Conversation record processing method and related apparatus

Abstract

The embodiment of the application discloses a conversation record processing method and a related device, the method comprises the following steps: obtaining a conversation record; screening the conversation record to obtain a target conversation record; designing a prompt word corresponding to the target conversation record, wherein the prompt word is used to indicate that a preset model is trained to obtain a work matter related to a work log; calling the preset model, inputting the target conversation record into the preset model according to the prompt word, and obtaining conversation record summary data; and performing data display on the conversation record summary data according to a work log display template. The embodiment of the application is beneficial to improving work efficiency.

Description

Technical Field

[0001] This application relates to the field of electronic equipment technology, specifically to a method and apparatus for processing dialogue records. Background Technology

[0002] With the increasing popularity of chat products, many companies now use the chat function of these products to distribute tasks in groups and exchange work-related matters.

[0003] However, as the conversations accumulate, employees may spend more than half of their time each day communicating with other employees about work matters and checking group updates. Near the end of each day or week, they also need to compile daily or weekly reports to review the day's or week's work or project progress and report to management. This requires them to spend a lot of time and energy reviewing chat logs or conversation records and compiling their own work logs, which leads to a decline in work efficiency. Summary of the Invention

[0004] This application provides a method and related apparatus for processing dialogue records, which helps to improve work efficiency.

[0005] In a first aspect, embodiments of this application provide a method for processing dialogue records, applied to an electronic device, the method comprising:

[0006] Get conversation history;

[0007] Filter the dialogue records to obtain the target dialogue records;

[0008] Design prompt words corresponding to the target dialogue record, wherein the prompt words are used to indicate the work items related to the work log obtained by the preset model training;

[0009] The preset model is invoked, and the target dialogue record is input into the preset model according to the prompt words to obtain dialogue record summary data;

[0010] Based on the work log display template, the summary data of the dialogue records is displayed.

[0011] Secondly, embodiments of this application provide a dialogue record processing apparatus, which is applied to an electronic device. The apparatus includes: an acquisition unit, a filtering unit, a design unit, a recall unit, and a display unit.

[0012] The acquisition unit is used to acquire dialogue records;

[0013] The filtering unit is used to filter the dialogue records to obtain the target dialogue records;

[0014] The design unit is used to design prompt words corresponding to the target dialogue record, wherein the prompt words are used to indicate the work items related to the work log obtained by the preset model training;

[0015] The calling unit is used to call the preset model, input the target dialogue record into the preset model according to the prompt words, and obtain dialogue record summary data;

[0016] The display unit is used to display the summary data of the dialogue records according to the work log display template.

[0017] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for performing steps in any method of the first aspect of this application.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in any method of the first aspect of this application.

[0019] Fifthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in any method of the first aspect of this application. The computer program product may be a software installation package.

[0020] As can be seen, in this embodiment, the process involves: acquiring dialogue records; filtering the dialogue records to obtain target dialogue records; designing prompts corresponding to the target dialogue records, wherein the prompts are used to instruct a preset model to train work items related to the work log; calling the preset model and inputting the target dialogue records into the preset model according to the prompts to obtain dialogue record summary data; and displaying the dialogue record summary data according to a work log display template. Thus, the electronic device can process the target dialogue records by calling the preset model to obtain dialogue record summary data, and then display the dialogue record summary data through a work log display template to complete the work log display. This eliminates the need for manual work log entry, thereby improving work efficiency. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the structure of a dialogue record processing system provided in an embodiment of this application;

[0023] Figure 2A This is a flowchart illustrating a dialogue record processing method provided in an embodiment of this application;

[0024] Figure 2B This is a schematic diagram illustrating a dialogue record provided in an embodiment of this application;

[0025] Figure 2C This is a schematic diagram illustrating a summary of dialogue records provided in an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0027] Figure 4 This is a block diagram of the functional units of a dialogue record processing device provided in an embodiment of this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0029] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0030] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0031] The electronic device can be a portable electronic device that also includes other functions such as a personal digital assistant and / or music player, such as a mobile phone, tablet computer, terminal device, wearable electronic device with wireless communication capabilities (such as a smartwatch, smart glasses), in-vehicle device, etc. Exemplary embodiments of the portable electronic device include, but are not limited to, portable electronic devices running iOS, Android, Microsoft systems, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer. It should also be understood that in some other embodiments, the aforementioned electronic device may not be a portable electronic device, but a desktop computer.

