User information processing method and device, equipment and storage medium
By extracting the summary information of the conversation text data and searching it in the user management library, the problem of customer service personnel needing to manually enter user information during the call is solved, improving work efficiency and user experience.
Patent Information
- Application Number
- CN202411361107.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-26
- Publication Date
- 2025-01-21
AI Technical Summary
During the customer service and user call, user information needs to be entered manually, resulting in low customer service work efficiency, long wait time for users and poor service experience.
By obtaining the dialogue text data, extract its abstract information, and enter and search for the summary information in the preset user management library to output the user information of the target user.
There is no need to manually enter the call content of customer service, which improves customer service efficiency, reduces user waiting time, and enhances the user's service experience.
Smart Images
Figure CN119336902A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a user information processing method, device, equipment and storage medium. Background Art
[0002] Generally, when customer service is talking to a user, they need to manually input the user information they consulted, such as name, license plate number, etc., into the system for query. If it is a new user or the user's information is updated, the customer service needs to manually input the user information into the system to create a new user list, or input the user information to search for the user list and manually change the information in the user list.
[0003] In the related art, customer service is required to manually input the user information consulted during the call. If the customer service typing speed is slow, the user will have to wait for a long time and have a poor service experience. Summary of the invention
[0004] The main purpose of this application is to provide a user information processing method, device, equipment and storage medium, which eliminates the need for customer service to manually input the content of the call during a call with the user, thereby improving the work efficiency of customer service, avoiding long waiting times for users, and thus improving the user's service experience.
[0005] In a first aspect, the present application provides a user information processing method, comprising:
[0006] Get the conversation text data;
[0007] Extracting summary information of the conversation text data;
[0008] Entering the summary information into a preset user management library;
[0009] According to the summary information, searching the user management database for a target user corresponding to the summary information;
[0010] Output the user information corresponding to the target user.
[0011] In a second aspect, the present application further provides a user information processing device, including:
[0012] An acquisition module, used to acquire conversation text data;
[0013] An information extraction module, used to extract summary information of the conversation text data;
[0014] An information input module, used for inputting the summary information into a preset user management library;
[0015] A search module, configured to search the user management database for a target user corresponding to the summary information according to the summary information;
[0016] The output module is used to output the user information corresponding to the target user.
[0017] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor;
[0018] The memory is used to store computer programs;
[0019] The processor is used to execute the computer program and implement the user information processing method as described above when executing the computer program.
[0020] 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 steps of the user information processing method as described above are implemented.
[0021] The present application provides a user information processing method, device, equipment and storage medium, wherein the method includes: obtaining conversation text data; extracting summary information of the conversation text data; inputting the summary information into a preset user management library; searching the user management library for a target user corresponding to the summary information according to the summary information; and outputting user information corresponding to the target user. The present application can accurately understand the key information of the user during the call by extracting summary information of the conversation text data between the customer service and the user during the call; and then inputting the summary information into the user management library to search the user management library for the target user corresponding to the summary information according to the summary information. The customer service does not need to manually input the content of the call during the call with the user, which improves the work efficiency of the customer service and avoids the user from waiting for a long time, thereby improving the user's service experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the technical solutions of 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 some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0023] Figure 1 A flowchart of a user information processing method provided in an embodiment of the present application;
[0024] Figure 2 A schematic diagram of the connection between the server and the terminal device provided in the embodiment of the present application;
[0025] Figure 3 A schematic block diagram of a user information processing device provided in an embodiment of the present application;
[0026] Figure 4 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0027] 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 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 ordinary technicians in this field without creative work are within the scope of protection of this application.
[0028] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.
[0029] The embodiments of the present application provide a user information processing method, apparatus, device and storage medium. The user information processing method can be applied to a terminal device, which can be a mobile phone, a tablet computer, a laptop computer, a desktop computer and the like. It can also be applied to a server, which can be a separate server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.
[0030] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.
[0031] See also Figure 1 , Figure 1 This is a flow chart of a user information processing method provided in an embodiment of the present application. It should be noted that the user information processing method provided in an embodiment of the present application can be used in a terminal device, and of course, can also be used in a server.
