, and will not be repeated here.

[0103] In an exemplary embodiment, as Figure 4 shown, a candidate word display device 400 is provided, including: an acquisition module 401, a query module 402, a processing module 403, and a sorting module 404, where:

[0104] The acquisition module 401 is configured to acquire the input information input by the target user, determine the first personal name library from multiple human resource personal name libraries according to the identification information corresponding to the target user, and acquire the second personal name library according to the social group corresponding to the target user; each human resource personal name library corresponds to at least one identification information;

[0105] The query module 402 is configured to acquire the target candidate word corresponding to the input information in the target personal name library; the target personal name library includes at least one of the first personal name library and the second personal name library;

[0106] The processing module 403 is configured to update the weight of the target candidate word according to the usage frequency of the target candidate word;

[0107] The sorting module 404 is configured to determine the display order of the target candidate words according to the updated weight of the target candidate words, and arrange and display the target candidate words according to the display order.

[0108] In one embodiment, the obtaining module 401 is further configured to obtain the user information of the target user when obtaining the input information input by the target user; the user information includes the human resource data and historical social data of the target user; and determine the identification information and social group corresponding to the target user according to the user information.

[0109] In one embodiment, the apparatus further includes:

[0110] A construction module 405, configured to determine the identification information corresponding to the target user according to the human resource data corresponding to the target user; the identification information includes one or more of geographical location, affiliated enterprise, department, and business field; determine the associated users having a social relationship with the target user according to the historical social data corresponding to the target user, and determine the social group corresponding to the target user according to the target user and the associated users.

[0111] In one embodiment, the construction module 405 is further configured to generate a node network diagram according to the historical social data; the node network diagram includes nodes and connections between every two nodes, the nodes are used to represent users, and the connections are used to represent the social relationships between users; calculate the similarity between every two nodes, and use the users corresponding to the two nodes with a similarity greater than the social relationship threshold as the two users having a social relationship; obtain the associated users according to the target node used to represent the target user in the node network diagram.

[0112] In one embodiment, the obtaining module 401 is further configured to obtain the input pinyin of the target user, and detect the input pinyin according to the default personal name library built in the input method; when there is text data in the default personal name library that matches the input pinyin, use the input pinyin as the input information.

[0113] In one embodiment, the query module 402 is further configured to obtain query candidate words corresponding to the input information in the target personal name library; obtain basic candidate words corresponding to the input information according to the default personal name library built in the input method; and use the basic candidate words and the query candidate words as the target candidate words.

[0114] In one embodiment, the processing module 403 is further configured to update the weights of the basic candidate words and the query candidate words according to the usage frequencies of the basic candidate words and the query candidate words, and the same candidate words between the basic candidate words and the query candidate words; and secondarily update the weight of the query candidate words according to the usage frequency of the query candidate words and the degree of correlation between the query candidate words and the identification information.

[0115] Each module in the above candidate word display device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or stored in a memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0116] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 5 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store thesaurus data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a candidate word display method.

[0117] Those skilled in the art can understand that Figure 5 the structure shown in

[0118] is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0119] In one embodiment, when the processor executes a computer program, the following steps are further implemented: when the input information input by the target user is obtained, obtain the user information of the target user; the user information includes the human resource data and historical social data of the target user; according to the user information, determine the identification information and social group corresponding to the target user.

[0120] In one embodiment, when the processor executes a computer program, the following steps are further implemented: according to the human resource data corresponding to the target user, determine the identification information corresponding to the target user; the identification information includes one or more of geographical location, affiliated enterprise, department, and business field; according to the historical social data corresponding to the target user, determine the associated users having a social relationship with the target user, and according to the target user and the associated users, determine the social group corresponding to the target user.

[0121] In one embodiment, when the processor executes a computer program, the following steps are further implemented: generate a node network diagram according to the historical social data; the node network diagram includes nodes and the connections between every two nodes, the nodes are used to represent users, and the connections are used to represent the social relationships between users; calculate the similarity between every two nodes, and use the users corresponding to the two nodes with a similarity greater than the social relationship threshold as the two users having a social relationship; according to the target node used to represent the target user in the node network diagram, obtain the associated users.

[0122] In one embodiment, when the processor executes a computer program, the following steps are further implemented: obtain the input pinyin of the target user, and detect the input pinyin according to the default personal name library built in the input method; when there is text data in the default personal name library that matches the input pinyin, use the input pinyin as the input information.