[0032] Currently, most company employees frequently need to use communication software to communicate with business stakeholders or colleagues regarding work-related matters, such as the internal TeamTalk communication tool. After the end of each day or week, employees need to compile daily or weekly work reports, which are often contained in the chat history of these communication software messages. Employees need to review their current work status, the progress of work tasks, and report results to management based on the compiled daily / weekly work reports.

[0033] However, most employees may spend more than half of their time each day communicating with other employees about work matters and checking group updates. Near the end of the workday or week, they also need to compile daily or weekly reports to review the day's or week's work content or project progress and report to management. This requires them to spend a lot of time and energy looking through chat logs or conversation records and compiling their own work logs, which leads to a decrease in work efficiency.

[0034] To address the aforementioned problems, this application proposes a dialogue recording processing method and related apparatus, which will be described in detail below.

[0035] Please see Figure 1 , Figure 1 This is a schematic diagram of the structure of a dialogue record processing system provided in this application; the system may include: a dialogue record acquisition module, a dialogue record filtering module, a work log generation module, a work log display module, and a work log saving module.

[0036] The conversation record acquisition module can be used by electronic devices to acquire daily or weekly contact conversation records and / or daily or weekly group conversation records from at least one chat software or application data source.

[0037] The dialogue record filtering module is used to perform initial screening of the above dialogue records to obtain the target dialogue records.

[0038] The work log generation module is used to design prompt words corresponding to the target dialogue record and call the preset model. Based on the prompt words, the target dialogue record is input into the preset model to obtain the dialogue record summary data.

[0039] The work log display module is used to display the summary data of the above dialogue records, thus obtaining the work log.

[0040] The work log saving module is used to push work logs to users and save them in the system in response to user modifications or save operations.

[0041] Please see Figure 2A , Figure 2A This is a flowchart illustrating a dialogue record processing method provided in an embodiment of this application, applied to an electronic device. As shown in the figure, the dialogue record processing method includes the following operations.

[0042] S201. Obtain the conversation history.

[0043] The aforementioned chat logs were obtained by the electronic device from at least one chat software data source.

[0044] The aforementioned conversation records can be conversation records of one or more contacts who have communicated and interacted with the user corresponding to the electronic device over a period of time (e.g., daily, weekly, monthly, or set by the user); or conversation records of one or more groups over a period of time.

[0045] The aforementioned chat logs can be read or unread by the user. When the chat logs correspond to a group, after the data is summarized and displayed through this application, the user does not need to view every group or follow every message in the group. The user can understand the latest dynamics in each group through the displayed work logs, which helps to improve work efficiency and ensures that no key information is missed.

[0046] The aforementioned chat logs may include at least one of the following: images, text, contact names, contact positions, chat times, group titles, group members, etc., without limitation.

[0047] It should be noted that in this application, "multiple" can refer to two or more, and is not limited to this.

[0048] S202. Filter the dialogue records to obtain the target dialogue records.

[0049] The aforementioned target conversation records may refer to conversation records that have been filtered by the user. These conversation records can be used to generate work logs, work schedules, work items, casual conversations, etc., and are not limited here.

[0050] For example, an electronic device can instruct a user to select function options on a filtering page to set filtering criteria for conversation records. For instance, a user can select a specific contact or group through options in the function options (e.g., developers, testers, product personnel, etc., or fixed contacts A, B, etc.) to extract the target conversation records corresponding to that specific contact or group.

[0051] For example, users can select to generate a work log through the function options. This allows them to filter out non-work-related content from the conversation log to obtain the target conversation log, such as... Figure 2B The diagram shows a sample dialogue record. This dialogue record corresponds to group A. Non-work-related content, such as descriptions of eating, can be filtered out from the dialogue record. Specifically, the dialogue records of tester B, tester C, and developer B containing non-work-related content can be filtered out to obtain the target dialogue record related to work matters.

[0052] S203. Design prompt words corresponding to the target dialogue record, wherein the prompt words are used to indicate the work items related to the work log obtained by the preset model training;

[0053] S204. Call the preset model, input the target dialogue record into the preset model according to the prompt words, and obtain the dialogue record summary data;

[0054] The prompt word is used to indicate filtering operations or task generation for work-related items in the work log, and can also indicate job responsibilities, job roles, etc. in a preset model, without limitation. It can be set by logically describing task objectives, related operations, and user requirements. Of course, the prompt word can be set by the user or by the system default, without limitation.