[0032] like Figure 2 As shown, the user information processing method is applied to a server, the server and the terminal device are connected in communication, and the user information obtained by the user information processing method can be sent to the terminal device through the server. Of course, it is not limited to this and is not limited here.
[0033] In the specific implementation, the terminal device includes but is not limited to: any one of a mobile phone, a tablet computer, a laptop computer, and a desktop computer; the server can be a single server, a server cluster, or a cloud server that provides cloud computing services.
[0034] like Figure 1 As shown, the user information processing method may include steps S101 to S105.
[0035] Step S101, obtaining conversation text data.
[0036] In the insurance field, the customer service of an insurance company generally contacts users by phone. During the conversation between the customer service and the user, the ASR (Automatic Speech Recognition) technology can be used to recognize the voice content of the customer service and the user during the conversation and convert the voice content into dialogue text data.
[0037] It should be noted that ASR is a technology that can convert human speech into text. It can process and analyze voice signals, identify words, phrases or sentences, and convert them into computer-readable text format.
[0038] Step S102: extract summary information of the conversation text data.
[0039] The embodiment of the present application can extract summary information of the conversation text data to understand the key information during the call between the customer service and the user, so as to accurately understand the user's needs. Specifically, the embodiment of the present application can extract summary information of the conversation text data through the TextRank algorithm to improve the efficiency of information acquisition.
[0040] It should be noted that the TextRank algorithm is a graph-based ranking algorithm, which is mainly used for keyword extraction and text summarization in text processing. The TextRank algorithm extracts summary information from the conversation text data by constructing a relationship graph between words or sentences in the conversation text data and iteratively updating the weights of the nodes corresponding to the words or sentences in the relationship graph.
[0041] In an exemplary implementation, step S102 may include steps S201 to S204.
[0042] Step S201: segment the conversation text data to obtain multiple text units.
[0043] Step S202: construct a node connection diagram based on the multiple text units. The node connection diagram includes multiple nodes and link relationships between the nodes. Each node corresponds to a text unit.
[0044] Step S203: Calculate the weight values corresponding to each text unit based on a preset iterative calculation formula, and determine the node weight values corresponding to each text unit when an iteration termination condition is met.
[0045] Step S204: Determine summary information of the conversation text data according to the weight values of the multiple nodes.
[0046] Exemplarily, the embodiment of the present application may first segment the conversation text data to obtain multiple text units. Specifically, the conversation text data may first be segmented to remove noise information and stop words to segment the sentences in the conversation text data into T = [S1, S2, S3 ... S m ], where m represents the number of sentences; then, for each sentence S l ∈T for word segmentation and part-of-speech tagging, l represents the lth sentence, and part-of-speech tagging refers to tagging nouns, verbs, adjectives and other parts of speech, that is, S l =[t l,1 ,t l.2 ,……,t l,n ], where t l,f ∈S l , n is the number of words, and finally the key information in the dialogue text data can be obtained, thereby obtaining multiple text units with part-of-speech tags.
[0047] In the embodiment of the present application, text units can be used as nodes, and the link relationship between multiple nodes can be determined based on the co-occurrence relationship, semantic similarity, etc. between the multiple text units to construct a node connection graph including nodes corresponding to multiple text units and the link relationship between the nodes.
[0048] Specifically, the node connection graph is a directed graph, that is, multiple nodes are represented by directed edges. For example, the first node is connected to the second node through a directed edge pointing to the second node. In this link relationship, for the second node, the first node is the in-link node of the second node, and the second node is the out-link node of the first node. Generally, when starting from the first node to reach multiple nodes, these multiple nodes can be combined into the out-link node set of the first node; when starting from multiple nodes to reach the first node, these multiple nodes can be combined into the in-link node set of the first node.
[0049] Based on the preset iterative calculation formula, the weight value corresponding to each text unit can be calculated, and when the iteration termination condition is met, the node weight value corresponding to the text unit can be determined. Exemplarily, the weight value corresponding to each text unit will be updated according to the link relationship between the corresponding node and other nodes; when the difference in the weight values of several consecutive text units gradually decreases or remains unchanged, it can be considered that the iteration termination condition is met, and the iteration is stopped and the node weight value corresponding to each text unit is determined; finally, the summary information of the conversation text data can be determined based on the text units corresponding to multiple node weight values.
