Decision information determination method and device, electronic equipment and medium

Abstract

The invention discloses a decision information determination method and device, electronic equipment and a medium, which are used for accurately and efficiently determining decision information suitable for each family member to the greatest extent. In the method, after dialogue information among family members is obtained, the demand of each family member contained in the dialogue information is identified, and for each demand, the emotional preference weight coefficient of each family member for the demand can be identified based on the dialogue information among the family members; the speech weight coefficient of each family member can be obtained based on pre-stored portrait information of each family member, and the fusion weight coefficient of the demand is determined based on the emotional preference weight coefficient of each family member for the demand and the speech weight coefficient of each family member; and the decision information recommended to the family can be determined based on the fusion weight coefficient of each demand, so that the decision information suitable for each family member can be accurately and efficiently determined to the greatest extent.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and in particular, to a method, apparatus, electronic device, and medium for determining decision-making information. Background Art

[0002] Discussions and decisions among family members, such as for events like buying a house, planning a vacation, planning the way to educate children, and the way to support the elderly, are common scenarios in daily life. However, oral consultations among family members are prone to long discussions and it is difficult to reach a unanimous decision efficiently.

[0003] In view of this, how to assist family members in determining decision-making information suitable for each family member as accurately and efficiently as possible by means of technology is a technical problem that urgently needs to be solved at present. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and medium for determining decision-making information to determine decision-making information suitable for each family member as accurately and efficiently as possible.

[0005] In a first aspect, this application provides a method for determining decision-making information, and the method includes:

[0006] Obtain conversation information and identify the needs of each family member included in the conversation information;

[0007] For each of the needs, based on the conversation information, determine the emotional preference weight coefficient of each family member for this need; and based on the portrait information of each family member saved in advance, obtain the speech weight coefficient of each family member; based on the emotional preference weight coefficient and the speech weight coefficient, determine the fusion weight coefficient of this need;

[0008] Based on the fusion weight coefficient of each need, determine the recommended decision-making information.

[0009] In a possible implementation manner, after identifying the needs of each family member included in the conversation information and before determining the fusion weight coefficient of this need based on the emotional preference weight coefficient and the speech weight coefficient, the method further includes:

[0010] For each of the needs, based on the planned event information in the pre-saved family plan list, determine the matching degree of this need with the family plan list, and based on the matching degree, determine the planned matching degree weight coefficient of this need;

[0011] The determining the fusion weight coefficient of this need based on the emotional preference weight coefficient and the speech weight coefficient includes:

[0012] Determine the fusion weight coefficient of the requirement based on the emotional preference weight coefficient, the discourse weight coefficient, and the plan matching degree weight coefficient.

[0013] In a possible implementation manner, the method further includes:

[0014] Identify the target event type of the decision information, and determine the target decision template corresponding to the target event type according to the pre - saved correspondence between the event type and the decision template;

[0015] Fuse the decision information with the target decision template, and output the fused decision information.

[0016] In a possible implementation manner, after determining the target decision template corresponding to the target event type and before fusing the decision information with the target decision template, the method further includes:

[0017] Determine the matching degree between the field information in the target decision template and the field information in the decision information; if the matching degree is less than a preset matching degree threshold, update the field information in the target decision template according to the field information in the decision information, and based on the updated target decision template, perform the subsequent step of fusing the decision information with the target decision template.

[0018] In a possible implementation manner, the method further includes:

[0019] If an adjustment instruction for adjusting the decision information is received from the user, identify the preferred requirements carried in the adjustment instruction, and adjust the decision information based on the preferred requirements.

[0020] In a possible implementation manner, after obtaining the dialogue information and before identifying the requirements of each family member included in the dialogue information, the method further includes:

[0021] Identify the selected dialogue information of a set number of rounds at the end of the dialogue information, and determine the semantic information of the other dialogue information in the dialogue information except the selected dialogue information;

[0022] Based on the semantic information and the selected dialogue information, perform the subsequent step of identifying the requirements of each family member included in the dialogue information.

[0023] In a second aspect, the present application provides a decision information determination device, and the device includes:

[0024] An identification module, configured to obtain dialogue information and identify the requirements of each family member included in the dialogue information;

[0025] A determination module, configured to determine, for each of the said requirements, based on the conversation information, an emotional preference weight coefficient of each family member for this requirement; and based on the pre-stored portrait information of each family member, obtain a speech weight coefficient of each family member; based on the emotional preference weight coefficient and the speech weight coefficient, determine a fusion weight coefficient of this requirement.

[0026] A recommendation module, configured to determine recommended decision information based on the fusion weight coefficient of each of the said requirements.

[0027] In a possible implementation manner, the determination module is further configured to:

[0028] For each of the said requirements, based on the planned event information in the pre-stored family plan list, determine the matching degree of this requirement with the family plan list, and based on the matching degree, determine a planned matching degree weight coefficient of this requirement.

[0029] Based on the emotional preference weight coefficient, the speech weight coefficient, and the planned matching degree weight coefficient, determine the fusion weight coefficient of this requirement.

[0030] In a possible implementation manner, the device further includes:

[0031] A fusion module, configured to identify the target event type of the decision information, and based on the pre-stored corresponding relationship between the event type and the decision template, determine the target decision template corresponding to the target event type;

[0032] Fuse the decision information with the target decision template, and output the fused decision information.

[0033] In a possible implementation manner, the fusion module is further configured to:

[0034] Determine the matching degree between the field information in the target decision template and the field information in the decision information; if the matching degree is less than a preset matching degree threshold, update the field information in the target decision template according to the field information in the decision information, and based on the updated target decision template, perform the subsequent step of fusing the decision information with the target decision template.

[0035] In a possible implementation manner, the device further includes:

[0036] An adjustment module, configured to, if receiving an adjustment instruction for adjusting the decision information input by the user, identify the preferred requirement carried in the adjustment instruction, and based on the preferred requirement, adjust the decision information.

[0037] In a possible implementation manner, the identification module is further configured to:

[0038] Identify the selected dialogue information of the set number of rounds that is later in position in the said dialogue information, and determine the semantic information of the other dialogue information in the said dialogue information except the said selected dialogue information;

[0039] Based on the said semantic information and the said selected dialogue information, perform the subsequent steps of identifying the needs of each family member included in the said dialogue information.

[0040] In a third aspect, the present application provides an electronic device, which at least includes a processor and a memory. When the processor executes the computer program stored in the memory, it realizes the steps of the method according to any one of the first aspects.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it realizes the steps of the method according to any one of the first aspects.