[0055] For example, if a user instructs an electronic device to generate a work log through a function option, the prompt word, based on the above design, controls the preset model's job responsibilities to perform tasks such as filtering work-related items or answering tasks, etc., without limitation, so as to obtain summary data of dialogue records used to present summaries of work logs and briefings of groups corresponding to target dialogue records.

[0056] For example, the aforementioned tasks could be completed or incomplete tasks by users in group chats or contact chats, etc., without any limitation.

[0057] The aforementioned preset models can be user-defined or system defaults, and are not limited here. For example, the preset model can be the ChatGLM model, which can be trained using P-Tuning V2 for fin-tune to obtain dialogue record summary data. This dialogue record summary data is used to generate and display the work log.

[0058] Among them, the ChatGLM model mentioned above is open source. P-Tuning V2 has reduced the parameters that need to be fine-tuned to 0.1% to 3% of the original, which greatly speeds up the training speed. Finally, using the optimized prompt words can make the output of the large language model more standardized and structured, and the resulting dialogue record summary data more accurate.

[0059] In practice, electronic devices can read text data from the target dialogue record through a preset model, and then segment and vectorize the text data. The preset question (which can be determined based on the prompt words) is vectorized. Then, at least one text vector with the highest similarity to the question vector can be matched from the text vectors. The target text data corresponding to at least one text vector is added to the prompt words as context and question, and an answer is generated, which is the dialogue record summary data.

[0060] S205. Based on the work log display template, display the summary data of the dialogue records.

[0061] The work log display template can be set by the user or by the system default, and no restrictions are imposed here.

[0062] Specifically, the setting or generation of the above-mentioned work log display template can be determined based on the prompt words, such as the task objectives, related operations, and user needs in the prompt words.

[0063] As can be seen, the dialogue record processing method described in this application involves: acquiring dialogue records; filtering the dialogue records to obtain target dialogue records; designing prompt words corresponding to the target dialogue records, wherein the prompt words are used to instruct a preset model to train work items related to the work log; calling the preset model and inputting the target dialogue records into the preset model according to the prompt words to obtain dialogue record summary data; and displaying the dialogue record summary data according to a work log display template. Thus, electronic devices can process target dialogue records by calling the preset model to obtain dialogue record summary data, and then display the dialogue record summary data through a work log display template to complete the work log display, eliminating the need for manual work log entry and improving work efficiency.

[0064] In one possible example, the conversation records correspond to multiple groups and / or multiple contacts; the method for filtering the conversation records to obtain target conversation records may include the following steps: feature-tagging the conversation records corresponding to the multiple groups and / or multiple contacts respectively to obtain feature tags corresponding to each group and / or contact's conversation record; assigning common content identifiers to feature tags with the same attributes among the feature tags corresponding to each group and / or contact's conversation record; filtering the conversation records based on the feature tags and common content identifiers corresponding to each group and / or contact's conversation record to obtain the target conversation record corresponding to each group and / or contact.

[0065] The aforementioned feature tags may include at least one of the following: group title, conversation text, work items, work progress, contact person name, contact person position, conversation time, group members, etc., without limitation.

[0066] For example, the contact person's job title mentioned above may include at least one of the following: tester, developer, product manager, etc., without limitation.

[0067] Different feature tags correspond to different attributes. For example, for the feature tag "work item", the corresponding attributes could be "test", "fix patch", etc. Feature tags with the same attributes can be marked with common content identifiers to help evaluate whether the conversation records corresponding to the feature tags corresponding to each common content identifier meet the user's needs when filtering conversation records (this can be reflected in the function options later).

[0068] Furthermore, this common content representation can also be used to optimize target dialogue records in the future, and can also be used to perform self-checks on the dialogue record summary data after generating work logs, and evaluate the effect of the preset model, such as whether the correct target dialogue records or feature labels have been addressed.

[0069] As can be seen in this example, if a user has joined many groups or added many contacts, the chat history corresponding to each group or contact can be finely filtered, and feature tags with the same attributes can be marked with common content, which helps to improve the filtering efficiency.