[0050] The embodiment of the present application can extract key information from a large amount of conversation text data, and then generate concise and clear summary information based on the extracted key information, thereby helping customer service to quickly understand the user's main needs and improve the efficiency of information acquisition.
[0051] In an exemplary implementation, the iterative calculation formula in the embodiment of the present application may be:
[0052]
[0053] Among them, V i Represents the node corresponding to the i-th text unit; V j V represents the node corresponding to the jth text unit; k Indicates the node corresponding to the kth text unit; WS(V i ) represents the weight of the i-th text unit; d is the preset coefficient; w ji Represents node V j To Node V i The weight of the link relationship; WS(V j ) represents the weight of the jth text unit; Out(V j ) represents the node V j The first node set with a first link relationship, the first link relationship is node V j The link relationship to the nodes in the first node set, In(V i ) represents the node V i A second node set with a second link relationship, where the second link relationship is from a node in the second node set to a node V i The link relationship of jk Represents node V j To Node V k The weight of the link relationship.
[0054] It should be noted that d can be used to represent the probability value from one node to another node in the node connection graph. Exemplarily, in the embodiment of the present application, d can be set to 0.86.
[0055] The embodiment of the present application can capture the co-occurrence relationship and semantic relationship between words in the conversation text data through an iterative calculation formula, so as to more accurately evaluate the importance of each word and better reflect the key information of the conversation text data.
[0056] In an exemplary implementation, step S204 may include step S2041 and step S2042.
[0057] Step S2041: determine a target text unit according to a plurality of node weight values, wherein the node weight value of the target text unit is greater than the node weight values of the text units other than the target text unit in the plurality of text units.
[0058] Step S2042: Determine summary information of the dialogue text data according to the target text unit.
[0059] When the iterative calculation is terminated, the embodiment of the present application can determine the node weight value of each text unit, and the target text unit can be determined according to the multiple node weight values. Specifically, the multiple node weight values can be sorted in order from large to small, the ranking of each node weight can be determined, and then the text unit corresponding to the node weight value whose ranking is before the preset ranking is used as the target text unit. Then, the summary information of the dialogue text data is determined according to the semantics and connection order of the target text unit. For example, the dialogue text data is "I live far away from the city, on Shangfeng Road in Tang Town. This year, I changed my new car again." Finally, according to the node weight value, it can be determined that the target text unit includes words such as "live", "Tang Town", "Shangfeng Road", "changed", and "new car". Then, according to the semantics and connection order of multiple target text units, the summary information of the dialogue text data can be determined as "the user has changed his new car". In the actual application scenario, for the customer service of the insurance company, the user indicates that he has changed his new car, and generally needs to update the information of the user in the insurance company in a timely manner.
[0060] The embodiment of the present application can further improve the accuracy of extracting summary information by screening out text units with larger node weight values.
[0061] Step S103: input summary information into a preset user management library.
[0062] The user management library can include user information of multiple users. Taking the insurance field as an example, an insurance company can set up a user management library. The user management library can store user information of multiple users, such as user name, ID number, mobile phone number, driver's license, vehicle registration certificate, and auto insurance contract.
[0063] For example, in the embodiment of the present application, a user list can be set in the user management library for each user who purchases auto insurance. The user list can also record the specific information of the user's vehicle accident.
[0064] After extracting the summary information of the conversation text data, the summary information can be directly entered into the user management library. Taking the insurance field as an example, during a call between a customer service representative and a user, the search interface of the user management library can be displayed, and the search interface can be displayed in the form of a list. Among them, the list may include a user's name input field, an ID number input field, a driver's license number input field, a mobile phone number input field, and the like. After extracting the summary information, the summary information can be entered into the corresponding position of the search interface. For example, if the summary information is the user's name, the user's name can be directly entered into the name input field in the search interface. The embodiment of the present application does not require the customer service to manually enter the content of the call with the user, which improves the work efficiency of the customer service, and avoids the need for the user to wait for a long time for the customer service to manually enter and query messages during the call with the customer service, thereby improving the user's service experience.