[0042] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes: computer program code. When the computer program code runs on a computer, it causes the computer to execute the steps of the method according to any one of the above first aspects.

[0043] Since in the embodiments of the present application, after obtaining the dialogue information between family members, the needs of each family member included in the dialogue information can be identified. For each need, based on the dialogue information between family members, the emotional preference weight coefficient of each family member for this need can be identified, and based on the portrait information of each family member pre-stored, the speech weight coefficient of each family member can be obtained. After that, based on the emotional preference weight coefficient of each family member for this need and the speech weight coefficient of each family member, the fusion weight coefficient of this need can be determined. Finally, based on the fusion weight coefficient of each need, the decision information recommended to this family can be determined. Based on this, the balance can be found to the greatest extent accurately among the diverse personal needs, emotional preferences, and family member speech priorities of each family member, and the decision information suitable for each family member can be determined accurately and efficiently to the greatest extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the implementation manners in related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings.

[0045] Figure 1 Shows a schematic diagram of the first decision information determination process provided by some embodiments;

[0046] Figure 2 The schematic diagram of the second decision information determination process provided by some embodiments is shown;

[0047] Figure 3 The schematic diagram of the third decision information determination process provided by some embodiments is shown;

[0048] Figure 4 The schematic diagram of the fourth decision information determination process provided by some embodiments is shown;

[0049] Figure 5 The schematic diagram of the fifth decision information determination process provided by some embodiments is shown;

[0050] Figure 6 The schematic diagram of the sixth decision information determination process provided by some embodiments is shown;

[0051] Figure 7 The schematic diagram of the seventh decision information determination process provided by some embodiments is shown;

[0052] Figure 8 The schematic diagram of the eighth decision information determination process provided by some embodiments is shown;

[0053] Figure 9 The schematic diagram of a decision information determination device provided by some embodiments is shown;

[0054] Figure 10 The schematic diagram of the structure of an electronic device provided by some embodiments is shown. Detailed implementation manners

[0055] To make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present application. Without conflict, the embodiments in the present application and the features in the embodiments may be combined with each other arbitrarily. And although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than here.

[0056] In the description and claims of this application and the above-mentioned drawings, the terms "first" and "second" are used to distinguish different objects, rather than to describe a specific order. In addition, the term "comprising" and any variations thereof are intended to cover non-exclusive protection. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include steps or units not listed, or may optionally further include other steps or units inherent to these processes, methods, products, or devices. "Multiple" in this application may mean at least two, for example, it may be two, three, or more, and the embodiments of this application do not make limitations.

[0057] The following describes exemplary embodiments of this application with reference to the accompanying drawings, including various details of the embodiments of this application to facilitate understanding, which should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the disclosure of this application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted below. It should be noted that in the embodiments of this application, certain industry-existing solutions such as certain software, components, models, etc. may be mentioned, which should be considered exemplary, and their purpose is only to illustrate the feasibility in the implementation of the technical solution of this application, but it does not mean that the applicant has already or necessarily used this solution.

[0058] In the technical solution of this application, the acquisition, transmission, storage, use, etc. of data all comply with the requirements of relevant national laws and regulations.

[0059] In order to determine decision-making information suitable for each family member with the highest degree of accuracy and efficiency, embodiments of this application propose a method, apparatus, device, and medium for determining decision-making information. The following describes some preferred embodiments of this application with reference to the accompanying drawings of the specification.

[0060] Embodiment 1:

[0061] Figure 1 The first decision-making information determination process diagram provided by some embodiments is shown, as Figure 1 shown, and this process includes the following steps:

[0062] S101: Obtain conversation information and identify the needs of each family member included in the conversation information.

[0063] The decision-making information determination method provided by the embodiments of this application is applied to an electronic device, which may be a device such as a personal computer (PC), a mobile terminal, or a server, etc., and this application does not make specific limitations on this.

[0064] In a possible implementation, when it is necessary to assist family members in determining decision-making information suitable for each family member by means of technical means (electronic devices), the family members can click the button for obtaining conversation information in the electronic device. The electronic device can obtain the conversation information (chat content) uploaded by the family members, or can obtain the conversation information among family members regarding events such as purchasing a house, planning a vacation, planning the education method of children, and the support method for the elderly by recording the real-time chat information among family members. Specifically, the electronic device can obtain the conversation information among family members regarding a certain matter through the Hypertext Transfer Protocol (HTTP) request provided by the Application Programming Interface (API), or can obtain the conversation information among family members regarding a certain matter (event) through the WebSocket communication protocol. This application does not make specific limitations in this regard and will not elaborate further here.

[0065] In a possible implementation, after obtaining the conversation information among family members, in order to accurately and efficiently determine the decision-making information suitable for each family member to the greatest extent, the needs of each family member in the conversation information can be identified first. Specifically, the voice recognition and semantic recognition can be performed on the conversation information in the voice form, so as to identify the needs of each family member included in the conversation information. Exemplarily, the identified needs of family members can be: Dad wants to go to Beijing to play, Mom wants to go to Xi'an to play, the child wants to go to Tianjin to play, the child wants to play outdoors, etc. This application does not make specific limitations in this regard.

[0066] S102: For each of the said needs, based on the conversation information, determine the emotional preference weight coefficient of each family member for this need; and based on the portrait information of each family member pre-saved, obtain the speech weight coefficient of each family member; based on the emotional preference weight coefficient and the speech weight coefficient, determine the fusion weight coefficient of this need.

[0067] In a possible implementation, for each need of each family member, sentiment analysis can be performed on the above-mentioned conversation information by means of semantic analysis technology, so as to identify the sentiment preference weight coefficient of each family member for this need. Exemplarily, for the need that mom wants to go to [a certain place] to play, through sentiment analysis, the sentiment preference weight coefficient of dad for this need, the sentiment preference weight coefficient of mom for this need, and the sentiment preference weight coefficient of the child for this need can be identified respectively. For example, when through sentiment analysis, it is identified that mom really strongly wants to go to [a certain place] to play, the sentiment preference weight coefficient of mom for this need can be configured as the maximum weight value such as 1. When it is identified that dad is also relatively interested in going to [a certain place] to play, the sentiment preference weight coefficient of dad for this need can be configured as a relatively large weight value such as 0.8. When it is identified that the child has a neutral attitude towards going to [a certain place] to play, the sentiment preference weight coefficient of the child for this need can be configured as a relatively small weight value such as 0. Or when it is identified that the child is relatively repelled by going to [a certain place] to play, the sentiment preference coefficient of the child for this need can be configured as the minimum weight value such as -0.5. The present application does not make specific limitations on this, and it can be flexibly set according to needs. Among them, it can be that the larger the sentiment preference weight coefficient of the family member for this need, the more it is considered that the family member is inclined to this need. On the contrary, it is considered that the family member is more repelled by this need. It can also be that the smaller the sentiment preference weight coefficient of the family member for this need, the more it is considered that the family member is inclined to this need. On the contrary, it is considered that the family member is more repelled by this need. For the convenience of understanding, hereinafter, taking the case that the larger the sentiment preference weight coefficient of the family member for this need, the more it is considered that the family member is inclined to this need as an example, the decision information determination process provided by the embodiments of the present application will be explained.