[0070] In one possible example, the method of filtering the conversation records based on the feature tags and common content identifiers corresponding to the conversation records of each group and / or contact to obtain the target conversation records corresponding to each group and / or contact may include the following steps: in response to the user's function options set for the conversation records, determining the correlation value between the feature tags corresponding to the conversation records of each group and / or contact and the function options; for any feature tag corresponding to any group and / or contact, if the correlation value between the feature tag and the function option is greater than or equal to a preset threshold, then the conversation record corresponding to the feature tag is taken as the target conversation record; and if the feature tag corresponds to the common content identifier, then the conversation record corresponding to the same common content identifier is taken as the target conversation record, thus obtaining the target conversation records corresponding to each group and / or contact.

[0071] The aforementioned functional options are used to reflect user needs and may include multiple functional components. The functional options may include various types, such as allowing users to choose whether to delete non-work-related content, or allowing users to choose whether to generate work logs, work schedules, work items, chat records, etc. There are no limitations on this. They may also be used for users to filter the groups, contacts, etc. that they want to select.

[0072] Specifically, the correlation value between feature tags and different types of function options can be set in advance. This correlation value can be used to indicate the association between feature tags and function options. The higher the correlation value, the higher the association between the dialogue record corresponding to the feature tag and the function option.

[0073] For example, when a user sets the type of the function option for the chat history to work log, the correlation values ​​between the work items and work progress and this function option can be set to 90% and 80% respectively, which are higher than the correlation values ​​of other feature tags, such as contact person position 60%, group title 50%, contact person position 20%, etc.

[0074] The aforementioned preset threshold can be set by the user or by the system default, and is not limited here. Considering that the relevant values ​​of the associated feature tags may vary for different types of function options, in order to ensure the accuracy of the filtered target dialogue records, the preset threshold can be determined according to the type of function option. For example, for function options of the work log type, the corresponding preset threshold can be set to 70%, and for work schedules, the corresponding preset threshold can be set to 60%.

[0075] The electronic device can be configured to have the same value for a feature tag with common content identifier as its associated function option. Since the same feature tag corresponds to different attributes, when the electronic device filters target conversation records for any feature tag corresponding to any group or contact, as long as the feature tag corresponds to a common content tag, there is no need to repeatedly compare or determine the corresponding value. The conversation records corresponding to the feature tags with the same common content identifier can be directly used as the target conversation records without repeated filtering.

[0076] As can be seen, in this example, only one feature tag corresponding to any group and / or contact is used as an example. In the specific implementation, multiple feature tags corresponding to multiple groups or multiple contacts can be filtered in the same way. For those with common content identifiers, there is no need to filter repeatedly. In this way, the target dialogue records of each group and / or contact that meet the user's needs and are associated with or matched with the function options can be obtained, which is conducive to improving the filtering efficiency. Moreover, dialogue records with different attributes of the same feature tag will not be missed, which is conducive to improving the filtering effect.

[0077] In one possible example, the method for designing the prompt words corresponding to the target conversation record may include the following steps: determining the user's identity; determining the permission scope corresponding to the work log display template based on the user identity and the function options; and designing the prompt words based on the permission scope and the target conversation record corresponding to each group and / or contact.

[0078] The user identities mentioned above can include at least one of the following: ordinary employees, team leaders, middle managers, senior managers, etc., without limitation. Each user identity has different responsibilities, and therefore, different work log display templates or the final generated work logs. Tables 1 and 2 are schematic diagrams of work log display templates for different user identities. Table 1 corresponds to the work log of an ordinary employee, and Table 2 corresponds to the work log of a middle manager. After the user selects a type in the function options, for example, if the function option is "work log," the permission scope of the corresponding work log display template differs for different user identities. For example, the work log permission scope of an ordinary employee is limited to their own work log, while the work log permission scope of a middle manager is the work logs of multiple contacts or groups (or ordinary employees).

[0079] Table 1. Work Log of Ordinary Employees

[0080]

[0081] Table 2. Work Logs of Middle-Level Managers

[0082]

[0083] In practice, electronic devices can design filtering operations or task generation items for work log-related work items based on the scope of permissions and the target dialogue records corresponding to each group or contact, so as to obtain prompt words.