[0123] In one embodiment, when the processor executes a computer program, the following steps are further implemented: in the target personal name library, obtain the query candidate words corresponding to the input information; according to the default personal name library built in the input method, obtain the basic candidate words corresponding to the input information; use the basic candidate words and the query candidate words as the target candidate words.

[0124] In one embodiment, when the processor executes a computer program, the following steps are further implemented: update the weights of the basic candidate words and the query candidate words according to the usage frequencies of the basic candidate words and the query candidate words, and the same candidate words between the basic candidate words and the query candidate words; secondarily update the weight of the query candidate word according to the usage frequency of the query candidate word and the degree of correlation between the query candidate word and the identification information.

[0125] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining input information input by a target user, determining a first personal name library from multiple human resource personal name libraries according to the identification information corresponding to the target user, and obtaining a second personal name library according to the social group corresponding to the target user; each human resource personal name library corresponds to at least one piece of identification information; in the target personal name library, obtaining a target candidate word corresponding to the input information; the target personal name library includes at least one of the first personal name library and the second personal name library; updating the weight of the target candidate word according to the usage frequency of the target candidate word; determining the display order of the target candidate words according to the updated weight of the target candidate word, and arranging and displaying the target candidate words according to the display order.

[0126] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: when obtaining the input information input by the target user, obtaining the user information of the target user; the user information includes the human resource data and historical social data of the target user; determining the identification information and social group corresponding to the target user according to the user information.

[0127] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining the identification information corresponding to the target user according to the human resource data corresponding to the target user; the identification information includes one or more of geographical location, affiliated enterprise, department, and business field; determining the associated users having a social relationship with the target user according to the historical social data corresponding to the target user, and determining the social group corresponding to the target user according to the target user and the associated users.

[0128] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: generating a node network diagram according to the historical social data; the node network diagram includes nodes and connections between every two nodes, the nodes are used to represent users, and the connections are used to represent the social relationships between users; calculating the similarity between every two nodes, and taking the users corresponding to the two nodes with a similarity greater than the social relationship threshold as the two users having a social relationship; obtaining the associated users according to the target node used to represent the target user in the node network diagram.

[0129] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtaining the input pinyin of the target user, and detecting the input pinyin according to the default personal name library built in the input method; when there is text data in the default personal name library that matches the input pinyin, taking the input pinyin as the input information.

[0130] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: In the target personal name library, obtain query candidate words corresponding to the input information; According to the default personal name library built into the input method, obtain basic candidate words corresponding to the input information; Use the basic candidate words and the query candidate words as target candidate words.

[0131] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: Update the weights of the basic candidate words and the query candidate words according to the usage frequencies of the basic candidate words and the query candidate words, and the same candidate words between the basic candidate words and the query candidate words; Secondarily update the weight of the query candidate word according to the usage frequency of the query candidate word and the degree of relevance between the query candidate word and the identification information.

[0132] In one embodiment, a computer program product is provided, including a computer program, which when executed by a processor, implements the following steps: Obtain input information input by a target user, determine a first personal name library from multiple human resource personal name libraries according to the identification information corresponding to the target user, and obtain a second personal name library according to the social group corresponding to the target user; Each human resource personal name library corresponds to at least one piece of identification information; In the target personal name library, obtain target candidate words corresponding to the input information; The target personal name library includes at least one of the first personal name library and the second personal name library; Update the weights of the target candidate words according to the usage frequencies of the target candidate words; Determine the display order of the target candidate words according to the updated weights of the target candidate words, and arrange and display the target candidate words according to the display order.

[0133] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: When the input information input by the target user is obtained, obtain the user information of the target user; The user information includes the human resource data and historical social data of the target user; Determine the identification information and social group corresponding to the target user according to the user information.

[0134] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: Determine the identification information corresponding to the target user according to the human resource data corresponding to the target user; The identification information includes one or more of geographical location, affiliated enterprise, department, and business field; Determine associated users having a social relationship with the target user according to the historical social data corresponding to the target user, and determine the social group corresponding to the target user according to the target user and the associated users.

[0135] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: generating a node network diagram according to historical social data; the node network diagram includes nodes and connections between every two nodes, where the nodes are used to represent users and the connections are used to represent the social relationships between users; calculating the similarity between every two nodes, and taking the users corresponding to the two nodes with a similarity greater than the social relationship threshold as two users with a social relationship; obtaining associated users according to the target node used to represent the target user in the node network diagram.