[0068] In a possible implementation, in addition to being able to determine the emotional preference weight coefficient of each family member for any need, in order to accurately and efficiently determine the decision-making information suitable for each family member to the greatest extent, the speech weight coefficient of each family member can also be obtained based on the portrait information of each family member pre-saved (acquired). Herein, the present application does not specifically limit the portrait information of family members, which can be flexibly set according to requirements. Exemplarily, the portrait information may include the speech weight coefficient of each family member in the family. For example, the speech weight coefficient of mom is 0.8, and the speech weight coefficient of dad is 0.5, etc. The present application does not specifically limit the speech weight coefficient of each family member either, which can be flexibly set according to requirements. Among them, it can be that the greater the speech weight coefficient of a family member, the more important the opinion of this family member is considered (the higher the speech priority), or it can be that the smaller the speech weight coefficient of a family member, the less important the opinion of this family member is considered (the lower the speech priority). The present application does not make a specific limitation on this. For ease of understanding, hereinafter, taking the case where the greater the speech weight coefficient of a family member, the more important the opinion of this family member is, the process of determining the decision-making information provided in the embodiments of the present application will be explained and illustrated.

[0069] In a possible implementation, for each need in the dialogue information, after identifying the emotional preference weight coefficient of each family member for this need and the speech weight coefficient of each family member, the fusion weight coefficient of this need can be determined based on the emotional preference weight coefficient of each family member for this need and the speech weight coefficient of each family member. Exemplarily, for each need, the weighted sum value of the emotional preference weight coefficient of each family member for this need and the speech weight coefficient of each family member can be determined as the fusion weight coefficient of this need. For example, for a certain need, if the emotional preference weight coefficient of mom for this need is 1, the emotional preference weight coefficient of dad for this need is 0, and the emotional preference weight coefficient of the child for this need is -0.5, where the speech weight coefficient of mom is 0.8, and the speech weight coefficients of dad and the child are 0.5 respectively, the fusion weight coefficient of this need can be: 1×0.8 + 0×0.5 + (-0.5)×0.5 = 0.55.

[0070] S103: Determine the recommended decision-making information based on the fusion weight coefficient of each of the said needs.

[0071] In a possible implementation manner, based on the above method, after determining the fusion weight coefficients of the needs of each family member in the conversation information, the final recommended decision information can be determined based on the fusion weight coefficients of each need. For example, taking the event of discussing a travel as an example, for each category of needs such as travel destination, tourist attractions, travel dates, etc., among the needs of this category, the need with the highest fusion weight coefficient can be determined as the sub-decision information of this category. By fusing the sub-decision information of each category, the decision information recommended to this family can be determined. For example, taking the needs of the travel destination category as an example, assuming that the fusion weight coefficient of the need to go to a certain place desired by the mother can be 0.55, the fusion weight coefficient of the need to go to a certain city desired by the father is 0.30, and the fusion weight coefficient of the need to go to a certain port desired by the child is 0.66, then the travel destination can be determined as a certain port.

[0072] Since this application can, after obtaining the conversation information among family members, identify the needs of each family member included in the conversation information. For each need, based on the conversation information among family members, it can identify the emotional preference weight coefficient of each family member for this need, and can obtain the discourse weight coefficient of each family member based on the pre-saved portrait information of each family member. After that, based on the emotional preference weight coefficient of each family member for this need and the discourse weight coefficient of each family member, the fusion weight coefficient of this need can be determined. Finally, based on the fusion weight coefficient of each need, the decision information recommended to this family can be determined. Based on this, it is possible to find a balance among the diverse personal needs, emotional preferences, and family member discourse priorities of each family member to the greatest extent accurately, and determine the decision information suitable for each family member accurately and efficiently to the greatest extent.

[0073] In addition, in this application, family members input conversation information, and the electronic device can identify the emotional preferences and needs (implicit needs) of family members by analyzing the conversation information (chat content) among family members. Then, it can quickly and real-time feedback decision information to family members. The operation of family members is simple and the usage threshold is low, which is conducive to the popularization and promotion of the technology.

[0074] Embodiment 2:

[0075] In order to determine the decision information suitable for each family member as accurately and efficiently as possible, on the basis of the above embodiment, in the embodiment of this application, after identifying the needs of each family member included in the conversation information, before determining the fusion weight coefficient of this need based on the emotional preference weight coefficient and the discourse weight coefficient, the method further includes:

[0076] For each of the said requirements, based on the planned event information in the pre-saved family plan list, determine the matching degree between the requirement and the family plan list, and based on the matching degree, determine the planned matching degree weight coefficient of the requirement;

[0077] Said determining the fusion weight coefficient of the requirement based on the emotional preference weight coefficient and the discourse weight coefficient includes:

[0078] Based on the emotional preference weight coefficient, the discourse weight coefficient and the planned matching degree weight coefficient, determine the fusion weight coefficient of the requirement.

[0079] In a possible implementation manner, for each requirement in the dialogue information, in addition to being able to determine the fusion weight coefficient of the requirement based on the emotional preference weight coefficient of each family member for the requirement and the discourse weight coefficient of each family member, it is also possible to determine the matching degree between the requirement and the family plan list based on the event information (for ease of description, referred to as planned event information) in the pre-saved family plan list, and based on the matching degree, determine the planned matching degree weight coefficient of the requirement. Exemplarily, the planned event information in the family plan list may include information such as event type (such as travel, buying a house, etc.), time of the event (such as month, or the first half of the year, the second half of the year), etc. For each requirement, the matching degree between the requirement and the family plan list can be calculated according to the event type, time and other information of the requirement and the planned event information in the family plan list.