[0084] For example, the prompt could be set as follows: You are an editor expert (set a pre-defined job identity), and your task is to summarize the conversation content and help company employees output work logs (job responsibilities). Before summarizing, you need to remove non-work-related conversation content from the conversation, such as conversations about food, clothing, housing, and transportation. Finally, summarize the remaining work-related content in no more than 100 words (work items, answers, etc.).

[0085] As can be seen in this example, the electronic device can design prompts for the target dialogue records corresponding to each group and / or contact according to user needs. This helps to instruct the preset model to train the target dialogue records and obtain a summary of dialogue records that meet user needs, which is beneficial to improving user experience.

[0086] In one possible example, the method of calling the preset model and inputting the target dialogue record into the preset model according to the prompt word to obtain dialogue record summary data may include the following steps: calling the preset model and inputting the target dialogue record corresponding to each group and / or contact into the preset model one by one; controlling the preset model to process the target dialogue record corresponding to each group and / or contact according to the prompt word to obtain the dialogue record summary data corresponding to each group and / or contact.

[0087] In one possible example, after obtaining the summary data of the dialogue records, the above method may further include the following step: outputting the summary data of the dialogue records in a preset format.

[0088] The electronic device can train on the target dialogue records corresponding to each group and / or contact one by one to obtain the summary data of the dialogue records corresponding to each group and / or contact.

[0089] The preset format can be set by the user or by the system default, and there is no limitation here; for example, it can be in JSON format.

[0090] In subsequent steps, the electronic device can summarize the data from each conversation and adapt it to the work log display template, such as... Figure 2C The image shown is a schematic diagram illustrating a summary of dialogue records. Specifically, it represents the output of a preset model and... Figure 2B The summary data of the target dialogue records for the corresponding group can be displayed in the work log display template shown in Table 2.

[0091] As can be seen in this example, the electronic device can process each contact and / or group individually. Especially for groups with a lot of unread messages, users do not need to view each group and pay attention to the messages or conversation records in the group. The latest dynamics in the group can be displayed through the work log generated by the summary data of the conversation records, without missing any key information. This is conducive to improving work efficiency and reducing costs.

[0092] In one possible example, the method of displaying the summary data of the dialogue records according to the work log display template may include the following steps: determining the display type and display module in the work log display template; and displaying the summary data of the dialogue records output in the preset format in a structured manner according to the display type and display module in the work log display template.

[0093] The aforementioned display types may include at least one of the following: summary data of conversation records, task content, task progress, related persons of the task, etc., without limitation. Display modules may include at least one of the following: group information summary, contact information summary, work tasks, etc., without limitation; different user identities will have different display modules in the work log display template used to reflect the scope of permissions. For example, for ordinary employees, the display modules may include work tasks, while for management employees, the display modules may include contact information summary, group information summary, work tasks, etc.

[0094] The electronic device can generate display content based on the summary data of the conversation records, as well as feature tags used to represent contact names, contact positions, work progress and work items, and display them in the corresponding display type.

[0095] For example, as shown in Table 3 below, this is a schematic diagram of a work log display template, which may include multiple display types, such as conversation record summary data, work item display module corresponding to item content, item progress and item associated persons, and display modules may include work items, contact information briefings and group information briefings, etc.

[0096] Table 3. Work Log Display Template

[0097]

[0098] As can be seen in this example, the summary data of the dialogue records can be displayed as a work log by displaying the display type and display module, so as to obtain a work log adapted to the user. Users do not need to extract key information from a large number of dialogue records, which reduces the time and effort users spend in editing work logs and helps to improve work efficiency.

[0099] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. As shown in the figure, the electronic device includes a processor, a memory, a communication interface, and one or more programs applied to the electronic device. The one or more programs are stored in the memory and are configured to be executed by the processor according to the following instructions:

[0100] Get conversation history;

[0101] Filter the dialogue records to obtain the target dialogue records;

[0102] Design prompt words corresponding to the target dialogue record, wherein the prompt words are used to indicate the work items related to the work log obtained by the preset model training;

[0103] The preset model is invoked, and the target dialogue record is input into the preset model according to the prompt words to obtain dialogue record summary data;

[0104] Based on the work log display template, the summary data of the dialogue records is displayed.