[0136] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtaining the input pinyin of the target user, and detecting the input pinyin according to the default personal name library built in the input method; in the case where there is text data in the default personal name library that matches the input pinyin, taking the input pinyin as the input information.

[0137] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtaining query candidate words corresponding to the input information in the target personal name library; obtaining basic candidate words corresponding to the input information according to the default personal name library built in the input method; taking the basic candidate words and the query candidate words as target candidate words.

[0138] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: updating the weights of the basic candidate words and the query candidate words according to the usage frequencies of the basic candidate words and the query candidate words, and the same candidate words between the basic candidate words and the query candidate words; secondarily updating the weight of the query candidate word according to the usage frequency of the query candidate word and the degree of correlation between the query candidate word and the identification information.

[0139] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0140] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0141] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0142] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A candidate word display method, characterized in that, The method includes: Obtaining input information entered by a target user, determining a first personal name library from multiple human resource personal name libraries according to the identification information corresponding to the target user, and obtaining a second personal name library according to the social group corresponding to the target user; each human resource personal name library corresponds to at least one piece of identification information; Obtaining a target candidate word corresponding to the input information in a target personal name library; the target personal name library includes at least one of the first personal name library and the second personal name library; Updating the weight of the target candidate word according to the usage frequency of the target candidate word; Determining the display order of the target candidate words according to the weight of the updated target candidate words, and arranging and displaying the target candidate words according to the display order.

2. The method according to claim 1, characterized in that, The method further includes: When obtaining the input information entered by the target user, obtaining the user information of the target user; the user information includes the human resource data and historical social data of the target user; Determining the identification information and social group corresponding to the target user according to the user information.

3. The method according to claim 2, wherein The determining the identification information and social group corresponding to the target user according to the user information includes: Determining the identification information corresponding to the target user according to the human resource data corresponding to the target user; the identification information includes one or more of geographical location, affiliated enterprise, department, and business field; Determining associated users having a social relationship with the target user according to the historical social data corresponding to the target user, and determining the social group corresponding to the target user according to the target user and the associated users.

4. The method according to claim 3, characterized in that The determining the associated users having a social relationship with the target user according to the historical social data corresponding to the target user includes: Generating a node network diagram according to the historical social data; the node network diagram includes nodes and connections between every two nodes, the nodes are used to represent users, and the connections are used to represent the social relationships between users; Calculating the similarity between every two nodes, and taking the users corresponding to the two nodes with a similarity greater than the social relationship threshold as two users having a social relationship; Obtaining the associated users according to the target node used to represent the target user in the node network diagram.

5. The method according to claim 1, wherein The obtaining the input information entered by the target user includes: Obtaining the input pinyin of the target user, and detecting the input pinyin according to the default personal name library built in the input method; When there is text data in the default personal name library that matches the input pinyin, taking the input pinyin as the input information.

6. The method according to claim 1, characterized in that The obtaining the target candidate word corresponding to the input information in the target personal name library includes: Obtaining query candidate words corresponding to the input information in the target personal name library; Obtaining basic candidate words corresponding to the input information according to the default personal name library built in the input method; Taking the basic candidate words and the query candidate words as the target candidate words.

7. The method according to claim 6, wherein The updating the weight of the target candidate word according to the usage frequency of the target candidate word includes: Update the weights of the basic candidate words and the query candidate words according to the usage frequencies of the basic candidate words and the query candidate words, and the same candidate words between the basic candidate words and the query candidate words; Secondarily update the weight of the query candidate word according to the usage frequency of the query candidate word and the correlation degree between the query candidate word and the identification information.

8. A candidate word display device, characterized in that, The device includes: An acquisition module, configured to acquire input information input by a target user, determine a first personal name library from multiple human resource personal name libraries according to the identification information corresponding to the target user, and acquire a second personal name library according to the social group corresponding to the target user; each human resource personal name library corresponds to at least one piece of identification information; A query module, configured to acquire a target candidate word corresponding to the input information in a target personal name library; the target personal name library includes at least one of the first personal name library and the second personal name library; A processing module, configured to update the weight of the target candidate word according to the usage frequency of the target candidate word; A sorting module, configured to determine the display order of the target candidate words according to the weights of the updated target candidate words, and arrange and display the target candidate words according to the display order.

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

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

Images