[0065] Step S104: Search the user management database for the target user corresponding to the summary information according to the summary information.
[0066] For example, after the summary information is input into the user management library, the target user corresponding to the summary information can be searched in the user management library. Specifically, the search can be performed through a search engine with fast search, real-time analysis and distributed storage functions to increase the search speed.
[0067] In an exemplary implementation, step S104 may include step S401 and step S402.
[0068] Step S401: Match the summary information with the user information in the user management database to obtain a matching value between the summary information and the user information.
[0069] Step S402: Determine the target user corresponding to the summary information according to the matching value corresponding to the user information and a preset matching threshold.
[0070] The embodiment of the present application can match the summary information with the user information in the user management library, so as to obtain the matching value of the summary information and the user information. For example, the obtained user name, address, ID number, car model and other summary information can be matched one by one with the user information in the user management library, that is, according to the text similarity between each summary information and the corresponding user information, the matching value of each summary information and the corresponding user information can be determined.
[0071] For example, the embodiment of the present application may first determine the matching value between each summary information and the corresponding user information, and then compare the matching value corresponding to each user information with a preset matching threshold to determine the target user corresponding to the summary information.
[0072] In an exemplary implementation, step S402 may include step S4021 and step S4022.
[0073] Step S4021: When the matching value corresponding to the user information is greater than the matching threshold, determine that the user corresponding to the user information whose matching value is greater than the matching threshold is the target user.
[0074] Step S4022: When the matching value corresponding to each user information in the user management database is less than or equal to the preset matching threshold, the target user corresponding to the summary information is added to the user management database.
[0075] It is understandable that there may be multiple users with the same name and similar addresses. Therefore, when comparing each summary information with the corresponding user information, it is necessary to consider whether all the summary information can be successfully matched with the user information in the user management library.
[0076] Based on this, the embodiment of the present application can set a matching threshold according to actual conditions. For example, when the matching value corresponding to the user information is greater than the matching threshold, it means that a matching user has been searched, that is, a user whose user information corresponding to the summary information is searched in the user management library. At this time, it is necessary to exclude situations such as the same name and similar address to determine that the user corresponding to the user information whose matching value is greater than the matching threshold is the target user.
[0077] When the matching value corresponding to each user information in the user management library is less than or equal to the preset matching threshold, it means that the search fails, that is, the target user corresponding to the summary information is not found in the user management library. At this time, the target user corresponding to the summary information can be added to the user management library. Specifically, the function of adding a new user in the user management library can be called, and the new user list corresponding to the function can be displayed, and then the summary information can be entered into the new user list.
[0078] Exemplarily, when the operation of inputting the summary information into the new user list is completed, in response to the click operation confirmed by the customer service, the operation of adding the target user corresponding to the summary information is completed in the user management library. When the embodiment of the present application adds the target user corresponding to the summary information in the user management library, there is no need for the customer service staff to manually input the user information of the target user, which saves the customer service staff time of manually inputting information, improves the customer service staff's work efficiency, and at the same time, improves the user's service experience.
[0079] In an exemplary implementation, after step S4021, step S4023 is further included.
[0080] Step S4023: Update the user information corresponding to the target user according to the summary information.
[0081] When the target user corresponding to the summary information is matched in the user management library and the matching value corresponding to the user information is less than the matching threshold, it means that there are some differences between the summary information and the user information recorded in the user management library. At this time, the user information corresponding to the target user can be updated according to the summary information. For example, the user name, ID number and license plate number in the summary information are consistent with the user information of the target user in the user management library; but the mobile phone number and address in the summary information are inconsistent with the user information of the target user in the user management library, then the mobile phone number and address of the target user in the user management library need to be updated according to the mobile phone number and address in the summary information.
[0082] For example, when a target user is matched in a user management library based on summary information, but some summary information is inconsistent with the user information of the target user, such content can be highlighted through highlighting, annotation, and other prompts; and after the information update is completed, the revised format is retained to facilitate customer service and users to check the user information that needs to be updated one by one.