[0105] As can be seen, the electronic device described in this embodiment acquires dialogue records; filters the dialogue records to obtain target dialogue records; designs prompt words corresponding to the target dialogue records, wherein the prompt words are used to instruct a preset model to train work items related to the work log; calls the preset model, inputs the target dialogue records into the preset model according to the prompt words, and obtains dialogue record summary data; and displays the dialogue record summary data according to the work log display template. Thus, the electronic device can process the target dialogue records by calling the preset model to obtain dialogue record summary data, and then display the dialogue record summary data through the work log display template to complete the work log display, eliminating the need for manual work log entry and improving work efficiency.

[0106] In one possible example, where the conversation records correspond to multiple groups and / or multiple contacts; regarding the filtering of the conversation records to obtain the target conversation records, the above procedure includes instructions for performing the following steps:

[0107] The dialogue records corresponding to the multiple groups and / or multiple contacts are feature-tagged to obtain the feature tags corresponding to the dialogue records of each group and / or contact.

[0108] Mark the feature tags with the same attributes in the feature tags corresponding to the dialogue records of each of the groups and / or contacts with common content identifiers;

[0109] Based on the feature tags and common content identifiers corresponding to the dialogue records for each group and / or contact, the dialogue records are filtered to obtain the target dialogue records corresponding to each group and / or contact.

[0110] In one possible example, regarding the step of filtering the conversation records based on the feature tags and common content identifiers corresponding to each of the groups and / or contacts to obtain the target conversation records corresponding to each of the groups and / or contacts, the above procedure includes instructions for performing the following steps:

[0111] In response to the user's function options for the chat history settings, determine the correlation value between the feature tags corresponding to the chat history for each group and / or contact and the function options;

[0112] For any of the feature tags corresponding to any of the groups and / or the contacts, if the correlation value between the feature tag and the function option is greater than or equal to a preset threshold, then the conversation record corresponding to the feature tag is taken as the target conversation record; and,

[0113] If the feature tag corresponds to the common content identifier, then the dialogue record corresponding to the same common content identifier is taken as the target dialogue record, and the target dialogue record corresponding to each group and / or contact is obtained.

[0114] In one possible example, regarding the design of the prompts corresponding to the target dialogue record, the above procedure includes instructions for performing the following steps:

[0115] Determine the user's identity;

[0116] Based on the user identity and the function options, determine the permission scope corresponding to the work log display template;

[0117] The prompt words are designed based on the permission scope and the target conversation records corresponding to each group and / or contact.

[0118] In one possible example, regarding the invocation of the preset model, inputting the target dialogue record into the preset model according to the prompt words, and obtaining dialogue record summary data, the above procedure includes instructions for performing the following steps:

[0119] Invoke the preset model and input the target dialogue records corresponding to each of the groups and / or contacts into the preset model one by one;

[0120] The preset model is controlled to process the target dialogue records corresponding to each group and / or contact according to the prompt words, so as to obtain the dialogue record summary data corresponding to each group and / or contact.

[0121] In one possible example, after obtaining the summary data of the dialogue records, the above procedure includes instructions for performing the following steps:

[0122] The summary data of the dialogue records will be output in a preset format.

[0123] In one possible example, regarding the data display of the summary data of the dialogue records based on the work log display template, the above procedure includes instructions for performing the following steps:

[0124] Determine the display type and display module in the work log display template;

[0125] The summary data of the dialogue records output in the preset format is displayed in the work log display template in a structured manner according to the display type and display module.

[0126] The above primarily describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the electronic device includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0127] This application embodiment can divide the electronic device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0128] When dividing each function into modules according to its corresponding function. Figure 4 A schematic diagram of a dialogue recording processing device is shown, such as Figure 4 As shown, the device is applied to an electronic device. The dialogue recording processing device 400 may include: an acquisition unit 401, a filtering unit 402, a design unit 403, a recall unit 404, and a display unit 405, wherein...

[0129] The acquisition unit 401 is used to acquire dialogue records;

[0130] The filtering unit 402 is used to filter the dialogue records to obtain the target dialogue records;

[0131] The design unit 403 is used to design prompt words corresponding to the target dialogue record, wherein the prompt words are used to indicate the work items related to the work log obtained by the preset model training;

[0132] The calling unit 404 is used to call the preset model, input the target dialogue record into the preset model according to the prompt words, and obtain dialogue record summary data;

[0133] The display unit 405 is used to display the summary data of the dialogue records according to the work log display template.