[0080] For example, when the planned event information in the family plan list is travel, when the requirement of a certain family member (for ease of description, referred to as requirement 1) is travel, and the requirement of another family member (for ease of description, referred to as requirement 2) is watching a movie, it can be considered that the matching degree between requirement 1 and the family plan list is higher, while the matching degree between requirement 2 and the family plan list is lower.

[0081] In a possible implementation manner, for each requirement, after determining the matching degree between the requirement and the family plan list, the planned matching degree weight coefficient of the requirement can be determined based on the matching degree. Exemplarily, the matching degree can be directly determined as the planned matching degree weight coefficient of the requirement, or the product or sum value of the matching degree and a set value (such as a positive number) can be determined as the planned matching degree weight coefficient of the requirement. The present application does not make specific limitations on this.

[0082] In a possible implementation, for each requirement, when determining the fusion weight coefficient of the requirement, the fusion weight coefficient of the requirement can be determined based on the emotional preference weight coefficient of each family member for the requirement, the speech weight coefficient of each family member, and the plan matching degree weight coefficient of the requirement. Exemplarily, for each requirement, the weighted sum value of the emotional preference weight coefficient of each family member for the requirement and the speech weight coefficient of each family member can be calculated first, and then the sum value of the weighted sum value and the plan matching degree weight coefficient of the requirement can be determined as the final fusion weight coefficient of the requirement.

[0083] For example, still taking a certain requirement as an example, the emotional preference weight coefficient of the mother for the requirement is 1, the emotional preference weight coefficient of the father for the requirement is 0, and the emotional preference weight coefficient of the child for the requirement is -0.5. Among them, the speech weight coefficient of the mother is 0.8, and the speech weight coefficients of the father and the child are 0.5 respectively. Assuming that the plan matching degree weight coefficient of the requirement is 0.6, the final fusion weight coefficient of the requirement can be: 1×0.8 + 0×0.5 + (-0.5)×0.5 + 0.6 = 1.15.

[0084] For ease of understanding, the following uses a specific embodiment to explain the decision information determination process provided by the present application. Refer to Figure 2 , Figure 2 shows a schematic diagram of the second decision information determination process provided by some embodiments. This process includes the following steps:

[0085] S201: Obtain conversation information and identify the requirements of each family member included in the conversation information.

[0086] S202: For each requirement, based on the conversation information, determine the emotional preference weight coefficient of each family member for the requirement; and based on the portrait information of each family member saved in advance, obtain the speech weight coefficient of each family member; based on the planned event information in the family plan list saved in advance, determine the matching degree of the requirement with the family plan list, and based on this matching degree, determine the plan matching degree weight coefficient of the requirement.

[0087] S203: For each requirement, based on the emotional preference weight coefficient of each family member for the requirement, the speech weight coefficient of each family member, and the plan matching degree weight coefficient of the requirement, determine the fusion weight coefficient of the requirement.

[0088] S204: Based on the fusion weight coefficient of each requirement, determine the recommended decision information.

[0089] Embodiment 3:

[0090] To improve the user experience, based on the above embodiments, in the embodiments of the present application, the method further includes:

[0091] Identify the target event type of the decision information, and determine the target decision template corresponding to the target event type according to the pre-stored correspondence between event types and decision templates;

[0092] Fuse the decision information with the target decision template and output the fused decision information.

[0093] In a possible implementation manner, after determining the decision information recommended to the family, in order to facilitate family members to view the recommended decision information, the decision information can be organized into a regular format and displayed to family members for viewing, thereby improving the user (family member) experience. Specifically, the event type of the decision information (referred to as the target event type for convenience of description) can be identified first. The target event type can be, for example, traveling, buying a house, going to school, etc., and the present application does not make specific limitations thereon. When identifying (obtaining) the target event type of the decision information, it can be obtained by performing semantic recognition on the conversation information among family members, or by displaying an input box for family members to input the target event type and using the event type received in the input box as the target event type. The present application does not make specific limitations thereon.

[0094] After obtaining the target event type of the decision information, the target decision template corresponding to the target event type can be determined according to the pre-stored correspondence between event types and decision templates. Then, the decision information can be fused with the target decision template, and the decision information fused with the target decision template can be output for family members to view. Among them, the present application does not make specific limitations on the decision template. Exemplarily, the decision template can include the target event type of the decision information (also referred to as the solution theme), action outline information with a coarser time granularity (such as in days), action details information with a finer time granularity (such as in hours), etc., and can be flexibly set according to requirements.

[0095] Since the present application can identify the target event type of the decision information, determine the target decision template corresponding to the target event type according to the pre-stored correspondence between event types and decision templates, fuse the decision information with the target decision template, and output the decision information fused with the target decision template for family members to view, the decision information viewed by family members is decision information with a relatively regular format, which can improve the user experience.

[0096] For ease of understanding, the following uses a specific embodiment to explain the decision information determination process provided by the present application. Refer to Figure 3 , Figure 3 shows a schematic diagram of the third decision information determination process provided by some embodiments. This process includes the following steps:

[0097] S301: Obtain the conversation information and identify the needs of each family member included in the conversation information.

[0098] S302: For each need, based on the conversation information, determine the emotional preference weight coefficient of each family member for this need; and based on the portrait information of each family member saved in advance, obtain the speech weight coefficient of each family member; based on the planned event information in the pre-saved family plan list, determine the matching degree of this need with the family plan list, and based on this matching degree, determine the planned matching degree weight coefficient of this need.

[0099] S303: For each need, based on the emotional preference weight coefficient of each family member for this need, the speech weight coefficient of each family member, and the planned matching degree weight coefficient of this need, determine the fusion weight coefficient of this need.

[0100] S304: Based on the fusion weight coefficient of each need, determine the recommended decision information.

[0101] S305: Identify the target event type of the decision information, and according to the corresponding relationship between the pre-saved event type and the decision template, determine the target decision template corresponding to the target event type; fuse the decision information with the target decision template and output the fused decision information.

[0102] Example 4:

[0103] Considering that the target decision template corresponding to the pre-saved target event type may not be very suitable for the current decision information. For example, taking tourism as an example, the target decision template may be a template applicable when the tourism time is 7 days, while the tourism time in the current decision information is only 3 days. At this time, the matching degree between the target decision template and the decision information may be poor. In order to improve the matching degree between the target decision template and the decision information, on the basis of the above embodiments, in the embodiment of the present application, after determining the target decision template corresponding to the target event type and before fusing the decision information with the target decision template, the method further includes:

[0104] Determine the matching degree between the field information in the target decision template and the field information in the decision information; if the matching degree is less than the preset matching degree threshold, then update the field information in the target decision template according to the field information in the decision information, and based on the updated target decision template, perform the subsequent step of fusing the decision information with the target decision template.