[0083] In addition, if the summary information of the extracted conversation text data is "I changed to a new car", the user information corresponding to the target user can be updated, for example, adding a new license plate number, a new car insurance contract, etc.
[0084] Step S105: output user information corresponding to the target user.
[0085] Exemplarily, when a target user is searched, in response to an update operation of the target user's user information, or in response to an addition operation of a new user, the user information corresponding to the target user is output, for example, user name, mobile phone number, address, license plate number, auto insurance contract number, vehicle accident information, etc., to facilitate confirmation between customer service and the user.
[0086] The user information processing method provided in the above embodiment includes: obtaining conversation text data; extracting summary information of the conversation text data; inputting the summary information into a preset user management library; searching the user management library for a target user corresponding to the summary information according to the summary information; and outputting the user information corresponding to the target user. This application can accurately understand the key information of the user during the call by extracting the summary information of the conversation text data between the customer service and the user during the call; and then inputting the summary information into the user management library to search the user management library for the target user corresponding to the summary information according to the summary information. The customer service does not need to manually input the content of the call during the call with the user, which improves the work efficiency of the customer service and avoids the user from waiting for a long time, thereby improving the user's service experience.
[0087] See also Figure 3 , Figure 3A schematic block diagram of a user information processing device provided in an embodiment of the present application. The user information processing device can be configured in a server or a terminal device to execute the aforementioned user information processing method.
[0088] like Figure 3 As shown, the user information processing device may include: an acquisition module 110 , an information extraction module 120 , an information input module 130 , a search module 140 and an output module 150 .
[0089] The acquisition module 110 is used to acquire the conversation text data.
[0090] The information extraction module 120 is used to extract summary information of the conversation text data.
[0091] The information input module 130 is used to input summary information into a preset user management library.
[0092] The search module 140 is used to search the user management library for a target user corresponding to the summary information according to the summary information.
[0093] The output module 150 is used to output the user information corresponding to the target user.
[0094] In an exemplary embodiment, the information extraction module 120 may include a processing submodule, a construction submodule, a calculation submodule, and an information determination submodule.
[0095] The processing submodule is used to segment the conversation text data to obtain multiple text units.
[0096] The construction submodule is used to construct a node connection diagram based on multiple text units. The node connection diagram includes multiple nodes and link relationships between each node, and each node corresponds to a text unit.
[0097] The calculation submodule is used to calculate the weight value corresponding to each text unit based on a preset iterative calculation formula, and determine the node weight value corresponding to each text unit when the iteration termination condition is met.
[0098] The information determination submodule is used to determine summary information of the conversation text data according to multiple node weight values.
[0099] In an exemplary embodiment, the information determination submodule may include a first information determination submodule and a second information determination submodule.
[0100] The first information determination submodule is used to determine a target text unit according to a plurality of node weight values, wherein the node weight value of the target text unit is greater than the node weight values of text units other than the target text unit in the plurality of text units.
[0101] The second information determination submodule is used to determine summary information of the dialogue text data according to the target text unit.
[0102] In an exemplary embodiment, the iterative calculation formula is:
[0103]
[0104] Among them, V i Represents the node corresponding to the i-th text unit; V j represents the node corresponding to the jth text unit; V k Indicates the node corresponding to the kth text unit; WS(V i ) represents the weight of the i-th text unit; d is the preset coefficient; w ji Represents node V j To Node V i The weight of the link relationship; WS(V j ) represents the weight of the jth text unit; Out(V j ) represents the node V j The first node set with a first link relationship, the first link relationship is node V j The link relationship to the nodes in the first node set, In(V i ) represents the node V i A second node set with a second link relationship, where the second link relationship is from a node in the second node set to a node V i The link relationship of jk Represents node V j To Node V k The weight of the link relationship.
[0105] In an exemplary embodiment, the search module 140 may include a matching submodule and a user determination submodule.
[0106] The matching submodule is used to match the summary information with the user information in the user management library to obtain a matching value between the summary information and the user information.