[0134] As can be seen, the dialogue record processing device provided in this application embodiment acquires dialogue records; filters the dialogue records to obtain target dialogue records; designs prompt words corresponding to the target dialogue records, wherein the prompt words are used to indicate work items related to the work log obtained by training a preset model; calls the preset model, inputs the target dialogue records into the preset model according to the prompt words, and obtains dialogue record summary data; and displays the dialogue record summary data according to the work log display template. Thus, electronic devices can process target dialogue records by calling the preset model to obtain dialogue record summary data, and display the dialogue record summary data through the work log display template to complete the work log display, eliminating the need for manual work log entry and improving work efficiency.

[0135] In one possible example, where the conversation records correspond to multiple groups and / or multiple contacts; regarding the filtering of the conversation records to obtain the target conversation records, the filtering unit 402 is specifically used for:

[0136] The dialogue records corresponding to the multiple groups and / or multiple contacts are feature-tagged to obtain the feature tags corresponding to the dialogue records of each group and / or contact.

[0137] Mark the feature tags with the same attributes in the feature tags corresponding to the dialogue records of each of the groups and / or contacts with common content identifiers;

[0138] Based on the feature tags and common content identifiers corresponding to the dialogue records for each group and / or contact, the dialogue records are filtered to obtain the target dialogue records corresponding to each group and / or contact.

[0139] In one possible example, regarding the step of filtering the dialogue records based on the feature tags and common content identifiers corresponding to each group and / or contact to obtain the target dialogue records corresponding to each group and / or contact, the filtering unit 402 is specifically used for:

[0140] In response to the user's function options for the chat history settings, determine the correlation value between the feature tags corresponding to the chat history for each group and / or contact and the function options;

[0141] For any of the feature tags corresponding to any of the groups and / or the contacts, if the correlation value between the feature tag and the function option is greater than or equal to a preset threshold, then the conversation record corresponding to the feature tag is taken as the target conversation record; and,

[0142] If the feature tag corresponds to the common content identifier, then the dialogue record corresponding to the same common content identifier is taken as the target dialogue record, and the target dialogue record corresponding to each group and / or contact is obtained.

[0143] In one possible example, regarding the design of the prompt words corresponding to the target dialogue record, the design unit 403 is specifically used for:

[0144] Determine the user's identity;

[0145] Based on the user identity and the function options, determine the permission scope corresponding to the work log display template;

[0146] The prompt words are designed based on the permission scope and the target conversation records corresponding to each group and / or contact.

[0147] In one possible example, regarding the invocation of the preset model, inputting the target dialogue record into the preset model according to the prompt words to obtain dialogue record summary data, the aforementioned invocation unit 404 is specifically used for:

[0148] Invoke the preset model and input the target dialogue records corresponding to each of the groups and / or contacts into the preset model one by one;

[0149] The preset model is controlled to process the target dialogue records corresponding to each group and / or contact according to the prompt words, so as to obtain the dialogue record summary data corresponding to each group and / or contact.

[0150] In one possible example, after obtaining the summary data of the dialogue records, the aforementioned display unit 405 is further used for:

[0151] The summary data of the dialogue records will be output in a preset format.

[0152] In one possible example, regarding the data display of the summary data of the dialogue records based on the work log display template, the display unit 405 is specifically used for:

[0153] Determine the display type and display module in the work log display template;

[0154] The summary data of the dialogue records output in the preset format is displayed in the work log display template in a structured manner according to the display type and display module.

[0155] It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0156] The electronic device provided in this embodiment is used to execute the above-described dialogue record processing method, and therefore can achieve the same effect as the above-described implementation method.

[0157] When using integrated units, the electronic device may include a processing module, a storage module, and a communication module. The processing module can be used to control and manage the actions of the electronic device; for example, it can support the electronic device in executing the steps performed by the acquisition unit 401, the filtering unit 402, the design unit 403, the calling unit 404, and the display unit 405. The storage module can support the electronic device in executing stored program code and data. The communication module can support communication between the electronic device and other devices.

[0158] The processing module can be a processor or a controller. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory. The communication module can specifically be a radio frequency circuit, a Bluetooth chip, a Wi-Fi chip, or other devices that interact with other electronic devices.

[0159] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0160] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0161] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0162] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0163] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0164] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0165] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0166] If the integrated units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0167] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk, etc.