[0105] In a possible implementation, after determining the target decision template, the matching degree between the field information in the target decision template and the field information in the decision information can be calculated (determined). For example, the matching degree between the number of days information in the "date (time)" field of the target decision template and the number of days information in the "date" field of the decision information can be calculated. Then, it can be determined whether the matching degree is less than a preset matching degree threshold. If the matching degree is not less than (greater than or equal to) the preset matching degree threshold, it can be considered that the target decision template and the decision information are probably matched, and the decision information can be directly fused with the target decision template to output the fused decision information.

[0106] In a possible implementation, when the matching degree between the field information in the target decision template and the field information in the decision information is less than the preset matching degree threshold, it can be considered that the target decision template and the decision information are not well matched. To improve the matching degree between the target decision template and the decision information, the corresponding field information in the target decision template can be updated according to the field information in the decision information. Then, based on the updated target decision template, the decision information can be fused with the updated target decision template. Exemplarily, when the number of days information in the "date (time)" field of the target decision template before update is 7 days, and the number of days information in the "date" field of the decision information is 3 days, and the matching degree of these two field information is less than the preset matching degree threshold, the number of days information in the target decision template can be updated according to the number of days information in the decision information, that is, the number of days information in the target decision template is updated to 3 days, and subsequently, the decision information can be fused with the updated target decision template.

[0107] Since in this application, when the matching degree between the field information in the target decision template and the field information in the decision information is less than the preset matching degree threshold, the field information in the target decision template can be updated according to the field information in the decision information, and based on the updated target decision template, the step of fusing the decision information with the target decision template can be performed, thereby improving the matching degree between the decision information and the target decision template for the fused decision information, and improving the user (family member) experience.

[0108] For ease of understanding, the following uses a specific embodiment to explain the decision information determination process provided by this application. Refer to Figure 4 , Figure 4 shows a schematic diagram of the fourth decision information determination process provided by some embodiments, and this process includes the following steps:

[0109] S401: Obtain the conversation information and identify the needs of each family member included in the conversation information.

[0110] S402: For each requirement, based on the conversation information, determine the emotional preference weight coefficient of each family member for this requirement; and based on the portrait information of each family member saved in advance, obtain the speech weight coefficient of each family member; based on the planned event information in the family plan list saved in advance, determine the matching degree between this requirement and the family plan list, and based on this matching degree, determine the planned matching degree weight coefficient of this requirement.

[0111] S403: For each requirement, based on the emotional preference weight coefficient of each family member for this requirement, the speech weight coefficient of each family member, and the planned matching degree weight coefficient of this requirement, determine the fusion weight coefficient of this requirement.

[0112] S404: Based on the fusion weight coefficient of each requirement, determine the recommended decision information.

[0113] S405: Identify the target event type of the decision information, and based on the corresponding relationship between the event type and the decision template saved in advance, determine the target decision template corresponding to the target event type.

[0114] S406: Determine the matching degree between the field information in the target decision template and the field information in the decision information; if this matching degree is less than the preset matching degree threshold, then update the field information in the target decision template according to the field information in the decision information, fuse the decision information with the updated target decision template, and output the fused decision information.

[0115] Example 5:

[0116] To improve the flexibility of determining the decision information, based on the above embodiments, in the embodiments of the present application, the method further includes:

[0117] If a adjustment instruction for adjusting the decision information is received from the user, identify the preferred requirement carried in the adjustment instruction, and based on the preferred requirement, adjust the decision information.

[0118] In a possible implementation, after presenting the recommended decision information for family members to view, the family members can rate their satisfaction with the decision information recommended by the electronic device. For the decision information with a relatively low satisfaction rating (such as a satisfaction rating lower than a preset score threshold), the electronic device can display an adjustment button. The family member can click the adjustment button and enter the desired requirements (for ease of description, referred to as preferred requirements) to trigger an adjustment instruction for adjusting the decision information. After receiving the adjustment instruction, the electronic device can identify the preferred requirements desired by the family member carried in the adjustment instruction and can adjust the decision information based on the preferred requirements. Exemplarily, the preferred requirements can be newly added requirements of the family member that are not yet in the decision information, or the requirements that the family member is not satisfied with a certain category of requirements in the decision information and desires for that category. This application does not make specific limitations on this.

[0119] In a possible implementation, when the preferred requirement is a newly added requirement of the family member that is not yet in the decision information, the preferred requirement can be directly used as a sub-decision information in the decision information and added to the decision information. When the preferred requirement is the requirement that the family member is not satisfied with a certain category of requirements (sub-decision information) in the decision information and desires for that category, relevant steps such as re-executing S102 - S103 or re-executing S202 - S204 can be performed. The preferred requirement can be used as the requirement with the highest fusion weight coefficient in the requirements of that category, and the preferred requirement can be determined as the sub-decision information of that category. Then, the sub-decision information of each category is fused again, and the decision information recommended to the family is determined again. The family member can be invited again to rate their satisfaction with the decision information until the satisfaction rating of the family member is higher than the preset score threshold. At this time, it can be considered that the family member (user) is relatively satisfied with the recommended decision information, and the process of adjusting the decision information can be exited.

[0120] In a possible implementation, the electronic device can also perform a self-evaluation of the decision information in combination with the satisfaction rating feedback by the user (family member) and the integrity, logic, etc. of the decision information, and output a self-evaluation score for reference by the staff, which will not be elaborated here.

[0121] For ease of understanding, the following uses a specific embodiment to explain the decision information determination process provided by this application. Refer to Figure 5 , Figure 5 shows a schematic diagram of the fifth decision information determination process provided by some embodiments. This process includes the following steps:

[0122] S501: Obtain the conversation information and identify the requirements of each family member included in the conversation information.

[0123] S502: For each requirement, based on the conversation information, determine the emotional preference weight coefficient of each family member for this requirement; and based on the portrait information of each family member pre - saved, obtain the speech weight coefficient of each family member; based on the planned event information in the pre - saved family plan list, determine the matching degree of this requirement with the family plan list, and based on this matching degree, determine the plan matching degree weight coefficient of this requirement.