[0107] The user determination submodule is used to determine the target user corresponding to the summary information according to the matching value corresponding to the user information and a preset matching threshold.
[0108] In an exemplary embodiment, the user determination submodule may include a determination submodule and an addition submodule.
[0109] The determination submodule is used to determine that the user corresponding to the user information whose matching value is greater than the matching threshold is the target user when the matching value corresponding to the user information is greater than the matching threshold.
[0110] The adding submodule is used to add the target user corresponding to the summary information in the user management library when the matching value corresponding to each user information in the user management library is less than or equal to the preset matching threshold.
[0111] In an exemplary embodiment, the apparatus further includes an update module.
[0112] The updating module is used to update the user information corresponding to the target user according to the summary information.
[0113] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described devices and modules and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0114] The method of the present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.
[0115] Exemplarily, the above method and apparatus may be implemented in the form of a computer program, which may be run on a computer device.
[0116] See also Figure 4 , Figure 4 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be a server or a terminal device.
[0117] like Figure 4 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a storage medium and an internal memory.
[0118] The storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute the steps of any user information processing method.
[0119] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.
[0120] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute the steps of any user information processing method.
[0121] The network interface is used for network communication, such as sending assigned tasks.
[0122] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0123] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be 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. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0124] In one embodiment, the processor is used to execute a computer program and implement the following steps when executing the computer program:
[0125] Get the conversation text data;
[0126] Extract summary information from conversation text data;
[0127] Enter summary information in the preset user management library;
[0128] According to the summary information, search the user management database for the target user corresponding to the summary information;
[0129] Output the user information corresponding to the target user.
[0130] In an exemplary embodiment, extracting summary information of the conversation text data includes:
[0131] Segmenting the conversation text data to obtain multiple text units;
[0132] According to the multiple text units, a node connection graph is constructed, wherein the node connection graph includes multiple nodes and link relationships between the nodes, and each node corresponds to a text unit;
[0133] Based on a preset iterative calculation formula, the weight values corresponding to each text unit are calculated, and when the iteration termination condition is met, the node weight values corresponding to each text unit are determined;
[0134] Determine summary information of the conversation text data based on multiple node weight values.
[0135] In an exemplary embodiment, determining summary information of the conversation text data according to a plurality of node weight values includes:
[0136] Determine a target text unit according to the plurality of node weight values, wherein the node weight value of the target text unit is greater than the node weight values of the text units other than the target text unit in the plurality of text units;
[0137] Based on the target text unit, summary information of the dialogue text data is determined.
[0138] In an exemplary embodiment, the iterative calculation formula is:
[0139]
[0140] Among them, V i Represents the node corresponding to the i-th text unit; V j V represents the node corresponding to the jth text unit; k Indicates the node corresponding to the kth text unit; WS(V i ) represents the weight of the i-th text unit; d is the preset coefficient; w ji Represents node V j To Node V i The weight of the link relationship; WS(V j ) represents the weight of the jth text unit; Out(V j ) represents the node V j The first node set with a first link relationship, the first link relationship is node V j The link relationship to the nodes in the first node set, In(V i ) represents the node V i A second node set with a second link relationship, where the second link relationship is from a node in the second node set to a node V i The link relationship of jk Represents node V j To Node V k The weight of the link relationship.
[0141] In an exemplary implementation, searching for a target user corresponding to the summary information in a user management library according to the summary information includes:
[0142] Match the summary information with the user information in the user management database to obtain a matching value between the summary information and the user information;
[0143] According to the matching value corresponding to the user information and the preset matching threshold, the target user corresponding to the summary information is determined.
[0144] In an exemplary implementation, determining a target user corresponding to the summary information according to a matching value corresponding to the user information and a preset matching threshold includes:
[0145] When the matching value corresponding to the user information is greater than the matching threshold, the user corresponding to the user information whose matching value is greater than the matching threshold is determined as the target user;
[0146] When the matching value corresponding to each user information in the user management database is less than or equal to the preset matching threshold, the target user corresponding to the summary information is added to the user management database.