[0168] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A dialogue recording processing method, applied to an electronic device, characterized in that, include: Obtain conversation records, which correspond to multiple groups and / or multiple contacts; The process involves filtering the dialogue records to obtain target dialogue records. Specifically, the dialogue records corresponding to the multiple groups and / or multiple contacts are characterized to obtain feature tags for each group and / or contact's corresponding dialogue record. Feature tags with the same attributes among the feature tags for each group and / or contact's corresponding dialogue record are marked with a common content identifier. In response to user-defined function options for the dialogue records, the correlation value between the feature tags and function options for each group and / or contact's corresponding dialogue record is determined. For any feature tag corresponding to any group and / or contact, if the correlation value between the feature tag and the function option is greater than or equal to a preset threshold, the dialogue record corresponding to that feature tag is selected as the target dialogue record. Furthermore, if the feature tag corresponds to a common content identifier, the dialogue records corresponding to the same common content identifier are selected as the target dialogue records, thus obtaining the target dialogue records for each group and / or contact. Design prompt words corresponding to the target dialogue record, wherein the prompt words are used to indicate the work items related to the work log obtained by the preset model training; The target dialogue record is input into the preset model, and the preset model is controlled to process the target dialogue record according to the prompt words to obtain dialogue record summary data; Based on the work log display template, the summary data of the dialogue records is displayed.

2. The method according to claim 1, characterized in that, The design of the prompt words corresponding to the target dialogue record includes: Determine the user's identity; Based on the user identity and the function options, determine the permission scope corresponding to the work log display template; The prompt words are designed based on the permission scope and the target conversation records corresponding to each group and / or contact.

3. The method according to claim 2, characterized in that, The step of inputting the target dialogue record into the preset model and controlling the preset model to process the target dialogue record according to the prompt words to obtain dialogue record summary data includes: Invoke the preset model and input the target dialogue records corresponding to each of the groups and / or contacts into the preset model one by one; The preset model is controlled to process the target dialogue records corresponding to each group and / or contact according to the prompt words, so as to obtain the dialogue record summary data corresponding to each group and / or contact.

4. The method according to claim 1 or 2, characterized in that, After obtaining the summary data of the dialogue records, the method further includes: The summary data of the dialogue records will be output in a preset format.

5. The method according to claim 4, characterized in that, The step of displaying the summary data of the dialogue records according to the work log display template includes: Determine the display type and display module in the work log display template; The summary data of the dialogue records output in the preset format is displayed in the work log display template in a structured manner according to the display type and display module.

6. A dialogue recording processing device, characterized in that, The device is applied to an electronic device, and the device includes: an acquisition unit, a filtering unit, a design unit, a calling unit, and a display unit, wherein... The acquisition unit is used to acquire conversation records, which correspond to multiple groups and / or multiple contacts; The filtering unit is used to filter the dialogue records to obtain target dialogue records, wherein: the dialogue records corresponding to the multiple groups and / or the multiple contacts are respectively characterized by feature tagging to obtain feature tags corresponding to the dialogue records of each group and / or contact; feature tags with the same attributes among the feature tags corresponding to the dialogue records of each group and / or contact are marked with common content identifiers; in response to the function options set by the user for the dialogue records, the correlation value between the feature tags corresponding to the dialogue records of each group and / or contact and the function options is determined; for any feature tag corresponding to any group and / or contact, if the correlation value between the feature tag and the function option is greater than or equal to a preset threshold, then the dialogue record corresponding to the feature tag is taken as the target dialogue record; and if the feature tag corresponds to a common content identifier, then the dialogue records corresponding to the same common content identifier are taken as the target dialogue records, thus obtaining the target dialogue records corresponding to each group and / or contact. The design unit is used to design prompt words corresponding to the target dialogue record, wherein the prompt words are used to indicate the work items related to the work log obtained by the preset model training; The calling unit is used to input the target dialogue record into the preset model and control the preset model to process the target dialogue record according to the prompt words to obtain dialogue record summary data; The display unit is used to display the summary data of the dialogue records according to the work log display template.

7. An electronic device, characterized in that, The method includes a processor, a memory, a communication interface, and one or more programs, said one or more programs being stored in the memory and configured to be executed by the processor, said programs including instructions for performing the steps of the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, A computer program for storing electronic data interchange is provided, wherein the computer program causes a computer to perform the method as described in any one of claims 1-5.

Images