[0124] S503: For each requirement, based on the emotional preference weight coefficient of each family member for this requirement, the speech weight coefficient of each family member, and the plan matching degree weight coefficient of this requirement, determine the fusion weight coefficient of this requirement.

[0125] S504: Based on the fusion weight coefficient of each requirement, determine the recommended decision information.

[0126] S505: Identify the target event type of the decision information, and according to the corresponding relationship between the pre - saved event type and the decision template, determine the target decision template corresponding to the target event type.

[0127] S506: Determine the matching degree between the field information in the target decision template and the field information in the decision information; if this matching degree is less than the preset matching degree threshold, then according to the field information in the decision information, update the field information in the target decision template, and fuse the decision information with the updated target decision template, and output the fused decision information.

[0128] S507: If an adjustment instruction for adjusting the decision information is received from the user, identify the preferred requirement carried in this adjustment instruction, and based on this preferred requirement, adjust the decision information.

[0129] Embodiment 5:

[0130] To improve efficiency, based on the above - mentioned embodiments, in the embodiment of the present application, after obtaining the conversation information and before identifying the requirements of each family member included in the conversation information, the method further includes:

[0131] Identify the selected conversation information of the set number of rounds at the end of the conversation information, and determine the semantic information of the other conversation information in the conversation information except the selected conversation information;

[0132] Based on the semantic information and the selected conversation information, perform the subsequent steps of identifying the requirements of each family member included in the conversation information.

[0133] In a possible implementation, after obtaining the conversation information and before identifying the needs of each family member included in the conversation information, a preprocessing process for the conversation information can be performed first. Among them, when preprocessing the conversation information, a cleaning process such as removing stop words, removing special characters, and correcting errors can be performed on each round of conversation in the conversation information. Among them, the prior art can be used to perform the cleaning process of the conversation information, which will not be elaborated here.

[0134] In a possible implementation, when preprocessing the conversation information, considering that in the conversation information among family members, the valid information contained in the first few rounds of conversation at the beginning of the conversation is usually less, and the valid information is usually concentrated in the last few rounds of conversation at the end of the conversation. To improve efficiency, before identifying the needs of each family member included in the conversation information, the conversation information of a set number of rounds at the end of the conversation information can be identified first (for ease of description, it is called the selected conversation information). Among them, the specific number of the set number of rounds is not specifically limited in this application. Exemplarily, the last 5 rounds of conversation in the conversation information can be selected as the selected conversation information. And the conversation information of other rounds except the selected selected conversation information in the conversation information can be semantically recognized, and the semantic information of the conversation information of other rounds can be summarized (determined). After that, based on the semantic information of the conversation information of other rounds at the front and the selected conversation information of the set number of rounds at the back, the step of quickly and efficiently identifying the needs of each family member included in the conversation information can be performed. Exemplarily, taking the example that there are 20 rounds of conversation among family members in the conversation information, the last 5 rounds of conversation can be selected as the selected conversation information, the semantic recognition of the first 15 rounds of conversation can be performed, and the semantic information of the first 15 rounds of conversation can be summarized. Finally, based on the semantic information of the first 15 rounds of conversation and the last 5 rounds of selected conversation information, the needs of each family member included in the conversation information can be determined (identified).

[0135] For ease of understanding, the following uses a specific embodiment to explain the decision information determination process provided by this application. Refer to Figure 6 , Figure 6 shows a schematic diagram of the sixth decision information determination process provided by some embodiments. This process includes the following steps:

[0136] S601: Obtain the conversation information among family members.

[0137] S602: Identify the selected conversation information of a set number of rounds at the end of the conversation information, and determine the semantic information of the other conversation information except the selected conversation information in the conversation information; based on this semantic information and the selected conversation information, identify the needs of each family member included in the conversation information.

[0138] In a possible implementation, when the needs of family members in the conversation information are not recognized, a prompt message for family members to re-enter the conversation information can be output. Family members can re-enter the conversation information, and the electronic device can recognize the needs of each family member included in the conversation information again.

[0139] S603: For each need, based on the conversation information, determine the emotional preference weight coefficient of each family member for this need; and based on the portrait information of each family member saved in advance, obtain the speech weight coefficient of each family member; based on the planned event information in the family plan list saved in advance, determine the matching degree between this need and the family plan list, and based on this matching degree, determine the planned matching degree weight coefficient of this need; then, based on the emotional preference weight coefficient of each family member for this need, the speech weight coefficient of each family member, and the planned matching degree weight coefficient of this need, determine the fusion weight coefficient of this need. Based on the fusion weight coefficient of each need, determine the recommended decision information.

[0140] Among them, the steps in S603 can also be called the steps of summarizing needs.

[0141] After determining the fusion weight coefficient of each need, decision-making algorithms such as the Analytic Hierarchy Process (also known as the multi-scheme decision-making method, Analytic Hierarchy Process, AHP), Technique for Order Preference by Similarity to an Ideal Solution (also known as the distance method of superior and inferior solutions, Technique for Order Preference by Similarity to an Ideal Solution, TOPSIS), and Multi-Criteria Decision Analysis (MCDA) can be used to maximize the accuracy of the recommended decision information, which will not be elaborated here.

[0142] S604: Identify the target event type of the decision information, and determine the target decision template corresponding to the target event type according to the correspondence between the event type and the decision template saved in advance.

[0143] S605: Determine the matching degree between the field information in the target decision template and the field information in the decision information; if this matching degree is less than the preset matching degree threshold, then update the field information in the target decision template according to the field information in the decision information, and based on the updated target decision template, fuse the decision information with the updated target decision template, and output the fused decision information.

[0144] Among them, the outline part in the target decision-making template can be self-optimized for the outline structure through the constructed Reflection module, large model prompts, etc. The process of self-optimizing the outline structure can adopt existing technologies and will not be elaborated here.

[0145] In addition, when fusing decision-making information with the target decision-making template, a generative model can be run, such as large language models like Bidirectional Encoder Representations from Transformers (bert), Wenyan Yixin, Generalized Linear Model (GLM), etc., to fuse the decision-making information with the target decision-making template to form a complete and fused decision-making information (solution). In addition, during the fusion process, text splicing technology and formatting technology can also be used to ensure the logic and readability of the fused decision-making information, which will not be elaborated here.

[0146] For ease of understanding, the decision-making information determination process provided by this application will be further explained through a specific embodiment below. Refer to Figure 7 , Figure 7 shows a schematic diagram of the seventh decision-making information determination process provided by some embodiments. This process includes the following steps:

[0147] S701: Obtain the conversation information among family members.