[0147] In an exemplary implementation, when there is user information corresponding to a matching value greater than a matching threshold, after determining that the user corresponding to the user information having a matching value greater than the matching threshold is the target user, the method further includes:
[0148] Update the user information corresponding to the target user according to the summary information.
[0149] It should be noted that technical personnel in the relevant field can clearly understand that for the convenience and brevity of description, the specific working process of the above-mentioned user information processing can refer to the corresponding process in the embodiment of the aforementioned user information processing method, and will not be repeated here.
[0150] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The method implemented when the computer program is executed by a processor can refer to the various embodiments of the user information processing method of the present application.
[0151] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.
[0152] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0153] It should also be understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.
[0154] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific implementation mode of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A user information processing method, characterized in that: include: Get the conversation text data; Extracting summary information of the conversation text data; Entering the summary information into a preset user management library; According to the summary information, searching the user management database for a target user corresponding to the summary information; Output the user information corresponding to the target user.
2. The user information processing method according to claim 1, characterized in that: The extracting summary information of the conversation text data includes: Segmenting the conversation text data to obtain a plurality of text units; According to the plurality of the text units, a node connection graph is constructed, wherein the node connection graph includes a plurality of nodes and link relationships between the nodes, and each of the nodes corresponds to one of the text units; Based on a preset iterative calculation formula, the weight values corresponding to each of the text units are calculated, and when an iteration termination condition is met, the node weight values corresponding to each of the text units are determined; The summary information of the conversation text data is determined according to the plurality of node weight values.
3. The user information processing method according to claim 2, characterized in that: Determining summary information of the conversation text data according to the plurality of node weight values includes: Determining a target text unit according to the plurality of node weight values, wherein the node weight value of the target text unit is greater than the node weight values of text units other than the target text unit in the plurality of text units; According to the target text unit, summary information of the dialogue text data is determined.
4. The user information processing method according to claim 2, characterized in that: The iterative calculation formula is: Among them, V i Represents the node corresponding to the i-th text unit; V j V represents the node corresponding to the jth text unit; k Indicates the node corresponding to the kth text unit; WS(V i ) represents the weight of the i-th text unit; d is the preset coefficient; w ji Represents node V j To Node V i The weight of the link relationship; WS(V j ) represents the weight of the jth text unit; Out(V j ) represents the node V j A first node set having a first link relationship, wherein the first link relationship is node V j The link relationship to the nodes in the first node set, In(V i ) represents the node V i A second node set having a second link relationship, wherein the second link relationship is from a node in the second node set to a node V i The link relationship of jk Represents node V j To Node V k The weight of the link relationship.
5. The user information processing method according to claim 1, characterized in that: The step of searching the user management library for a target user corresponding to the summary information according to the summary information includes: Matching the summary information with the user information in the user management database to obtain a matching value between the summary information and the user information; The target user corresponding to the summary information is determined according to the matching value corresponding to the user information and a preset matching threshold.
6. The user information processing method according to claim 5, characterized in that: The determining, according to the matching value corresponding to the user information and a preset matching threshold, a target user corresponding to the summary information includes: When the matching value corresponding to the user information is greater than the matching threshold, determining the user corresponding to the user information having the matching value greater than the matching threshold as the target user; When the matching value corresponding to each piece of user information in the user management database is less than or equal to a preset matching threshold, the target user corresponding to the summary information is added to the user management database.
7. The user information processing method according to claim 6, characterized in that: When the matching value corresponding to the user information is greater than the matching threshold, after determining that the user corresponding to the user information having the matching value greater than the matching threshold is the target user, the method further includes: The user information corresponding to the target user is updated according to the summary information.
8. A user information processing device, characterized in that: include: An acquisition module, used to acquire conversation text data; An information extraction module, used to extract summary information of the conversation text data; An information input module, used for inputting the summary information into a preset user management library; A search module, configured to search the user management database for a target user corresponding to the summary information according to the summary information; The output module is used to output the user information corresponding to the target user.
9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the user information processing method according to any one of claims 1 to 7 when executing the computer program.
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 user information processing method according to any one of claims 1 to 7 are implemented.