[0148] S702: Identify the selected conversation information of the set number of turns at the end of the conversation information, and determine the semantic information of the other conversation information in the conversation information except the selected conversation information; based on this semantic information and the selected conversation information, identify the needs of each family member included in the conversation information.

[0149] S703: For each need, based on the conversation information, determine the emotional preference weight coefficient of each family member for this need; and based on the pre-saved portrait information of each family member, obtain the speech weight coefficient of each family member; based on the emotional preference weight coefficient of each family member for this need and the speech weight coefficient of each family member, determine the fusion weight coefficient of this need. Based on the fusion weight coefficient of each need, determine the recommended decision-making information.

[0150] S704: Identify the target event type of the decision-making information, and determine the target decision-making template corresponding to the target event type according to the pre-saved correspondence between the event type and the decision-making template.

[0151] S705: Determine the matching degree between the field information in the target decision template and the field information in the decision information; if the matching degree is less than the preset matching degree threshold, update the field information in the target decision template according to the field information in the decision information, and based on the updated target decision template, fuse the decision information with the updated target decision template, and output the fused decision information.

[0152] For ease of understanding, the decision information determination process provided by this application will be further explained through a specific embodiment below. Refer to Figure 8 , Figure 8 which shows a schematic diagram of the eighth decision information determination process provided by some embodiments. This process includes the following steps:

[0153] S801: Obtain the conversation information among family members.

[0154] S802: Identify the selected conversation information of the set number of turns at the end of the conversation information, and determine the semantic information of the other conversation information except the selected conversation information in the conversation information; based on this semantic information and the selected conversation information, identify the needs of each family member included in the conversation information.

[0155] S803: For each need, based on the conversation information, determine the emotional preference weight coefficient of each family member for this need; and based on the portrait information of each family member saved in advance, obtain the speech weight coefficient of each family member; based on the planned event information in the family plan list saved in advance, determine the matching degree between this need and the family plan list, and based on this matching degree, determine the planned matching degree weight coefficient of this need; then, based on the emotional preference weight coefficient of each family member for this need, the speech weight coefficient of each family member, and the planned matching degree weight coefficient of this need, determine the fusion weight coefficient of this need. Based on the fusion weight coefficient of each need, determine the recommended decision information.

[0156] S804: Identify the target event type of the decision information, and according to the corresponding relationship between the event type and the decision template saved in advance, determine the target decision template corresponding to the target event type, and fuse the decision information with the target decision template, and output the fused decision information.

[0157] S805: If an adjustment instruction for adjusting the decision information is received from the user, identify the preferred need carried in the adjustment instruction, and adjust the decision information based on this preferred need.

[0158] Embodiment 6:

[0159] Based on the same technical concept, this application provides a decision information determination device. Refer to Figure 9 , Figure 9The figure shows a schematic diagram of a decision information determination device provided by some embodiments. The device includes:

[0160] An identification module 901, configured to obtain conversation information and identify the needs of each family member included in the conversation information;

[0161] A determination module 902, configured to, for each of the needs, determine, based on the conversation information, an emotional preference weight coefficient of each family member for the need; and obtain a speech weight coefficient of each family member based on the pre-stored portrait information of each family member; and determine a fusion weight coefficient of the need based on the emotional preference weight coefficient and the speech weight coefficient;

[0162] A recommendation module 903, configured to determine the recommended decision information based on the fusion weight coefficient of each of the needs.

[0163] In a possible implementation manner, the determination module 902 is further configured to:

[0164] For each of the needs, determine a matching degree between the need and the family plan list based on the plan event information in the pre-stored family plan list, and determine a plan matching degree weight coefficient of the need based on the matching degree;

[0165] Determine the fusion weight coefficient of the need based on the emotional preference weight coefficient, the speech weight coefficient, and the plan matching degree weight coefficient.

[0166] In a possible implementation manner, the device further includes:

[0167] A fusion module 904, configured to identify the target event type of the decision information, and determine a target decision template corresponding to the target event type according to the corresponding relationship between the pre-stored event type and the decision template;

[0168] Fuse the decision information with the target decision template and output the fused decision information.

[0169] In a possible implementation manner, the fusion module 904 is further configured to:

[0170] Determine the matching degree between the field information in the target decision template and the field information in the decision information; if the matching degree is less than a preset matching degree threshold, update the field information in the target decision template according to the field information in the decision information, and perform the subsequent step of fusing the decision information with the target decision template based on the updated target decision template.

[0171] In a possible implementation manner, the device further includes:

[0172] An adjustment module 905, configured to, if receiving an adjustment instruction for the adjustment decision information input by a user, identify the preferred requirements carried in the adjustment instruction, and based on the preferred requirements, adjust the decision information.

[0173] In a possible implementation manner, the recognition module 901 is further configured to:

[0174] Identify the selected dialogue information of a set number of rounds that is located later in the dialogue information, and determine the semantic information of other dialogue information in the dialogue information except the selected dialogue information;

[0175] Based on the semantic information and the selected dialogue information, perform the subsequent step of identifying the requirements of each family member included in the dialogue information.

[0176] Embodiment 7:

[0177] Based on the same technical concept, the present application further provides an electronic device, Figure 10 showing a schematic structural diagram of an electronic device provided by some embodiments, as Figure 10 shown, the electronic device includes: a processor 1001, a communication interface 1002, a memory 1003, and a communication bus 1004, where the processor 1001, the communication interface 1002, and the memory 1003 complete mutual communication through the communication bus 1004;

[0178] A computer program is stored in the memory 1003, and when the program is executed by the processor 1001, the processor 1001 is caused to execute the following steps:

[0179] Obtain dialogue information, and identify the requirements of each family member included in the dialogue information;

[0180] For each of the requirements, based on the dialogue information, determine the emotional preference weight coefficient of each family member for the requirement; and based on the portrait information of each family member saved in advance, obtain the speech weight coefficient of each family member; based on the emotional preference weight coefficient and the speech weight coefficient, determine the fusion weight coefficient of the requirement;

[0181] Based on the fusion weight coefficient of each requirement, determine the recommended decision information.

[0182] In a possible implementation manner, the processor 1001 is further configured to:

[0183] For each of the requirements, based on the planned event information in the pre-saved family plan list, determine the matching degree of the requirement with the family plan list, and based on the matching degree, determine the planned matching degree weight coefficient of the requirement;

[0184] Determine the fusion weight coefficient of the requirement based on the emotional preference weight coefficient, the discourse weight coefficient, and the plan matching degree weight coefficient.

[0185] In a possible implementation manner, the processor 1001 is further configured to:

[0186] Identify the target event type of the decision information, and determine the target decision template corresponding to the target event type according to the pre-stored correspondence between the event type and the decision template;

[0187] Fuse the decision information with the target decision template, and output the fused decision information.

[0188] In a possible implementation manner, the processor 1001 is further configured to:

[0189] Determine the matching degree between the field information in the target decision template and the field information in the decision information; if the matching degree is less than the preset matching degree threshold, update the field information in the target decision template according to the field information in the decision information, and based on the updated target decision template, perform the subsequent step of fusing the decision information with the target decision template.

[0190] In a possible implementation manner, the processor 1001 is further configured to:

[0191] If an adjustment instruction for adjusting the decision information is received from the user, identify the preferred requirement carried in the adjustment instruction, and adjust the decision information based on the preferred requirement.

[0192] In a possible implementation manner, the processor 1001 is further configured to:

[0193] Identify the selected dialogue information of the set number of turns at the later position in the dialogue information, and determine the semantic information of the other dialogue information in the dialogue information except the selected dialogue information;

[0194] Based on the semantic information and the selected dialogue information, perform the subsequent step of identifying the requirements of each family member included in the dialogue information.

[0195] The communication bus mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience in representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0196] The communication interface 1002 is used for communication between the above electronic device and other devices.

[0197] The memory may include a Random Access Memory (RAM), or may also include a Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0198] The above processor may be a general-purpose processor, including a central processing unit, a Network Processor (NP), etc.; it may also be a Digital Signal Processing (DSP), an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0199] Embodiment 8:

[0200] Based on the same technical concept, an embodiment of the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program executable by an electronic device. When the program runs on the electronic device, it enables the electronic device to implement any of the above embodiments when executed. Since the principle of the computer-readable storage medium for solving problems is similar to that of the decision information determination method, the implementation of the computer-readable storage medium can refer to the implementation of the method, and the repeated parts will not be described again.

[0201] The above computer-readable storage medium may be any available medium or data storage device accessible by the processor in the electronic device, including but not limited to magnetic memories such as floppy disks, hard disks, magnetic tapes, magneto-optical discs (MO), etc., optical memories such as CDs, DVDs, BDs, HVDs, etc., and semiconductor memories such as ROMs, EPROMs, EEPROMs, Non-Volatile Memories (NAND FLASH), Solid State Drives (SSD), etc.

[0202] Based on the same inventive concept, the present application provides a computer program product, which includes computer program code that, when running on a computer, enables the computer to execute the method described in any of the method embodiments applied to an electronic device as described above.

[0203] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof, and can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part.

[0204] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0205] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0206] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0207] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the steps specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 in one block or a plurality of blocks.

[0208] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A method for determining decision information, characterized in that: The method comprises: Acquire the conversation information and identify the needs of each family member contained in the conversation information; For each of the requirements, based on the conversation information, determine the emotional preference weight coefficient of each family member for the requirement; and based on the pre-saved portrait information of each family member, obtain the speech weight coefficient of each family member; based on the emotional preference weight coefficient and the speech weight coefficient, determine the fusion weight coefficient of the requirement; Based on the fusion weight coefficient of each of the requirements, the recommended decision information is determined.

2. The method according to claim 1, characterized in that After identifying the needs of each family member included in the dialogue information, and before determining the fusion weight coefficient of the needs based on the emotion preference weight coefficient and the speech weight coefficient, the method further includes: For each of the requirements, based on the planned event information in the pre-saved family plan list, determining the matching degree between the requirement and the family plan list, and based on the matching degree, determining the plan matching weight coefficient of the requirement; The determining of the fusion weight coefficient of the demand based on the emotion preference weight coefficient and the discourse weight coefficient includes: Based on the emotion preference weight coefficient, the discourse weight coefficient and the plan matching weight coefficient, the fusion weight coefficient of the demand is determined.

3. The method according to claim 1 or 2, characterized in that: The method further comprises: Identifying the target event type of the decision information, and determining the target decision template corresponding to the target event type according to the pre-saved correspondence between the event type and the decision template; The decision information is fused with the target decision template, and the fused decision information is output.

4. The method according to claim 3, characterized in that After determining the target decision template corresponding to the target event type and before fusing the decision information with the target decision template, the method further includes: Determine the degree of match between the field information in the target decision template and the field information in the decision information; if the degree of match is less than a preset degree of match threshold, update the field information in the target decision template according to the field information in the decision information, and perform subsequent steps of fusing the decision information with the target decision template based on the updated target decision template.

5. The method according to claim 3, characterized in that: The method further comprises: If an adjustment instruction input by a user to adjust the decision information is received, a preferred requirement carried in the adjustment instruction is identified, and the decision information is adjusted based on the preferred requirement.

6. The method according to any one of claims 1-2, 4-5, characterized in that: After acquiring the conversation information and before identifying the needs of each family member contained in the conversation information, the method further includes: identifying selected dialogue information of a set number of rounds that is located later in the dialogue information, and determining semantic information of other dialogue information in the dialogue information except the selected dialogue information; A subsequent step of identifying the needs of each family member contained in the conversation information is performed based on the semantic information and the selected conversation information.

7. A decision information determination device, characterized in that: The device comprises: an identification module, used to obtain the conversation information and identify the needs of each family member contained in the conversation information; A determination module, for determining, for each of the requirements, based on the conversation information, the emotional preference weight coefficient of each family member for the requirement; and obtaining the speech weight coefficient of each family member based on the pre-saved portrait information of each family member; and determining the fusion weight coefficient of the requirement based on the emotional preference weight coefficient and the speech weight coefficient; The recommendation module is used to determine the recommended decision information based on the fusion weight coefficient of each of the requirements.

8. The device according to claim 7, characterized in that The determining module is further used for: For each of the requirements, based on the planned event information in the pre-saved family plan list, determining the matching degree between the requirement and the family plan list, and based on the matching degree, determining the plan matching weight coefficient of the requirement; Based on the emotion preference weight coefficient, the discourse weight coefficient and the plan matching weight coefficient, the fusion weight coefficient of the demand is determined.

9. An electronic device, characterized in that: The electronic device comprises at least a processor and a memory, and the processor is used to implement the steps of any one of the methods according to claims 1-6 when executing a computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Images